Go · npm
egladman/magus
El repositorio no publica descripción.
Licencia propia31 jul 2026 · métricas 2.10.0
Todas las etiquetas
Etiqueta del catálogo
#harness
Todos los repositorios del registro público que llevan esta etiqueta, procedente de sus topics de GitHub o de las palabras clave que publican sus registros de paquetes. La salud se mide con la misma metodología versionada que el resto del registro.
96 registros
npm
fusengine/harness
Harness-agnostic toolkit for AI coding agents: detect the harness (Claude, Codex, Cursor, Cline, Gemini, Aider...) and run a pure policy core. One Bun-native package.
MIT5 sept 2026 · métricas 2.10.0
PyPI · crates.io
nickderobertis/onejudge
A simulated interaction and evaluation loop over oneharness: drive a harness through a multi-turn conversation and score the transcript.
MIT29 ago 2026 · métricas 2.10.0
PyPI
haqaliz/belay
The agent harness: sandbox any agent, verify each step by replaying it against real state, and keep a deterministic trace.
Apache-2.020 ago 2026 · métricas 2.10.0
npm
llblab/pi-telegram
Telegram runtime adapter for Pi
Sin licencia20 jul 2026 · métricas 2.10.0
npm
Kal-elSam/harness
Installable AI governance harness for Codex, Cursor, Claude, Gemini, Copilot, Engram, and Graphify.
MIT6 sept 2026 · métricas 2.10.0
npm · crates.io
duct-tape-and-markdown/temper
A typed maintenance surface for the Claude Code harness — the Rust of agentic harnesses: declare a contract, gate on conformance.
Apache-2.029 ago 2026 · métricas 2.10.0
npm
robmclarty/plumbbob
Claude Code plugin that turns LLM coding into a loop you control — plan first, build in small steps, pause for your approval before each commit.
Apache-2.022 ago 2026 · métricas 2.10.0
PyPI
yuchanns/bazaar-compute-node
Collaborate with your Agents in the bazaar across compute nodes, through any interface, with any harness runtime.
Licencia propia29 ago 2026 · métricas 2.10.0
npm
AIDD-Projects/harness
Production-grade Harness Engineering Framework for multi-developer AI coding agents — guardrails, state persistence, direction alignment, and self-correction across 6 IDEs. Zero dependencies.
MIT22 jul 2026 · métricas 2.10.0
Go
farazhassan/gantry
A tiny testable, Go-native agent runtime for teams that want control, conformance, and no framework lock-ins.
MIT18 jul 2026 · métricas 2.10.0
Go
mlhher/late-cli
Stop degrading your model's reasoning. A minimal, zero-config AI coding agent. Enforced ephemeral subagents keep context pure. From tiny local models up to Sol, Fable and Kimi K3.
Licencia propia20 jul 2026 · métricas 2.10.0
Go
pardnchiu/go-agent-skills
Make AI actually work for you - A personal agent that writes its own tools and repairs itself.
Apache-2.017 jul 2026 · métricas 2.10.0
Go
pardnchiu/go-skill-runner
Make AI actually work for you - A personal agent that writes its own tools and repairs itself.
Apache-2.016 jul 2026 · métricas 2.10.0
npm
huiliyi37/Tianshu-harness
天枢 (Tianshu) 是一个基于harness工程的终端编程智能体运行时（Tui X Gui），针对DeepSeek V4 做了前缀缓存工程优化（长会话实测稳态命中率 97–99%）和深度适配。它跳出了传统 AI 编程助手把大模型仅当成“工具”的局限，基于认知虚拟机 (CVM)、自感知层和信息素（Stigmergy）自衰减记忆构建，让 AI 成为有独立判断与认知防护的“开发伙伴”。
Apache-2.022 ago 2026 · métricas 2.10.0
npm
jorgehn98/jorgex-stack
Harness multi-agente portable: instala la config JorgeX (agentes, skills, hooks, Engram, MCPs) en Claude Code, Codex CLI y OpenCode
MIT20 jul 2026 · métricas 2.10.0
npm
TylerJPresley/voidrift
Project VoidRift: Local-first Agentic Development Framework
Apache-2.030 jul 2026 · métricas 2.10.0
PyPI
klyd-studio/klyd-harness
klyd: the harness that stops terminal coding agents from silently drifting your architecture. Extracts, stores, and enforces design decisions across sessions.
MIT4 ago 2026 · métricas 2.10.0
npm
richpaul1/harness-maestro
El repositorio no publica descripción.
Apache-2.019 jul 2026 · métricas 2.10.0
npm
Adrianlpz211/AGENTIX-KDD
Autonomous development pipeline for Cursor & Claude Code. Type `aa:` and a persistent SQLite knowledge graph auto-records patterns, decisions and verified contracts every cycle. 54 MCP tools, AST impact analysis, preservation gates & audit mode.
Sin licencia1 ago 2026 · métricas 2.10.0
npm · PyPI
ictseoyoungmin/HADARA
Portable agentic development workbench for evidence-backed, resumable AI-assisted software workflows.
MIT29 jul 2026 · métricas 2.10.0
PyPI
HenryZ838978/deepseek-harness
Python-side witness stack for the official DeepSeek Harness (Node). Five `dsh doctor --node` probes each report something the Node runtime will not. `pip install deepseek-harness-cli` first
MIT22 ago 2026 · métricas 2.10.0
npm
EricMoin/rolebox
Composable AI agent teams defined in YAML. Roles, skills, subagents & collaboration — no code required.
Sin licencia19 jul 2026 · métricas 2.10.0
PyPI · Go
ROCK-LAB-PRIVATE-LIMITED/federaide
P2P multi agent orchestration harness, universal automation system and IDE
Apache-2.01 ago 2026 · métricas 2.10.0
npm
lloyal-ai/reasoning-run
A private reasoner for your terminal. Direct conversation or grounded multi-agent research, GPU-native and fully local. No API keys, no inference servers.
MIT19 jul 2026 · métricas 2.10.0
npm
Linux2010/openhorse
El repositorio no publica descripción.
Sin licencia16 jul 2026 · métricas 2.10.0
npm
vantanminh/5harness
El repositorio no publica descripción.
MIT17 jul 2026 · métricas 2.10.0
npm · PyPI
CHNAICORP/cortx
Cortx — AI Agent runtime | Harness Agent + Agentic Loop | 43 tools | Python + TypeScript
MIT21 jul 2026 · métricas 2.10.0
PyPI
evanl666/loom
The agent harness you can read, replay, and rewind. One Effect boundary, five superpowers: deterministic replay, fork-at-any-turn, bisect, free CI tests, cost accounting.
MIT22 ago 2026 · métricas 2.10.0
PyPI · Go
ROCK-LAB-PRIVATE-LIMITED/federