Registro públicoModerado
Informe de salud del softwareesquema 0.26.0 · métricas 1.13.0 · 2026-07-22 19:51 UTC
jjang-ai / jangq
JANG — GGUF for MLX. YOU MUST USE JANG_Q RUNTIME. Adaptive Mixed-Precision Quantization + Runtime for Apple Silicon
jjang-ai/jangq tiene un índice de salud de 54 sobre 100, lo que lo sitúa en la banda Moderado. Su puntuación más alta es Vitality (82/100) y la más baja, Security (26/100). Se actualizó por última vez hoy. Una sola persona concentra la mayor parte del trabajo reciente.
54
global / 100Índice de salud del software
Las métricas se agrupan en categorías ponderadas sobre una escala de 1 a 100. El resultado global parte de su media; cuando la evidencia pública activa la Política de Jurisdicciones de Alto Riesgo, la calificación se ajusta y recibe el límite 49 (En riesgo). Preparación para IA queda fuera.
54
Excelente85-100Ejemplar; cumple prácticamente todos los criterios evaluados
Bueno70-84Saludable; carencias menores
Moderado50-69Aceptable con carencias notables; se recomienda revisión
En riesgo30-49Debilidades significativas; su adopción exige cautela
Crítico1-29Problemas graves (proyecto abandonado, un solo mantenedor, sin higiene)
Perfil de puntuación
Cada eje es una categoría. La forma importa más que la media: un proyecto sano llena toda la figura, mientras que un perfil de picos y cráteres indica que la fortaleza en una dimensión enmascara el riesgo en otra.
Titularidad
Eric Jinho JangCuenta personal
217 seguidores8 repositorios públicosdesde jul 2023Osaurus.ai
Este repositorio pertenece a una cuenta personal. Un proyecto con un único propietario conlleva más riesgo de continuidad que uno respaldado por una organización.
Ecosistemas de paquetes
| Registro | Paquete | Versión | Descargas / mes | Versiones | Última publicación | Etiquetas |
|---|---|---|---|---|---|---|
| PyPI | jang | 2.5.33 | - | 43 | hace 0 días | quantizationllmapple-siliconmetalmlxjangmoemixed-precision |
Métricas por categoría
Vitalidad
¿Está vivo el proyecto: se escribe código y se publican versiones?
82
Actividad de desarrollo
76Bueno
Cómo se puntúa
| 36/36 | Recencia de push — último push hace 0 días |
| 11.8/36 | Cadencia de commits — 17/52 semanas con commits |
| 18/18 | Volumen de commits — 565 commits en el último año |
| 10/10 | OpenSSF Scorecard: Maintained — 30 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 10 |
Datos de entrada utilizados
| commits_last_year | 565 |
| human_commit_share | 1 |
| days_since_last_push | 0 |
| active_weeks_last_year | 17 |
Disciplina de publicación
90Excelente
Cómo se puntúa
| 27/27 | Publica versiones — 9 versiones publicadas |
| 36/36 | Recencia de las versiones — última versión hace 0 días |
| 27/27 | Cadencia de publicación — una versión cada ~15,4 días |
| 0/10 | OpenSSF Scorecard: Signed-Releases — Project has not signed or included provenance with any releases. |
Datos de entrada utilizados
| releases_count | 9 |
| latest_release_tag | v2.5.33 |
| releases_from_tags | no |
| days_since_latest_release | 0 |
| mean_days_between_releases | 15,4 |
Comunidad y Adopción
¿Tiene el proyecto usuarios, descargas, atención y unas condiciones acogedoras para quienes contribuyen?
39
Popularidad y adopción
51Moderado
Cómo se puntúa
| 37.8/60 | Estrellas — 214 estrellas |
| 11.8/25 | Forks — 27 forks |
| 1.7/15 | Observadores — 3 observadores |
Datos de entrada utilizados
| forks | 27 |
| stars | 214 |
| watchers | 3 |
| growth_state | unverified |
| growth_factor_pct | 100 |
| growth_unverified_reason | no_history |
Salud de la comunidad
25Crítico
Cómo se puntúa
| 22.5/22.5 | README |
| 0/22.5 | Licencia — no se detectó ningún archivo de licencia |
| 0/18 | Guía CONTRIBUTING |
| 0/13.5 | Código de conducta |
| 0/7.2 | Plantilla de issues |
| 0/6.3 | Plantilla de PR |
Datos de entrada utilizados
| has_readme | sí |
| has_license | no |
| has_contributing | no |
| has_issue_template | no |
| has_code_of_conduct | no |
| has_pull_request_template | no |
Sostenibilidad y Gobernanza
¿Sobrevivirá el proyecto a sus personas: factor bus, capacidad de respuesta, quién lo respalda y mantenimiento del paquete?
39
Cómo se puntúa
| 9/54 | Factor bus — la mitad de los commits recae en 1 contribuyente(s) |
| 0/22.5 | Distribución de commits — el principal contribuyente firma el 100% de los commits |
| 1.4/13.5 | Amplitud de contribuyentes — 1 contribuyentes |
| 3/10 | OpenSSF Scorecard: Contributors — project has 1 contributing companies or organizations -- score normalized to 3 |
Datos de entrada utilizados
| bus_factor | 1 |
| contributors_sampled | 1 |
| top_contributor_share | 1 |
Capacidad de respuesta a issues y PR
12Crítico
Cómo se puntúa
| 4.7/46.8 | Resolución de issues — 10% de issues cerradas |
| 7.7/38.3 | Aceptación de PR — 1/5 PR decididos fusionados |
| 0/15 | OpenSSF Scorecard: Code-Review — Found 0/30 approved changesets -- score normalized to 0 |
Datos de entrada utilizados
| merged_prs | 1 |
| open_issues | 9 |
| closed_issues | 1 |
| issue_closed_ratio | 0,1 |
| closed_unmerged_prs | 4 |
Propiedad y custodia
50Moderado
Cómo se puntúa
| 10/30 | Respaldo de la propiedad — cuenta personal (usuario) |
| 0/20 | Dominio verificado — no aplicable a cuentas de usuario |
| 16.8/25 | Alcance del propietario — 217 seguidores de jjang-ai |
| 13.1/25 | Trayectoria — 8 repos públicos, cuenta de ~3 años |
Datos de entrada utilizados
| followers | 217 |
| owner_type | User |
| is_verified | — |
| owner_login | jjang-ai |
| public_repos | 8 |
| account_age_days | 1115 |
Excluidos de la puntuación (sin datos o no aplicable): Dominio verificado. Los pesos restantes se han renormalizado.
Mantenimiento de paquetes
100Excelente
Cómo se puntúa
| 25/25 | Publicado y resoluble — 1 paquete(s) en pypi |
| 35/35 | Recencia de publicación — última publicación hace 0 días |
| 20/20 | Historial de versiones — 43 versiones en el registro |
| 20/20 | No obsoleto — activo, ni obsoleto ni retirado |
Datos de entrada utilizados
| packages | jang |
| ecosystems | pypi |
| any_deprecated | no |
| min_days_since_publish | 0 |
Calidad de Ingeniería
¿Existen unas prácticas mínimas de ingeniería y documentación?
76
Prácticas de ingeniería
60Moderado
Cómo se puntúa
| 24/24 | Flujos de trabajo de CI — 1 flujo(s) de trabajo |
| 24/24 | Pruebas presentes |
| 0/16 | Configuración de linter |
| 0/9.6 | Hooks de pre-commit |
| 0/6.4 | .editorconfig |
| 0/20 | OpenSSF Scorecard: CI-Tests — sin datos |
Datos de entrada utilizados
| has_ci | sí |
| has_tests | sí |
| has_editorconfig | no |
| has_linter_config | no |
| has_precommit_config | no |
Excluidos de la puntuación (sin datos o no aplicable): OpenSSF Scorecard: CI-Tests. Los pesos restantes se han renormalizado.
Documentación
100Excelente
Cómo se puntúa
| 30/30 | README |
| 25/25 | Directorio de documentación |
| 15/15 | Sitio de documentación / página del proyecto — https://jangq.ai/ |
| 10/10 | Descripción del repositorio |
| 10/10 | Topics — 10 topics |
| 10/10 | Wiki |
Datos de entrada utilizados
| topics | gguf, llamacpp, llm, mlx, mlxllm, quantization, apple-silicon, jang-quantization, omlx, omlx-alternative |
| has_wiki | sí |
| homepage | https://jangq.ai/ |
| has_readme | sí |
| has_docs_dir | sí |
| has_description | sí |
Seguridad
¿Son sólidas las prácticas visibles de seguridad y de cadena de suministro, sin exposición jurisdiccional de alto riesgo sin resolver?
26
Postura de seguridad
26Crítico
Cómo se puntúa
| 7.5/7.5 | Binary-Artifacts — no binaries found in the repo |
| 0/7.5 | Branch-Protection — branch protection not enabled on development/release branches |
| 0/2.5 | CI-Tests — sin datos |
| 0/2.5 | CII-Best-Practices — no effort to earn an OpenSSF best practices badge detected |
| 0/7.5 | Code-Review — Found 0/30 approved changesets -- score normalized to 0 |
| 0.8/2.5 | Contributors — project has 1 contributing companies or organizations -- score normalized to 3 |
| 10/10 | Dangerous-Workflow — no dangerous workflow patterns detected |
| 0/7.5 | Dependency-Update-Tool — no update tool detected |
| 0/5 | Fuzzing — project is not fuzzed |
| 0/2.5 | Licencia — license file not detected |
| 7.5/7.5 | Maintained — 30 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 10 |
| 0/5 | Packaging — sin datos |
| 0/5 | Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 0 |
| 0/5 | SAST — no SAST tool detected |
| 0/5 | Security-Policy — security policy file not detected |
| 0/7.5 | Signed-Releases — Project has not signed or included provenance with any releases. |
| 0/7.5 | Token-Permissions — detected GitHub workflow tokens with excessive permissions |
| 0/7.5 | Vulnerabilities — 34 existing vulnerabilities detected |
Datos de entrada utilizados
| source | openssf_scorecard |
| checks_evaluated | 16 |
| scorecard_version | v5.5.0 |
| checks_inconclusive | 2 |
| scorecard_aggregate | 2,6 |
Excluidos de la puntuación (sin datos o no aplicable): ci_tests, packaging. Los pesos restantes se han renormalizado.
Preparación para IA
¿Hasta qué punto está el repositorio preparado para desarrollarse y mantenerse con agentes de codificación de IA? Es una insignia independiente y experimental — peso 0,0, de modo que se presenta por separado y no afecta a la puntuación de salud global.
34
Contexto y guía para agentes
24Crítico
Cómo se puntúa
| 0/45 | Instrucciones para agentes — sin CLAUDE.md / AGENTS.md / reglas de editor |
| 0/15 | Documentación legible por máquinas (llms.txt) |
| 24.5/40 | Historial de commits legible — 46 de 100 commits humanos declaran su intención (asunto estructurado o cuerpo explicativo) |
Datos de entrada utilizados
| has_llms_txt | no |
| legible_history_share | 0,46 |
| agent_instruction_files | — |
| agent_instruction_max_bytes | — |
Cómo se puntúa
| 0/18 | Arranque con un solo comando |
| 22/22 | Pruebas automatizadas |
| 0/11 | Configuración de lint / formato |
| 0/11 | Verificación estática de tipos |
| 10/10 | Entorno reproducible — lockfile |
| 0/10 | Práctica demostrada con agentes — ningún commit con autoría de agente entre los últimos 100 |
| 0/8 | Mantenimiento automatizado — no se observan actualizaciones automáticas de dependencias |
| 0/10 | OpenSSF Scorecard: Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 0 |
Datos de entrada utilizados
| has_nix | no |
| has_tests | sí |
| lockfiles | uv.lock |
| has_dockerfile | no |
| typed_language | no |
| bootstrap_files | — |
| has_devcontainer | no |
| has_linter_config | no |
| typecheck_configs | — |
| agent_commit_share | 0 |
| toolchain_manifests | — |
| dependency_bot_commit_share | 0 |
Legibilidad del código para modelos
54Moderado
Cómo se puntúa
| 0/45 | Código verificable por tipos — Python sin configuración de verificación de tipos |
| 54.5/55 | Tamaños de archivo manejables — 5/589 archivos fuente de más de 60 KB |
Datos de entrada utilizados
| primary_language | Python |
| largest_source_bytes | 99.406 |
| source_files_sampled | 589 |
| oversized_source_files | 5 |
Interfaces legibles por máquina
40En riesgo
Cómo se puntúa
| 0/40 | Esquema de API (OpenAPI/GraphQL/proto) |
| 0/20 | Servidor MCP |
| 40/40 | Ejemplos ejecutables — examples |
Datos de entrada utilizados
| example_dirs | examples |
| has_mcp_signal | no |
| api_schema_files | — |
Datos clave
214estrellas de GitHub
1contribuidores
565commits en los últimos 12 meses
0días desde el último push
9versiones publicadas
1factor bus
9issues abiertas
PyPIecosistemas de paquetes
Advertencias de recopilación de datos
- Star history unavailable: GitHub GraphQL error: Resource not accessible by personal access token
- Could not fetch pypi package 'jang-ralph-runner' from its registry
- GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository
- deps.dev does not index pypi:jang@2.5.33; advisories assessed against the repository dependency graph instead
Más detalle
Historial de estrellas y forks 0 ★ / 27 ⇿
0Estrellas
27Forks
8Versiones
Cuándo se añadió cada estrella y fork, recopilado de GitHub y agrupado por día. El crecimiento acumulado se sitúa justo encima de las adiciones diarias que lo componen, de modo que ambos se leen en conjunto: la acumulación orgánica sostenida no se parece en nada a un pico abrupto y efímero. Cuando esa diferencia es medible, se informa como autenticidad del crecimiento.
Mayor 0Menor 1Parche 5
OpenSSF Scorecard 2.6 / 10
2.6agregado
Evaluación de seguridad independiente y agnóstica en cuanto a herramientas, procedente del proyecto de código abierto OpenSSF Scorecard. Cada comprobación premia una práctica de seguridad, no la herramienta de un proveedor concreto. Las comprobaciones que Scorecard no pudo determinar se marcan como n/d y se excluyen de la puntuación de seguridad (nunca se cuentan como cero).
| 10 | Binary-Artifacts | no binaries found in the repo |
| 0 | Branch-Protection | branch protection not enabled on development/release branches |
| n/d | CI-Tests | no pull request found |
| 0 | CII-Best-Practices | no effort to earn an OpenSSF best practices badge detected |
| 0 | Code-Review | Found 0/30 approved changesets -- score normalized to 0 |
| 3 | Contributors | project has 1 contributing companies or organizations -- score normalized to 3 |
| 10 | Dangerous-Workflow | no dangerous workflow patterns detected |
| 0 | Dependency-Update-Tool | no update tool detected |
| 0 | Fuzzing | project is not fuzzed |
| 0 | License | license file not detected |
| 10 | Maintained | 30 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 10 |
| n/d | Packaging | packaging workflow not detected |
| 0 | Pinned-Dependencies | dependency not pinned by hash detected -- score normalized to 0 |
| 0 | SAST | no SAST tool detected |
| 0 | Security-Policy | security policy file not detected |
| 0 | Signed-Releases | Project has not signed or included provenance with any releases. |
| 0 | Token-Permissions | detected GitHub workflow tokens with excessive permissions |
| 0 | Vulnerabilities | 34 existing vulnerabilities detected |
Dependencias directas 8
| Registro | Paquete | Restricción de versión | Manifiesto |
|---|---|---|---|
| PyPI | safetensors | >=0.4 | jang-tools/pyproject.toml |
| PyPI | numpy | >=1.24 | jang-tools/pyproject.toml |
| PyPI | tqdm | >=4.60 | jang-tools/pyproject.toml |
| PyPI | huggingface_hub | >=0.20 | jang-tools/pyproject.toml |
| PyPI | jinja2 | >=3.1 | jang-tools/pyproject.toml |
| PyPI | ruamel.yaml | >=0.18 | ralph_runner/pyproject.toml |
| PyPI | huggingface_hub | >=0.20 | ralph_runner/pyproject.toml |
| PyPI | rich | >=13.0 | ralph_runner/pyproject.toml |
Todas las dependencias no recopilado
No fue posible recopilar el conjunto de dependencias resuelto para este informe: GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository
Informe JSON sin procesar legible por máquina
{
"data": {
"repo": {
"topics": [
"gguf",
"llamacpp",
"llm",
"mlx",
"mlxllm",
"quantization",
"apple-silicon",
"jang-quantization",
"omlx",
"omlx-alternative"
],
"is_fork": false,
"size_kb": 98331,
"has_wiki": true,
"homepage": "https://jangq.ai/",
"languages": {
"Jinja": 4802,
"Metal": 64647,
"Shell": 16933,
"Swift": 1131018,
"Python": 3900023
},
"pushed_at": "2026-07-22T18:49:02Z",
"created_at": "2026-03-15T11:11:16Z",
"owner_type": "User",
"updated_at": "2026-07-22T19:16:30Z",
"description": "JANG — GGUF for MLX. YOU MUST USE JANG_Q RUNTIME. Adaptive Mixed-Precision Quantization + Runtime for Apple Silicon",
"is_archived": false,
"is_disabled": false,
"license_spdx": null,
"default_branch": "main",
"license_spdx_raw": null,
"primary_language": "Python",
"significant_languages": [
"Python",
"Swift"
]
},
"owner": {
"blog": null,
"name": "Eric Jinho Jang",
"type": "User",
"login": "jjang-ai",
"company": "Osaurus.ai",
"location": null,
"followers": 217,
"avatar_url": "https://avatars.githubusercontent.com/u/138501656?v=4",
"created_at": "2023-07-03T14:06:32Z",
"is_verified": null,
"public_repos": 8,
"account_age_days": 1115
},
"license": {
"state": "absent",
"spdx_id": null,
"raw_spdx": null,
"file_present": false,
"scorecard_found": false,
"profile_has_license": false
},
"activity": {
"releases": [
{
"tag": "v2.5.33",
"kind": "patch",
"published_at": "2026-07-22T18:51:13Z"
},
{
"tag": "v2.5.29",
"kind": "patch",
"published_at": "2026-05-13T02:13:16Z"
},
{
"tag": "v2.5.28",
"kind": "patch",
"published_at": "2026-05-12T10:38:31Z"
},
{
"tag": "v2.5.18",
"kind": "patch",
"published_at": "2026-05-04T21:47:19Z"
},
{
"tag": "v2.5.8",
"kind": "patch",
"published_at": "2026-04-26T01:27:07Z"
},
{
"tag": "jang-studio-v1.0.1",
"kind": "other",
"published_at": "2026-04-22T02:11:25Z"
},
{
"tag": "jang-studio-v1.0.0",
"kind": "other",
"published_at": "2026-04-22T00:41:23Z"
},
{
"tag": "v2.2.0",
"kind": "minor",
"published_at": "2026-03-23T04:31:15Z"
},
{
"tag": "v2.1.5",
"kind": "patch",
"published_at": "2026-03-21T22:23:08Z"
}
],
"recent_commits": [
{
"oid": "b788273e47b0f5be834d85c5b31e757b34e4d950",
"body": null,
"is_bot": false,
"headline": "fix(laguna): publish mixed-affine runtime contract",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-07-22T18:47:52Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "801209c13c189ebb8fb4d1596748a336f568da38",
"body": null,
"is_bot": false,
"headline": "docs(laguna): finalize integration review evidence",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-07-22T04:18:10Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "dd220b8c778f7e3219f4a2eb54fe25e9dabbdd74",
"body": null,
"is_bot": false,
"headline": "fix(jang): validate storage widths and clarify Laguna AWQ",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-07-22T04:17:36Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "aa9ce009cff354771b9ef475f4877a2754cbfa34",
"body": null,
"is_bot": false,
"headline": "docs(laguna): record storage-width review fix",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-07-22T04:13:57Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f5d4077813910e7b854f0b497424be567f72780e",
"body": null,
"is_bot": false,
"headline": "fix(jang): keep one-bit storage out of allocation",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-07-22T04:13:43Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "85ec5fe48f59bbb0d35daa9ebb2d2c934dc1ef8b",
"body": null,
"is_bot": false,
"headline": "docs(laguna): record clean package build",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-07-22T04:08:19Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "19566b205a1623453b011c5d303718e8dc3d0a97",
"body": null,
"is_bot": false,
"headline": "docs(laguna): record release integration proof boundary",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-07-22T04:07:22Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "994b8111d4d4969057e9da8925a9f04bdb216892",
"body": null,
"is_bot": false,
"headline": "jang: preserve one-bit affine storage metadata",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-07-22T04:02:23Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d2b45418d8010a067399edc480a20c0cc51b0280",
"body": "NOTES.md: 10-point inference checklist (bf16 stream, wired limit,\nper-layer-type masks, keep=0, layer-indexed attention, softplus gate\nwidth branch, router math, eos [2,24]/no-double-BOS, thinking-on default,\nper-module quant bits), session changelog, verification protocol with\ninterpretation nuance\n[…]\n-forced pre/post-window agreement is the real gate).\npython_example.py: smoke / chat / teacher-forced parity drivers.\nSWIFT.md: vmlx-swift port checklist ordered by the audited M.1\nlayer-indexing bug.",
"is_bot": false,
"headline": "docs: laguna-s21 runtime notes, examples, Swift port checklist",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-07-22T04:00:44Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "f8127a22e260f7450108b068f83ceff22262098f",
"body": "Capture runs the REAL jang_tools.laguna.model.LagunaLayer in MLX — not a\nhand-rolled torch forward — so the capture math is the verified runtime\nmath by construction (per-layer heads, dual RoPE/partial rotary, softplus\ngating, sigmoid+bias routing). Streams the 235 GB source with a 2-shard\nLRU (~10 \n[…]\nsured on S-2.1 (corpus_v3 8x512): absmean alpha=0.25 wins at BOTH\n2-bit (+2.4% reconstruction vs the alpha=0 no-AWQ baseline) and 4-bit\n(+2.9%), 0/144384 inert channels. Shipped bundles are AWQ-based.",
"is_bot": false,
"headline": "laguna: AWQ capture (MLX layer-streaming) + cross-family awq_search fix",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-07-22T04:00:44Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "19b021dac7982cee2b69b90b9932ea78fce4d6e4",
"body": "poolside/Laguna-S-2.1 (118B-A8B, 48 layers, 256 routed top-10 + shared,\ndense L0, hybrid 12 full/36 SWA with per-layer head counts 48/72).\nProfiles: JANG_2L = the proven M.1 recipe byte-for-byte (routed 2/2/3,\nattn+g_proj 8, shared/dense/embed 6, lm_head 8, gs64), JANG_3L 3/3/4,\nJANG_4M 4/4/4 with s\n[…]\ncoherent) with a loud warning at <=3-bit;\n--awq folds captured scales into routed+shared gate/up and the router gate\nwith the inverse on post_attention_layernorm, keeping routing logits\nbit-identical.",
"is_bot": false,
"headline": "laguna: S-2.1 all-affine JANG converter + FAMILY_MAP registration",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-07-22T04:00:44Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "39bf08514a60d756c8fd239ebd9597501f677fd2",
"body": "fp16 stream (bundle sidecar dtype) NaN'd S-2.1-JANG_4M: the residual\ngrows ~4 -> 942k across 48 layers and the L46 MoE intermediate overflows\nfp16's 65504 ceiling -> inf -> NaN logits -> argmax 0 -> UNK spam. The\nsource is torch_dtype=bfloat16; cast all fp16 params to bf16 at load so\nQuantizedLinear\n[…]\ned under decode —\n4M measured 14.0 -> 32.6 tok/s wired; 2L was silently throttled too\n(31.9 -> 48.3). Auto-stamp min(bundle*1.2 + 8GB, 118GB); the 118 GB\nceiling is Ornith-proven on the 128 GB M5 Max.",
"is_bot": false,
"headline": "laguna: bf16 activation stream + wired-limit auto-stamp",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-07-22T04:00:44Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "ddb5639232b0c553725ac8603cdac9982c9eb3f8",
"body": "Two hybrid-attention bugs, both invisible below the 512-token window:\n\n1. __call__ built ONE causal mask from caches[0] and fed it to every\n layer. Layer 0 is full attention (plain KVCache), so mlx_lm returned\n the 'causal' fast path and SWA layers attended the whole prefix on\n prompts > 512. \n[…]\nhed==no-cache greedy parity across the window. Both bugs\nverified caught via negative controls. Verified on the real S-2.1 118B:\nteacher-forced top-1 agreement 1.000 across 2401 post-window positions.",
"is_bot": false,
"headline": "laguna: per-layer-type prefill masks + RotatingKVCache keep=0",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-07-22T04:00:44Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "c6dfb47f46c7b95231944d8e03225ea63b5fe436",
"body": "Laguna-M.1-JANG_2L is a jang-affine-mixed bundle (per-module bits in\nconfig.json[quantization]: attention 8-bit, MoE gate/up/down 6-bit, some\nrouted experts 2/3-bit). Two load-path bugs made it emit a dequant error\nand empty output:\n\n1. runtime.py affine path called nn.quantize with a single top-lev\n[…]\n keeps the broadcast,\n per-element multiplies elementwise into the flattened attention out.\n\nLive-proven: loads in 13s, coherent generation (capital-of-France ->\nParis), no dequant/broadcast errors.",
"is_bot": false,
"headline": "laguna: fix mixed-precision affine load + per-element attention gating",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-07-22T04:00:35Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "ca75f0cb6622673f79009f82d25cbedb205931ce",
"body": null,
"is_bot": false,
"headline": "fix(mistral3): keep text runtime independent of Pixtral",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-07-21T21:45:27Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "ee3f6faad04b17b7b081e33e5990d2838beacfc6",
"body": null,
"is_bot": false,
"headline": "fix(dsv4): bound lazy long-prefill graph lifetime",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-07-21T06:27:10Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "70b2a7fb08f2ddbe183954399377caf4334501d5",
"body": null,
"is_bot": false,
"headline": "fix(omni): stream native decode tokens",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-07-19T20:42:00Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "000e41c7c69240c226663e80cd9e96dca3745167",
"body": null,
"is_bot": false,
"headline": "fix(turboquant): preserve wide NAX activation range",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-07-19T13:53:14Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "9081c92476a63b912f4d2ce96146674971b5c83e",
"body": null,
"is_bot": false,
"headline": "Preserve attention dtype in TurboQuant KV cache",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-07-16T15:52:41Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "8260f889423e43688c907c2f27bf69e8a7522791",
"body": "…ut AudioConfig)\n\n_mlx_vlm_skeleton force-injected audio_config={} into every bundle config;\nupdate_module_configs treats any non-None value as a real audio component and\nresolves model_class.AudioConfig — which step3p7 does not define, so every\nStep-3.7 JANGTQ load died with AttributeError. Default the key to None: the\ndataclass shape keeps the field, the module-config update correctly skips it,\nand bundles that actually ship audio still declare audio_config themselves.",
"is_bot": false,
"headline": "load_jangtq_vlm: stop forcing audio_config={} (crashes families witho…",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-07-12T23:31:04Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "affa817d59d5ccf22d8e7f6939abb7a3793906ba",
"body": "2026-07-10 depth sweep on Hy3-JANG_2K-MTP (greedy 600-tok x3/arm): baseline\n27.8 tok/s; d1 30.6 (+10%, ~full acceptance); d2 26.3 (-6%, 24.5% accept);\nd3 19.1 (-31%, 1.9% accept). Depth 1 is the only profitable depth for the\nhy3 head; write vmlx_mtp_tuning.json so the engine autodetects it.",
"is_bot": false,
"headline": "hy3: stamp measured MTP tuning sidecar (best_depth=1) on preserve builds",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-07-11T01:44:53Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "e89f976b4c4095ebb0c7e054b1fe5c2eb2ee068b",
"body": "Loop gate on the final post-train (2026-07-10): at temp 0.9 the 2-bit routed\ntail loops with top_p>=0.95 (3/6 seeds at 1.0, 2/6 at 0.95); top_p 0.9 and\nmin_p 0.05 each independently drop it to 0/6. The converter was stamping the\nvendor recommendation (0.9/1.0/-1) verbatim into chat.sampling_defaults\n[…]\nemperature 0.9 + top_p 0.9 + min_p 0.05 instead (min_p also covers\nthe MoE chunked-prefill cold/warm routing nudge). Vendor values remain in\ngeneration_config; explicit request params always override.",
"is_bot": false,
"headline": "hy3: stamp audited chat sampling defaults — floor the 2-bit tail",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-07-10T23:44:51Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "7daf8955c6770f87afbe4f74396f0ecc25ce1baf",
"body": null,
"is_bot": false,
"headline": "hy3: zero num_nextn_predict_layers when MTP dropped (synced from max2)",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-07-10T19:56:58Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "9b6e4fc658410970eaa3bbbf8fafbbd758a1f1ef",
"body": null,
"is_bot": false,
"headline": "hy3: JANG_2L drops MTP by default (synced from max2 8af9f12)",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-07-10T19:41:59Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "e9ad23461ce9800dae9aea1579b37dc5f5f8d461",
"body": null,
"is_bot": false,
"headline": "hy3: lm_head via quantized_matmul (synced from max2)",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-07-10T05:25:48Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "ca60bcb228c79349c99c6424b453a66684a3f4dd",
"body": null,
"is_bot": false,
"headline": "hy3 converter: scalar quantization.bits + bits_by_role (synced)",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-07-10T05:18:59Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "b14736fb2925db9c38b5823eb27d9c414d4ee784",
"body": "… max2)",
"is_bot": false,
"headline": "hy3 converter: canonical capabilities + hard-fail verify (synced from…",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-07-10T05:17:13Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "2fc2c65b3bfcf87db2faef445b30063c6d56c683",
"body": null,
"is_bot": false,
"headline": "hy3: exact bundle size estimator (synced from max2)",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-07-10T04:54:20Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d6bce9ff830fa9630bc3fcd041d64fc5ac7e9268",
"body": null,
"is_bot": false,
"headline": "hy3: AWQ scale selection by measured error (synced from max2)",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-07-10T04:37:07Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "2fbc8e49be4effb4ef05730eb89cf41018341ee8",
"body": null,
"is_bot": false,
"headline": "hy3: awq_capture — per-read shard open/close (box thrash fix)",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-07-10T04:25:13Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "8f6e707372ee6d0998ce94d6b7f64c8f207bc67c",
"body": "…ning)",
"is_bot": false,
"headline": "hy3: awq_capture — per-layer torch.mps.empty_cache (MPS SIGABRT harde…",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-07-10T03:50:41Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "bc111ebc9226742cf27bc941eaaf555f1f10fc40",
"body": "…shes MPSGraph)",
"is_bot": false,
"headline": "hy3: awq_capture — use SDPA is_causal (fp32 mask vs bf16 operands cra…",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-07-10T01:37:38Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d5d6787c853a499da179abc8e8e4b7b387f88290",
"body": "…e MTP head (synced from max2)",
"is_bot": false,
"headline": "hy3: final-release JANG_2L all-affine converter + AWQ capture + nativ…",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-07-10T01:21:49Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f468269ec0288d8934b65208654a77930fe4470f",
"body": "Laguna-XS.2-mxfp4 failed to load with\n ValueError: Module does not have parameter named \"experts\".\n\nThe affine converters (JANG_*, MXFP4) do not ship routed experts unpacked.\nThey pre-stack them and fuse gate+up into a single tensor:\n layers.L.mlp.experts.gate_up_proj.{weight,scales,biases} (\n[…]\n0 layers, 256 experts): the engine loads\nand produces coherent output (\"...its capital is a well-known city. I think the\ncapital is Paris.\"), which also confirms the gate/up halves are not transposed.",
"is_bot": false,
"headline": "laguna: split fused affine expert tensors so MXFP4/JANG bundles load",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-07-09T19:02:08Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "b10f7fcf37414499b37f856a43846c2995484455",
"body": "The two lineages had each accumulated work the other lacked. origin/main\ncarried the reasoning parsers, the expanded quant_shape_inference, the\ngemma4 `_patch_chat_template` decomposition and the `_resolve_modality`\nexplicit-has_vision fix. The local lineage carried n2 expert pruning\n(`_is_n2_expert\n[…]\nndent path so the test no longer depends on being run from the\n repo root.\n- pyproject: union -- origin`s description and gemma4/mimo-v2 entry points\n plus the local qwen35 mxfp4/mxfp8 entry points.",
"is_bot": false,
"headline": "Merge origin/main into the local jang-tools lineage",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-07-09T18:43:36Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "a8fa5294b7fd314470aecc762596007297903815",
"body": "…ime_metadata\n\nResolve the four unmerged files left by an interrupted `git stash pop`.\n`convert.py`, `format/writer.py` and `examples/mtp/inspect_mtp_bundle.py` had\nbeen left holding the STASHED side, which would have reverted committed work:\nwriter.py's per-module quantization manifest (a uniform t\n[…]\nn2 override test no longer depends on cwd; mimo_v2 SWA test asserts\n the KVCache the runtime actually builds; except-Exception threshold raised to\n 199 to cover the untracked MXTQ/MXRQ lane modules.",
"is_bot": false,
"headline": "jang-tools: finish the interrupted stash-pop; restore _stamp_mtp_runt…",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-07-09T18:39:54Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "e70f22082236e36be99072d9ec946264265d5db4",
"body": "…ert pruning, Qwen3.5 MXFP4/MXFP8 converters, Step3p7/DSV4/Nemotron tools + tests",
"is_bot": false,
"headline": "jang-tools: add MiniMax-M3 + MiMo-V2(+VLM) conversion tooling, n2 exp…",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-06-21T07:49:23Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "314468f70525b56be91949f37cc2d052e8466872",
"body": "…g, Qwen3.5 MXFP4/MXFP8 converters, allocation summaries + tests",
"is_bot": false,
"headline": "jang-tools: MiniMax-M3 + MiMo-V2 conversion tooling, n2 expert prunin…",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-06-21T07:45:00Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "a72394be479d42a23f8f892117d56e440d7c622b",
"body": null,
"is_bot": false,
"headline": "Update runtime package capabilities",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-06-11T23:17:52Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "8e9d9c785ae053c4f244da65b0442a124f2bb59a",
"body": null,
"is_bot": false,
"headline": "Add Step3p7 JANG runtime bridge",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-06-11T22:29:24Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "81c1dc5ea7d34154c651194750d5c975fcf2c6f7",
"body": null,
"is_bot": false,
"headline": "Add Step3p7 JANG runtime bridge",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-06-11T22:28:19Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f994144d8e8ed2370d401e9bcce73f7ad6acc497",
"body": null,
"is_bot": false,
"headline": "Update jang tools runtime package surface",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-06-10T00:34:03Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "3f1bac506a56fb2172581ed46523c173b1a21675",
"body": null,
"is_bot": false,
"headline": "Fix JANG Studio runner cancellation",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-06-10T00:20:20Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "3ed8f09304e6eb0cd2d4d0de593fb14203f6e75c",
"body": null,
"is_bot": false,
"headline": "Build JANG Studio Swift tests in CI",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-06-09T23:56:53Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "9eb66f0f8e9fd57a308be9f9281a94dc4fe27e95",
"body": null,
"is_bot": false,
"headline": "Bound JANG Studio Swift test duration",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-06-09T23:49:24Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "b627e3cba721dd922c587119878dcc9488e6829b",
"body": null,
"is_bot": false,
"headline": "Limit JANG Studio CI scheme to unit tests",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-06-09T23:41:54Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "494a5490c4c1a5fc7b543343d98ad9cadda53dd9",
"body": null,
"is_bot": false,
"headline": "Fix WizardFlowTests Swift isolation",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-06-09T23:32:31Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "a8b853151a68de175297a2f66e06d89a2945ef7d",
"body": null,
"is_bot": false,
"headline": "Fix CoverageMatrixTests Swift isolation",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-06-09T23:28:33Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "25ecbc1f0676358b71fe1a11c5058cf3ad351610",
"body": null,
"is_bot": false,
"headline": "Fix AppSettingsTests Swift isolation",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-06-09T23:24:45Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "e124f79d95dddb0ad9c91051193848699a34e33b",
"body": null,
"is_bot": false,
"headline": "Skip NAX tests without MPP headers",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-06-09T23:20:27Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "6bbca6f54eef27fee791cde3e295b874076cb194",
"body": null,
"is_bot": false,
"headline": "Fix JANG Studio Python CI deps",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-06-09T23:16:41Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "0e447d9cbab25112799b74e544a52fe486fcffac",
"body": null,
"is_bot": false,
"headline": "Record Gemma4 JANG4M HF uploads",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-06-09T23:11:57Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "fefebbed3f6d87fd805b8faa3a02b6a6e53819a6",
"body": null,
"is_bot": false,
"headline": "Fix Gemma4 QAT JANG4M conversion",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-06-09T23:11:57Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "9caf7bcc4f5110db5d29e2578b6aac557d14fa01",
"body": null,
"is_bot": false,
"headline": "Fix MiMo JANGTQ VLM hydration",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-06-08T11:56:25Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d67d75327e089347a63faddb9eff1acc437a0d9a",
"body": null,
"is_bot": false,
"headline": "Accept MiMo prestacked JANGTQ bundles",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-06-07T10:17:27Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c00fed310ac168e6d3dd62604025dfc69fa5413a",
"body": null,
"is_bot": false,
"headline": "Document MiMo Python VL runtime gap",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-06-06T17:29:05Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "98f57a6897cf3a07bdfea1f0ccf0ca265ed73d58",
"body": null,
"is_bot": false,
"headline": "Keep MiMo media metadata text-only until wired",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-06-06T14:58:08Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "9532380c82eb09463e9ee70507bbd7576ac05f20",
"body": null,
"is_bot": false,
"headline": "Fix MiMo manual sink boolean masks",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-06-06T08:59:08Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "9e5709e5ea8c47394b911680a7f3754874250e28",
"body": null,
"is_bot": false,
"headline": "Add MiMo sink runtime probe",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-06-06T08:51:35Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d1316c3a1bcd7f4eeef899ffbc1ced729cfa0780",
"body": null,
"is_bot": false,
"headline": "Add MiMo V2 JANG runtime support",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-06-06T04:09:12Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "ea3f36c4033108c2ae3ade1393e19805ea9d6946",
"body": "…template\n\nThe shipped Gemma 4 template lists tools but has no tool_choice branch, so\nOpenAI tool_choice:required was not encoded in the prompt. _copy_sidecars now\npatches chat_template.jinja (native Gemma format, fires only on required) and\nfolds the patched template into tokenizer_config.json so rebuilt MXFP4/MXFP8/\nJANG bundles keep the fix.",
"is_bot": false,
"headline": "gemma4 converter: inject conditional tool_choice==required into chat …",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-06-03T19:57:47Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "1750fbd20fa6b5a1eabf656b78b8a470346fd26e",
"body": "- convert_gemma4_mxfp: MXFP4/MXFP8 for the dense, omni-modal gemma4_unified\n release. convert_gemma4_jang: JANG_4M (8-bit affine attention + 4-bit affine\n MLP/embed) with a correct mixed-bit per-module quantization config.\n- Handle the gemma4-specific traps: scale_shift=0 RMSNorm (norms passed thr\n[…]\nl.->language_model.model.), and no MTP.\n- Register gemma4_unified / gemma4_unified_text in the capability FAMILY_MAP.\n- Add runtime contract docs/runtime/2026-06-03-gemma4-12b-unified-runtime-spec.md.",
"is_bot": false,
"headline": "Add Gemma 4 12B (gemma4_unified) MXFP4/MXFP8/JANG converters",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-06-03T19:29:01Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "72bf517edd8a2e1a6dc7663edbd96971749ed713",
"body": null,
"is_bot": false,
"headline": "fix: handle qwen vl frame-list video fallback",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-06-01T08:54:25Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "0c3c576cbf22c26d91035d721062afb888b0b9c8",
"body": null,
"is_bot": false,
"headline": "fix: fallback for vlm video processor dependency errors",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-05-31T05:12:25Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "7eb20644f22316c9d5b69b2d233fd43c8440f6d4",
"body": null,
"is_bot": false,
"headline": "fix: repair qwen affine shape ambiguity",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-05-23T23:41:25Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "173e6c33df324d9e6c55762d2ec1238adf0b0072",
"body": null,
"is_bot": false,
"headline": "docs: refresh dsv4 vmlx blocker status",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-05-23T22:56:02Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "8c476c350f387a945efac7ea7069335099918f04",
"body": null,
"is_bot": false,
"headline": "fix: stamp hy3 long-output chat defaults",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-05-23T08:10:52Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "b5f66a75aab052d3db141e460436964c96bea9f8",
"body": null,
"is_bot": false,
"headline": "fix: cache materialized dsv4 pool reads",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-05-22T20:47:21Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "49e558e06c3b0c4e08329a7ce9b5229113987389",
"body": null,
"is_bot": false,
"headline": "fix: append dsv4 pool quant rows",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-05-22T19:18:27Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "09ca9a8132d2306e01fd55b7df58feb6c24b78c4",
"body": null,
"is_bot": false,
"headline": "test: track dsv4 v3 helper contracts",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-05-22T15:26:38Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4e270e9911b905b279e987fc90617fdf5d0fc5ff",
"body": null,
"is_bot": false,
"headline": "docs: update dsv4 vmlx release blocker",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-05-22T14:22:19Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "1b693bcca1195c27f8637810cff0343bdc32200e",
"body": null,
"is_bot": false,
"headline": "docs: record dsv4 vmlx quality blocker",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-05-22T12:46:27Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "496e2233ab53737a0e303a45f868ef53cdf28c62",
"body": null,
"is_bot": false,
"headline": "test: pin dsv4 high precision rebuild lane",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-05-22T11:50:54Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "b6a8f8908e847df4b2f354028a86394ac6a9aab9",
"body": null,
"is_bot": false,
"headline": "docs: update dsv4 vmlx quality blocker",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-05-22T07:58:50Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "2ca4cabfb9028d5d58df2bc5ce6137b6a39b039d",
"body": null,
"is_bot": false,
"headline": "docs: record dsv4 vmlx quality blocker",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-05-22T07:23:54Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "7f643ed57806c38d015e9d7f0a094c48b7e47484",
"body": null,
"is_bot": false,
"headline": "dsv4: preserve flash rope scaling metadata",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-05-20T19:36:55Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4431a9350257a78022438c4145d1faed510981c7",
"body": null,
"is_bot": false,
"headline": "dsv4: add affine projection tuning controls",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-05-18T02:07:50Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "61d73ac08a06a3a96ceee9f05636096bd6c2fe62",
"body": null,
"is_bot": false,
"headline": "feat: add DSV4 affine JANG-K projection plan",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-05-17T12:06:50Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4129f287859c018259c09290d27f9b8b03d64b3d",
"body": null,
"is_bot": false,
"headline": "Add Qwen MXFP4 MTP bundle support",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-05-15T21:43:52Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d236dc1a2acb52e09d7bf43f52add466b65e4fde",
"body": null,
"is_bot": false,
"headline": "Preserve Qwen MTP and VL in JANG conversion",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-05-15T21:03:55Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "6f6f01235d22d8bd7e9143a93cdd66bdf317f7e3",
"body": null,
"is_bot": false,
"headline": "jang-tools: harden JANGTQ M5 dispatch defaults",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-05-15T07:15:22Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "460a0a59c5ef39d377d98ebc78ed63858dff4238",
"body": null,
"is_bot": false,
"headline": "Harden Nemotron Omni encoder view",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-05-13T08:48:35Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "1df306c951fcbf09bd0b7c7c55b08c5b4212b3f4",
"body": null,
"is_bot": false,
"headline": "Correct Kimi artifact verification paths",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-05-13T02:18:07Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "e0c5a81fb34a63f1547030902044a4b99d3f2345",
"body": null,
"is_bot": false,
"headline": "Release jang 2.5.29",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-05-13T02:11:26Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f1f336cd4370633fa2ec44793b1a7fd49a052111",
"body": null,
"is_bot": false,
"headline": "Add Kimi JANGTQ_K conversion profile",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-05-13T00:44:37Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "2be5c5f83a29b326a762b323869423990887a59f",
"body": null,
"is_bot": false,
"headline": "Add JANGTQ MPP NAX TensorOps lane",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-05-12T20:50:07Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f378bd3748742d1a060184a7fca4038f8d8baf80",
"body": null,
"is_bot": false,
"headline": "Release jang 2.5.28",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-05-12T10:35:47Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "0baf523cfdea043aaf65233ac6df0a08c5a936e3",
"body": null,
"is_bot": false,
"headline": "Fix DSV4 mHC pure fallback",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-05-12T04:26:40Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c11679a29609ae1ad0c759f28ef219525f0f45cb",
"body": null,
"is_bot": false,
"headline": "Harden DSV4 V3 plan metadata",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-05-12T02:09:41Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "1025fd0d23fc6fc75dcb6feed32f7cf2f8385fc8",
"body": null,
"is_bot": false,
"headline": "Adjust exception-site threshold for latest taxonomy count",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-05-11T19:29:36Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "46d99ddf01c04716c4e1a130a0a649f684b04a09",
"body": null,
"is_bot": false,
"headline": "Fix Nemotron Omni media runtime paths",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-05-11T05:02:54Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "607eee1a8d60f83b0805dabcb58f94fbda535e26",
"body": null,
"is_bot": false,
"headline": "Harden JANGTQ runtime release paths",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-05-11T04:16:26Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "1d55ebaf9e28fabe61e3312cdc61da13ecde96eb",
"body": null,
"is_bot": false,
"headline": "Add TurboQuant KV batch cache API",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-05-10T19:16:57Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c7b2abf0816c8018f691e87ac5b9cd690eaeec5c",
"body": null,
"is_bot": false,
"headline": "fix(hy3): document JANGTQ1 coherence boundary",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-05-10T09:54:02Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "ee076810a991346224af7aad3abd6f84fe37071c",
"body": null,
"is_bot": false,
"headline": "Harden Hy3 JANGTQ runtime registration",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-05-10T09:47:47Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f7167d531c1a4cd446456bd0593f603b7b7516e6",
"body": "Adds jang_tools/zaya1_vl/ package mirroring laguna/mistral3/dsv4/zaya/hy3\npattern. The 816-line model.py is the canonical Zaya1VL adapter (CCA\nattention + top-1 MOD/MoE language trunk + Qwen2.5-VL vision tower +\nimage-token LoRA gating + sanitize that maps language_model.* / lm_head /\npatch_embed.pr\n[…]\ntils)\n are importable. Try-except on the actual import + pytest.skip with a\n clear message.\n\nTests: 448 passed, 9 skipped (the dsv4 v3 contract pre-existing failures\nremain ignored for this commit).",
"is_bot": false,
"headline": "feat(zaya1_vl): port Zaya1VL adapter from vmlx into jang-tools",
"author_name": "Eric",
"author_login": null,
"committed_at": "2026-05-10T09:45:28Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "89367e2977b02636ac43dab65d6f3fe763033253",
"body": "Adds Hy3 JANGTQ1 as an experimental size-floor profile: routed expert gate/up/down projections use 1-bit MXTQ while attention, shared expert, dense FFN, embeddings, lm_head, and MTP matmuls stay at 8-bit affine.\n\nAdds early vector-packing guards for routed expert input widths, JANGTQ1 support in the\n[…]\nshed size after conversion completes.\n\nJANGTQ2 remains the first 128 GB release candidate. Hy3 MTP remains preserved_disabled until an accept/reject speculative runtime path is implemented and tested.",
"is_bot": false,
"headline": "feat(hy3): add experimental JANGTQ1 profile",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-05-10T09:27:44Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "8b42b21308f8aece8d6382e8e33c85c2c069aa89",
"body": null,
"is_bot": false,
"headline": "Harden Hy3 top-k runtime path",
"author_name": "Jinho Jang",
"author_login": "jjang-ai",
"committed_at": "2026-05-10T08:49:11Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "3338630e5b117ba42cbb3f90b92162bbe245cb9f",
"body": "ZAYA reasons by default — measured live with the runtime port:\n`enable_thinking=False` (the template's default closed </think> block)\nstill produces chain-of-thought output (\"Okay, I need to calculate...\nstep by step...\") for the 17×23 prompt. Same for enable_thinking=True\nmodulo template framing.\n\n\n[…]\ny: replaced bare except: pass at load_jangtq.py:79 with\nspecific (TypeError, ValueError, ZeroDivisionError) catch — the\nexception-invariant test caught it after Codex's recent JANGTQ\nloader hardening.",
"is_bot": false,
"headline": "fix(capabilities): mark zaya/zaya1_vl supports_thinking=True",
"author_name": "Eric",
"author_login": null,
"committed_at": "2026-05-10T08:31:12Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "51befe2c60673b8d971bb4cc7272141de4062268",
"body": "Adds jang_tools/topk_override.py: a model-walk helper that lowers MoE\nrouters' per-token expert count below the trained K to trade quality\nfor decode speed. Mechanism is universal across MoE families — Hy3,\ndots1, DSV3/V4, qwen3_moe, bailing/ling, laguna, minimax all expose\ntop_k on their router cla\n[…]\n/ when not to use, future work.\n\nQuality caveat: only short smoke prompts validated. HumanEval, MMLU,\nlong reasoning chains have not been A/B-ed. Always measure before\nshipping K<trained as a default.",
"is_bot": false,
"headline": "feat(topk): universal MoE inference-time top-K override",
"author_name": "Eric",
"author_login": null,
"committed_at": "2026-05-10T08:25:52Z",
"body_truncated": true,
"is_coding_agent": false
}
],
"releases_count": 9,
"commits_last_year": 565,
"latest_release_at": "2026-07-22T18:51:13Z",
"latest_release_tag": "v2.5.33",
"releases_from_tags": false,
"days_since_last_push": 0,
"active_weeks_last_year": 17,
"days_since_latest_release": 0,
"mean_days_between_releases": 15.4
},
"community": {
"has_readme": true,
"has_license": false,
"has_description": true,
"has_contributing": false,
"health_percentage": 28,
"has_issue_template": false,
"has_code_of_conduct": false,
"has_pull_request_template": false
},
"ecosystem": {
"packages": [
{
"name": "jang",
"exists": true,
"license": "Apache-2.0",
"keywords": [
"quantization",
"llm",
"apple-silicon",
"metal",
"mlx",
"jang",
"moe",
"mixed-precision",
"Development Status :: 4 - Beta",
"Intended Audience :: Developers",
"Intended Audience :: Science/Research",
"Operating System :: MacOS",
"Programming Language :: Python :: 3",
"Programming Language :: Python :: 3.11",
"Programming Language :: Python :: 3.12",
"Programming Language :: Python :: 3.13",
"Topic :: Scientific/Engineering :: Artificial Intelligence"
],
"ecosystem": "pypi",
"matches_repo": true,
"registry_url": "https://pypi.org/project/jang/",
"is_deprecated": false,
"latest_version": "2.5.33",
"repository_url": "https://github.com/jjang-ai/jangq",
"versions_count": 43,
"total_downloads": null,
"dependents_count": null,
"deprecation_note": null,
"maintainers_count": null,
"monthly_downloads": null,
"first_published_at": "2026-03-16T08:05:31.871805Z",
"latest_published_at": "2026-07-22T18:50:15.686040Z",
"latest_version_yanked": null,
"days_since_latest_publish": 0
}
]
},
"popularity": {
"forks": 27,
"stars": 214,
"watchers": 3,
"fork_history": {
"days": [
{
"date": "2026-03-19",
"count": 1
},
{
"date": "2026-03-20",
"count": 1
},
{
"date": "2026-03-25",
"count": 2
},
{
"date": "2026-03-29",
"count": 1
},
{
"date": "2026-04-04",
"count": 1
},
{
"date": "2026-04-05",
"count": 1
},
{
"date": "2026-04-07",
"count": 2
},
{
"date": "2026-04-08",
"count": 2
},
{
"date": "2026-04-09",
"count": 1
},
{
"date": "2026-04-14",
"count": 1
},
{
"date": "2026-04-15",
"count": 1
},
{
"date": "2026-04-19",
"count": 1
},
{
"date": "2026-04-23",
"count": 2
},
{
"date": "2026-04-27",
"count": 2
},
{
"date": "2026-04-28",
"count": 1
},
{
"date": "2026-05-09",
"count": 1
},
{
"date": "2026-05-18",
"count": 1
},
{
"date": "2026-06-11",
"count": 1
},
{
"date": "2026-06-27",
"count": 1
},
{
"date": "2026-07-05",
"count": 1
},
{
"date": "2026-07-10",
"count": 1
},
{
"date": "2026-07-12",
"count": 1
}
],
"complete": true,
"collected": 27,
"total_forks": 27
},
"star_history": null,
"open_issues_and_prs": 14
},
"ai_readiness": {
"has_nix": false,
"example_dirs": [
"examples"
],
"has_llms_txt": false,
"has_dockerfile": false,
"has_mcp_signal": false,
"bootstrap_files": [],
"api_schema_files": [],
"has_devcontainer": false,
"typecheck_configs": [],
"toolchain_manifests": [],
"largest_source_bytes": 99406,
"source_files_sampled": 589,
"oversized_source_files": 5,
"agent_instruction_files": [],
"agent_instruction_max_bytes": null
},
"dependencies": {
"manifests": [
"jang-tools/pyproject.toml",
"ralph_runner/pyproject.toml"
],
"advisories": {
"error": null,
"scope": null,
"source": null,
"findings": [],
"collected": false,
"malicious": [],
"truncated": false,
"by_severity": {},
"advisory_count": 0,
"affected_count": 0,
"assessed_count": 0,
"malicious_count": 0,
"assessed_package": null,
"unassessed_count": 0,
"direct_affected_count": 0
},
"ecosystems": [
"pypi"
],
"dependencies": [
{
"name": "safetensors",
"manifest": "jang-tools/pyproject.toml",
"ecosystem": "pypi",
"version_constraint": ">=0.4"
},
{
"name": "numpy",
"manifest": "jang-tools/pyproject.toml",
"ecosystem": "pypi",
"version_constraint": ">=1.24"
},
{
"name": "tqdm",
"manifest": "jang-tools/pyproject.toml",
"ecosystem": "pypi",
"version_constraint": ">=4.60"
},
{
"name": "huggingface_hub",
"manifest": "jang-tools/pyproject.toml",
"ecosystem": "pypi",
"version_constraint": ">=0.20"
},
{
"name": "jinja2",
"manifest": "jang-tools/pyproject.toml",
"ecosystem": "pypi",
"version_constraint": ">=3.1"
},
{
"name": "ruamel.yaml",
"manifest": "ralph_runner/pyproject.toml",
"ecosystem": "pypi",
"version_constraint": ">=0.18"
},
{
"name": "huggingface_hub",
"manifest": "ralph_runner/pyproject.toml",
"ecosystem": "pypi",
"version_constraint": ">=0.20"
},
{
"name": "rich",
"manifest": "ralph_runner/pyproject.toml",
"ecosystem": "pypi",
"version_constraint": ">=13.0"
}
],
"all_dependencies": {
"error": "GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository",
"source": null,
"packages": [],
"collected": false,
"truncated": false,
"total_count": null,
"direct_count": null,
"indirect_count": null
}
},
"maintainership": {
"issues": {
"open_prs": 5,
"merged_prs": 1,
"open_issues": 9,
"closed_ratio": 0.1,
"closed_issues": 1,
"closed_unmerged_prs": 4
},
"bus_factor": 1,
"bot_contributors": 0,
"top_contributors": [
{
"type": "User",
"login": "jjang-ai",
"commits": 567,
"avatar_url": "https://avatars.githubusercontent.com/u/138501656?v=4"
}
],
"contributors_sampled": 1,
"top_contributor_share": 1
},
"quality_signals": {
"has_ci": true,
"has_tests": true,
"ci_workflows": [
"jang-studio.yml"
],
"has_docs_dir": true,
"linter_configs": [],
"has_editorconfig": false,
"has_linter_config": false,
"has_precommit_config": false
},
"security_signals": {
"lockfiles": [
"uv.lock"
],
"scorecard": {
"checks": [
{
"name": "Binary-Artifacts",
"score": 10,
"reason": "no binaries found in the repo",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#binary-artifacts"
},
{
"name": "Branch-Protection",
"score": 0,
"reason": "branch protection not enabled on development/release branches",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#branch-protection"
},
{
"name": "CI-Tests",
"score": null,
"reason": "no pull request found",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#ci-tests"
},
{
"name": "CII-Best-Practices",
"score": 0,
"reason": "no effort to earn an OpenSSF best practices badge detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#cii-best-practices"
},
{
"name": "Code-Review",
"score": 0,
"reason": "Found 0/30 approved changesets -- score normalized to 0",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#code-review"
},
{
"name": "Contributors",
"score": 3,
"reason": "project has 1 contributing companies or organizations -- score normalized to 3",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#contributors"
},
{
"name": "Dangerous-Workflow",
"score": 10,
"reason": "no dangerous workflow patterns detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#dangerous-workflow"
},
{
"name": "Dependency-Update-Tool",
"score": 0,
"reason": "no update tool detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#dependency-update-tool"
},
{
"name": "Fuzzing",
"score": 0,
"reason": "project is not fuzzed",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#fuzzing"
},
{
"name": "License",
"score": 0,
"reason": "license file not detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#license"
},
{
"name": "Maintained",
"score": 10,
"reason": "30 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 10",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#maintained"
},
{
"name": "Packaging",
"score": null,
"reason": "packaging workflow not detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#packaging"
},
{
"name": "Pinned-Dependencies",
"score": 0,
"reason": "dependency not pinned by hash detected -- score normalized to 0",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#pinned-dependencies"
},
{
"name": "SAST",
"score": 0,
"reason": "no SAST tool detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#sast"
},
{
"name": "Security-Policy",
"score": 0,
"reason": "security policy file not detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#security-policy"
},
{
"name": "Signed-Releases",
"score": 0,
"reason": "Project has not signed or included provenance with any releases.",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#signed-releases"
},
{
"name": "Token-Permissions",
"score": 0,
"reason": "detected GitHub workflow tokens with excessive permissions",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#token-permissions"
},
{
"name": "Vulnerabilities",
"score": 0,
"reason": "34 existing vulnerabilities detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#vulnerabilities"
}
],
"commit": "b788273e47b0f5be834d85c5b31e757b34e4d950",
"ran_at": "2026-07-22T19:51:03Z",
"aggregate_score": 2.6,
"scorecard_version": "v5.5.0"
},
"has_codeql_workflow": false,
"has_security_policy": false,
"has_dependabot_config": false
},
"contribution_flow": {
"collected": true,
"ci_last_run_at": "2026-07-22T18:51:55Z",
"oldest_open_prs": [
{
"number": 6,
"created_at": "2026-04-27T13:48:38Z",
"last_comment_at": "2026-04-27T14:15:45Z",
"last_comment_author": "eauchs"
},
{
"number": 7,
"created_at": "2026-04-28T19:40:13Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 8,
"created_at": "2026-05-15T07:57:40Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 14,
"created_at": "2026-06-11T21:45:15Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 19,
"created_at": "2026-07-12T08:20:39Z",
"last_comment_at": null,
"last_comment_author": null
}
],
"last_merged_pr_at": "2026-06-10T00:37:25Z",
"ci_last_conclusion": "SUCCESS",
"oldest_open_issues": [
{
"number": 1,
"created_at": "2026-03-26T22:48:47Z",
"last_comment_at": "2026-03-26T22:52:36Z",
"last_comment_author": "slygren"
},
{
"number": 2,
"created_at": "2026-04-06T17:17:53Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 3,
"created_at": "2026-04-09T22:05:03Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 4,
"created_at": "2026-04-17T17:35:22Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 5,
"created_at": "2026-04-19T08:35:32Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 13,
"created_at": "2026-06-11T21:38:08Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 16,
"created_at": "2026-06-21T12:45:00Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 17,
"created_at": "2026-06-21T12:57:01Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 18,
"created_at": "2026-07-12T07:14:21Z",
"last_comment_at": null,
"last_comment_author": null
}
]
}
},
"config": {
"disabled_metrics": [],
"disabled_categories": [],
"disabled_components": {}
},
"source": {
"url": "https://github.com/jjang-ai/jangq",
"host": "github.com",
"name": "jangq",
"owner": "jjang-ai"
},
"metrics": {
"overall": {
"key": "overall",
"band": "moderate",
"name": "Overall health",
"note": null,
"notes": [],
"value": 54,
"inputs": {
"security": 26,
"vitality": 82,
"community": 39,
"governance": 39,
"engineering": 76
},
"components": []
},
"categories": [
{
"key": "vitality",
"band": "good",
"name": "Vitality",
"value": 82,
"weight": 0.22,
"metrics": [
{
"key": "development_activity",
"band": "good",
"name": "Development activity",
"note": null,
"notes": [],
"value": 76,
"inputs": {
"commits_last_year": 565,
"human_commit_share": 1,
"days_since_last_push": 0,
"active_weeks_last_year": 17
},
"components": [
{
"key": "push_recency",
"name": "Push recency",
"detail": "last push 0 days ago",
"points": 36,
"status": "met",
"details": [
{
"code": "push_recency",
"params": {
"days": 0
}
}
],
"max_points": 36
},
{
"key": "commit_cadence",
"name": "Commit cadence",
"detail": "17/52 weeks with commits",
"points": 11.8,
"status": "partial",
"details": [
{
"code": "commit_cadence_weeks",
"params": {
"weeks": 17
}
}
],
"max_points": 36
},
{
"key": "commit_volume",
"name": "Commit volume",
"detail": "565 commits in the last year",
"points": 18,
"status": "met",
"details": [
{
"code": "commits_last_year",
"params": {
"count": 565
}
}
],
"max_points": 18
},
{
"key": "openssf_scorecard_maintained",
"name": "OpenSSF Scorecard: Maintained",
"detail": "30 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 10",
"points": 10,
"status": "met",
"details": [],
"max_points": 10
}
]
},
{
"key": "release_discipline",
"band": "excellent",
"name": "Release discipline",
"note": null,
"notes": [],
"value": 90,
"inputs": {
"releases_count": 9,
"latest_release_tag": "v2.5.33",
"releases_from_tags": false,
"days_since_latest_release": 0,
"mean_days_between_releases": 15.4
},
"components": [
{
"key": "ships_releases",
"name": "Ships releases",
"detail": "9 releases published",
"points": 27,
"status": "met",
"details": [
{
"code": "releases_published",
"params": {
"count": 9
}
}
],
"max_points": 27
},
{
"key": "release_recency",
"name": "Release recency",
"detail": "latest release 0 days ago",
"points": 36,
"status": "met",
"details": [
{
"code": "release_recency",
"params": {
"days": 0
}
}
],
"max_points": 36
},
{
"key": "release_cadence",
"name": "Release cadence",
"detail": "a release every ~15.4 days",
"points": 27,
"status": "met",
"details": [
{
"code": "release_cadence",
"params": {
"gap": 15.4
}
}
],
"max_points": 27
},
{
"key": "openssf_scorecard_signed_releases",
"name": "OpenSSF Scorecard: Signed-Releases",
"detail": "Project has not signed or included provenance with any releases.",
"points": 0,
"status": "missed",
"details": [],
"max_points": 10
}
]
},
{
"key": "abandonment",
"band": "excellent",
"name": "Abandonment",
"note": null,
"notes": [],
"value": 100,
"inputs": {
"cap": null,
"state": "unverified",
"guards": [],
"signals": [],
"red_flag": false,
"multiplier_pct": 100,
"declared_reason": null,
"unverified_reason": "repository_too_young",
"unanswered_open_prs": null,
"unanswered_open_issues": null,
"days_since_last_merged_pr": null,
"days_since_last_human_commit": null,
"days_since_last_human_commit_is_floor": false
},
"components": [
{
"key": "project_is_still_maintained",
"name": "Project is still maintained",
"detail": "maintenance record not established from the collected data",
"points": 100,
"status": "met",
"details": [
{
"code": "abandonment_unverified",
"params": {}
}
],
"max_points": 100
}
]
}
],
"description": "Is the project alive — is code being written and are releases shipping?"
},
{
"key": "community",
"band": "at_risk",
"name": "Community & Adoption",
"value": 39,
"weight": 0.18,
"metrics": [
{
"key": "popularity",
"band": "moderate",
"name": "Popularity & adoption",
"note": null,
"notes": [],
"value": 51,
"inputs": {
"forks": 27,
"stars": 214,
"watchers": 3,
"growth_state": "unverified",
"growth_factor_pct": 100,
"growth_unverified_reason": "no_history"
},
"components": [
{
"key": "stars",
"name": "Stars",
"detail": "214 stars",
"points": 37.8,
"status": "partial",
"details": [
{
"code": "stars",
"params": {
"count": 214
}
}
],
"max_points": 60
},
{
"key": "forks",
"name": "Forks",
"detail": "27 forks",
"points": 11.8,
"status": "partial",
"details": [
{
"code": "forks",
"params": {
"count": 27
}
}
],
"max_points": 25
},
{
"key": "watchers",
"name": "Watchers",
"detail": "3 watchers",
"points": 1.7,
"status": "partial",
"details": [
{
"code": "watchers",
"params": {
"count": 3
}
}
],
"max_points": 15
}
]
},
{
"key": "community_health",
"band": "critical",
"name": "Community health",
"note": null,
"notes": [],
"value": 25,
"inputs": {
"has_readme": true,
"has_license": false,
"has_contributing": false,
"has_issue_template": false,
"has_code_of_conduct": false,
"has_pull_request_template": false
},
"components": [
{
"key": "readme",
"name": "README",
"detail": null,
"points": 22.5,
"status": "met",
"details": [],
"max_points": 22.5
},
{
"key": "license",
"name": "License",
"detail": "no license file detected",
"points": 0,
"status": "missed",
"details": [
{
"code": "license_absent",
"params": {}
}
],
"max_points": 22.5
},
{
"key": "contributing_guide",
"name": "CONTRIBUTING guide",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 18
},
{
"key": "code_of_conduct",
"name": "Code of conduct",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 13.5
},
{
"key": "issue_template",
"name": "Issue template",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.2
},
{
"key": "pr_template",
"name": "PR template",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 6.3
}
]
}
],
"description": "Does the project have users, downloads, attention, and a welcoming setup for contributors?"
},
{
"key": "governance",
"band": "at_risk",
"name": "Sustainability & Governance",
"value": 39,
"weight": 0.24,
"metrics": [
{
"key": "maintainer_resilience",
"band": "critical",
"name": "Maintainer resilience (bus factor)",
"note": null,
"notes": [],
"value": 13,
"inputs": {
"bus_factor": 1,
"contributors_sampled": 1,
"top_contributor_share": 1
},
"components": [
{
"key": "bus_factor",
"name": "Bus factor",
"detail": "1 contributor(s) cover half of all commits",
"points": 9,
"status": "partial",
"details": [
{
"code": "bus_factor",
"params": {
"count": 1
}
}
],
"max_points": 54
},
{
"key": "commit_distribution",
"name": "Commit distribution",
"detail": "top contributor authored 100% of commits",
"points": 0,
"status": "missed",
"details": [
{
"code": "top_contributor_share",
"params": {
"share": 100
}
}
],
"max_points": 22.5
},
{
"key": "contributor_breadth",
"name": "Contributor breadth",
"detail": "1 contributors",
"points": 1.4,
"status": "partial",
"details": [
{
"code": "contributors_sampled",
"params": {
"count": 1
}
}
],
"max_points": 13.5
},
{
"key": "openssf_scorecard_contributors",
"name": "OpenSSF Scorecard: Contributors",
"detail": "project has 1 contributing companies or organizations -- score normalized to 3",
"points": 3,
"status": "partial",
"details": [],
"max_points": 10
}
]
},
{
"key": "responsiveness",
"band": "critical",
"name": "Issue & PR responsiveness",
"note": null,
"notes": [],
"value": 12,
"inputs": {
"merged_prs": 1,
"open_issues": 9,
"closed_issues": 1,
"issue_closed_ratio": 0.1,
"closed_unmerged_prs": 4
},
"components": [
{
"key": "issue_resolution",
"name": "Issue resolution",
"detail": "10% of issues closed",
"points": 4.7,
"status": "partial",
"details": [
{
"code": "issues_closed_share",
"params": {
"share": 10
}
}
],
"max_points": 46.75
},
{
"key": "pr_acceptance",
"name": "PR acceptance",
"detail": "1/5 decided PRs merged",
"points": 7.7,
"status": "partial",
"details": [
{
"code": "decided_prs_merged",
"params": {
"merged": 1,
"decided": 5
}
}
],
"max_points": 38.25
},
{
"key": "openssf_scorecard_code_review",
"name": "OpenSSF Scorecard: Code-Review",
"detail": "Found 0/30 approved changesets -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 15
}
]
},
{
"key": "stewardship",
"band": "moderate",
"name": "Ownership & stewardship",
"note": "Excluded from scoring (no data or not applicable): Verified domain. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"verified_domain"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 50,
"inputs": {
"followers": 217,
"owner_type": "User",
"is_verified": null,
"owner_login": "jjang-ai",
"public_repos": 8,
"account_age_days": 1115
},
"components": [
{
"key": "ownership_backing",
"name": "Ownership backing",
"detail": "personal (user) account",
"points": 10,
"status": "partial",
"details": [
{
"code": "owner_personal",
"params": {}
}
],
"max_points": 30
},
{
"key": "verified_domain",
"name": "Verified domain",
"detail": "not applicable to user accounts",
"points": 0,
"status": "excluded",
"details": [
{
"code": "not_applicable_to_user_accounts",
"params": {}
}
],
"max_points": 20
},
{
"key": "owner_reach",
"name": "Owner reach",
"detail": "217 followers of jjang-ai",
"points": 16.8,
"status": "partial",
"details": [
{
"code": "owner_followers",
"params": {
"count": 217,
"login": "jjang-ai"
}
}
],
"max_points": 25
},
{
"key": "track_record",
"name": "Track record",
"detail": "8 public repos, account ~3 yr old",
"points": 13.1,
"status": "partial",
"details": [
{
"code": "public_repos",
"params": {
"count": 8
}
},
{
"code": "account_age_years",
"params": {
"years": 3
}
}
],
"max_points": 25
}
]
},
{
"key": "package_maintenance",
"band": "excellent",
"name": "Package maintenance",
"note": null,
"notes": [],
"value": 100,
"inputs": {
"packages": [
"jang"
],
"ecosystems": "pypi",
"any_deprecated": false,
"min_days_since_publish": 0
},
"components": [
{
"key": "published_resolvable",
"name": "Published & resolvable",
"detail": "1 package(s) on pypi",
"points": 25,
"status": "met",
"details": [
{
"code": "packages_published",
"params": {
"count": 1,
"ecosystems": "pypi"
}
}
],
"max_points": 25
},
{
"key": "publish_recency",
"name": "Publish recency",
"detail": "latest publish 0 days ago",
"points": 35,
"status": "met",
"details": [
{
"code": "publish_recency",
"params": {
"days": 0
}
}
],
"max_points": 35
},
{
"key": "version_history",
"name": "Version history",
"detail": "43 published versions",
"points": 20,
"status": "met",
"details": [
{
"code": "published_versions",
"params": {
"count": 43
}
}
],
"max_points": 20
},
{
"key": "not_deprecated",
"name": "Not deprecated",
"detail": "active, not deprecated or yanked",
"points": 20,
"status": "met",
"details": [
{
"code": "package_not_deprecated",
"params": {}
}
],
"max_points": 20
}
]
}
],
"description": "Will the project survive its people — bus factor, responsiveness, who backs it, and package upkeep?"
},
{
"key": "engineering",
"band": "good",
"name": "Engineering Quality",
"value": 76,
"weight": 0.2,
"metrics": [
{
"key": "engineering_practices",
"band": "moderate",
"name": "Engineering practices",
"note": "Excluded from scoring (no data or not applicable): OpenSSF Scorecard: CI-Tests. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"openssf_scorecard_ci_tests"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 60,
"inputs": {
"has_ci": true,
"has_tests": true,
"has_editorconfig": false,
"has_linter_config": false,
"has_precommit_config": false
},
"components": [
{
"key": "ci_workflows",
"name": "CI workflows",
"detail": "1 workflow(s)",
"points": 24,
"status": "met",
"details": [
{
"code": "ci_workflows",
"params": {
"count": 1
}
}
],
"max_points": 24
},
{
"key": "tests_present",
"name": "Tests present",
"detail": null,
"points": 24,
"status": "met",
"details": [],
"max_points": 24
},
{
"key": "linter_config",
"name": "Linter config",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 16
},
{
"key": "pre_commit_hooks",
"name": "Pre-commit hooks",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 9.6
},
{
"key": "editorconfig",
"name": ".editorconfig",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 6.4
},
{
"key": "openssf_scorecard_ci_tests",
"name": "OpenSSF Scorecard: CI-Tests",
"detail": "no pull request found",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_data",
"params": {}
}
],
"max_points": 20
}
]
},
{
"key": "documentation",
"band": "excellent",
"name": "Documentation",
"note": null,
"notes": [],
"value": 100,
"inputs": {
"topics": [
"gguf",
"llamacpp",
"llm",
"mlx",
"mlxllm",
"quantization",
"apple-silicon",
"jang-quantization",
"omlx",
"omlx-alternative"
],
"has_wiki": true,
"homepage": "https://jangq.ai/",
"has_readme": true,
"has_docs_dir": true,
"has_description": true
},
"components": [
{
"key": "readme",
"name": "README",
"detail": null,
"points": 30,
"status": "met",
"details": [],
"max_points": 30
},
{
"key": "documentation_directory",
"name": "Documentation directory",
"detail": null,
"points": 25,
"status": "met",
"details": [],
"max_points": 25
},
{
"key": "documentation_homepage_site",
"name": "Documentation / homepage site",
"detail": "https://jangq.ai/",
"points": 15,
"status": "met",
"details": [],
"max_points": 15
},
{
"key": "repository_description",
"name": "Repository description",
"detail": null,
"points": 10,
"status": "met",
"details": [],
"max_points": 10
},
{
"key": "topics",
"name": "Topics",
"detail": "10 topics",
"points": 10,
"status": "met",
"details": [
{
"code": "topics_count",
"params": {
"count": 10
}
}
],
"max_points": 10
},
{
"key": "wiki",
"name": "Wiki",
"detail": null,
"points": 10,
"status": "met",
"details": [],
"max_points": 10
}
]
}
],
"description": "Are baseline engineering and documentation practices in place?"
},
{
"key": "security",
"band": "critical",
"name": "Security",
"value": 26,
"weight": 0.16,
"metrics": [
{
"key": "security_posture",
"band": "critical",
"name": "Security posture",
"note": "Excluded from scoring (no data or not applicable): CI-Tests, Packaging. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"ci_tests",
"packaging"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 26,
"inputs": {
"source": "openssf_scorecard",
"checks_evaluated": 16,
"scorecard_version": "v5.5.0",
"checks_inconclusive": 2,
"scorecard_aggregate": 2.6
},
"components": [
{
"key": "binary_artifacts",
"name": "Binary-Artifacts",
"detail": "no binaries found in the repo",
"points": 7.5,
"status": "met",
"details": [],
"max_points": 7.5
},
{
"key": "branch_protection",
"name": "Branch-Protection",
"detail": "branch protection not enabled on development/release branches",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
},
{
"key": "ci_tests",
"name": "CI-Tests",
"detail": "no pull request found",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_data",
"params": {}
}
],
"max_points": 2.5
},
{
"key": "cii_best_practices",
"name": "CII-Best-Practices",
"detail": "no effort to earn an OpenSSF best practices badge detected",
"points": 0,
"status": "missed",
"details": [],
"max_points": 2.5
},
{
"key": "code_review",
"name": "Code-Review",
"detail": "Found 0/30 approved changesets -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
},
{
"key": "contributors",
"name": "Contributors",
"detail": "project has 1 contributing companies or organizations -- score normalized to 3",
"points": 0.8,
"status": "partial",
"details": [],
"max_points": 2.5
},
{
"key": "dangerous_workflow",
"name": "Dangerous-Workflow",
"detail": "no dangerous workflow patterns detected",
"points": 10,
"status": "met",
"details": [],
"max_points": 10
},
{
"key": "dependency_update_tool",
"name": "Dependency-Update-Tool",
"detail": "no update tool detected",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
},
{
"key": "fuzzing",
"name": "Fuzzing",
"detail": "project is not fuzzed",
"points": 0,
"status": "missed",
"details": [],
"max_points": 5
},
{
"key": "license",
"name": "License",
"detail": "license file not detected",
"points": 0,
"status": "missed",
"details": [],
"max_points": 2.5
},
{
"key": "maintained",
"name": "Maintained",
"detail": "30 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 10",
"points": 7.5,
"status": "met",
"details": [],
"max_points": 7.5
},
{
"key": "packaging",
"name": "Packaging",
"detail": "packaging workflow not detected",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_data",
"params": {}
}
],
"max_points": 5
},
{
"key": "pinned_dependencies",
"name": "Pinned-Dependencies",
"detail": "dependency not pinned by hash detected -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 5
},
{
"key": "sast",
"name": "SAST",
"detail": "no SAST tool detected",
"points": 0,
"status": "missed",
"details": [],
"max_points": 5
},
{
"key": "security_policy",
"name": "Security-Policy",
"detail": "security policy file not detected",
"points": 0,
"status": "missed",
"details": [],
"max_points": 5
},
{
"key": "signed_releases",
"name": "Signed-Releases",
"detail": "Project has not signed or included provenance with any releases.",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
},
{
"key": "token_permissions",
"name": "Token-Permissions",
"detail": "detected GitHub workflow tokens with excessive permissions",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
},
{
"key": "vulnerabilities",
"name": "Vulnerabilities",
"detail": "34 existing vulnerabilities detected",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
}
]
}
],
"description": "Are visible security and supply-chain practices strong, with no malicious dependency and no unresolved high-risk jurisdiction exposure?"
},
{
"key": "ai_readiness",
"band": "at_risk",
"name": "AI Readiness",
"value": 34,
"weight": 0,
"metrics": [
{
"key": "ai_agent_context",
"band": "critical",
"name": "Agent context & guidance",
"note": null,
"notes": [],
"value": 24,
"inputs": {
"has_llms_txt": false,
"legible_history_share": 0.46,
"agent_instruction_files": [],
"agent_instruction_max_bytes": null
},
"components": [
{
"key": "agent_instructions",
"name": "Agent instructions",
"detail": "no CLAUDE.md / AGENTS.md / editor rules",
"points": 0,
"status": "missed",
"details": [
{
"code": "no_agent_instructions",
"params": {}
}
],
"max_points": 45
},
{
"key": "machine_readable_docs_llms_txt",
"name": "Machine-readable docs (llms.txt)",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 15
},
{
"key": "legible_commit_history",
"name": "Legible commit history",
"detail": "46 of 100 human commits state their intent (structured subject or explanatory body)",
"points": 24.5,
"status": "partial",
"details": [
{
"code": "legible_history",
"params": {
"legible": 46,
"sampled": 100
}
}
],
"max_points": 40
}
]
},
{
"key": "ai_verify_loop",
"band": "at_risk",
"name": "Verify loop (build / test / typecheck)",
"note": null,
"notes": [],
"value": 32,
"inputs": {
"has_nix": false,
"has_tests": true,
"lockfiles": [
"uv.lock"
],
"has_dockerfile": false,
"typed_language": false,
"bootstrap_files": [],
"has_devcontainer": false,
"has_linter_config": false,
"typecheck_configs": [],
"agent_commit_share": 0,
"toolchain_manifests": [],
"dependency_bot_commit_share": 0
},
"components": [
{
"key": "one_command_bootstrap",
"name": "One-command bootstrap",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 18
},
{
"key": "automated_tests",
"name": "Automated tests",
"detail": null,
"points": 22,
"status": "met",
"details": [],
"max_points": 22
},
{
"key": "lint_format_config",
"name": "Lint / format config",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 11
},
{
"key": "static_type_checking",
"name": "Static type checking",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 11
},
{
"key": "reproducible_environment",
"name": "Reproducible environment",
"detail": "lockfile",
"points": 10,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "lockfile"
}
}
],
"max_points": 10
},
{
"key": "demonstrated_agent_practice",
"name": "Demonstrated agent practice",
"detail": "no agent-authored commits among the last 100",
"points": 0,
"status": "missed",
"details": [
{
"code": "no_agent_authored_commits",
"params": {
"sampled": 100
}
}
],
"max_points": 10
},
{
"key": "automated_maintenance",
"name": "Automated maintenance",
"detail": "no automated dependency updates observed",
"points": 0,
"status": "missed",
"details": [
{
"code": "no_dependency_automation",
"params": {}
}
],
"max_points": 8
},
{
"key": "openssf_scorecard_pinned_dependencies",
"name": "OpenSSF Scorecard: Pinned-Dependencies",
"detail": "dependency not pinned by hash detected -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 10
}
]
},
{
"key": "ai_code_legibility",
"band": "moderate",
"name": "Code legibility for models",
"note": null,
"notes": [],
"value": 54,
"inputs": {
"primary_language": "Python",
"largest_source_bytes": 99406,
"source_files_sampled": 589,
"oversized_source_files": 5
},
"components": [
{
"key": "type_checkable_code",
"name": "Type-checkable code",
"detail": "Python without a type-check config",
"points": 0,
"status": "missed",
"details": [
{
"code": "no_typecheck_config_language",
"params": {
"language": "Python"
}
}
],
"max_points": 45
},
{
"key": "manageable_file_sizes",
"name": "Manageable file sizes",
"detail": "5/589 source files over 60KB",
"points": 54.5,
"status": "partial",
"details": [
{
"code": "oversized_source_files",
"params": {
"kb": 60,
"sampled": 589,
"oversized": 5
}
}
],
"max_points": 55
}
]
},
{
"key": "ai_interfaces",
"band": "at_risk",
"name": "Machine-readable interfaces",
"note": null,
"notes": [],
"value": 40,
"inputs": {
"example_dirs": [
"examples"
],
"has_mcp_signal": false,
"api_schema_files": []
},
"components": [
{
"key": "api_schema_openapi_graphql_proto",
"name": "API schema (OpenAPI/GraphQL/proto)",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 40
},
{
"key": "mcp_server",
"name": "MCP server",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 20
},
{
"key": "runnable_examples",
"name": "Runnable examples",
"detail": "examples",
"points": 40,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "examples"
}
}
],
"max_points": 40
}
]
}
],
"description": "How well is the repo equipped to be developed and maintained with AI coding agents? An independent, experimental badge — weight 0.0, so it is surfaced on its own and does not affect the overall health score."
}
],
"metrics_version": "1.13.0"
},
"warnings": [
"Star history unavailable: GitHub GraphQL error: Resource not accessible by personal access token",
"Could not fetch pypi package 'jang-ralph-runner' from its registry",
"GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository",
"deps.dev does not index pypi:jang@2.5.33; advisories assessed against the repository dependency graph instead"
],
"report_type": "repository",
"generated_at": "2026-07-22T19:51:09.166068Z",
"schema_version": "0.26.0",
"badge_url": "https://raw.githubusercontent.com/inspect-software/badges/main/v1/j/jjang-ai/jangq.svg",
"full_name": "jjang-ai/jangq",
"license_state": "absent",
"license_spdx": null
}Las puntuaciones son señales, no garantías. Reflejan prácticas públicamente visibles en GitHub; no son una auditoría de código ni una garantía de seguridad.
Los datos ausentes se excluyen y los pesos se renormalizan; nunca se puntúan como cero. La metodología es versionada y abierta: métricas v1.13.0, esquema v0.26.0 — metodología completa · wiki de métricas.
Cómo se sitúa un resultado dentro del registro general: estadísticas agregadas — PyPI.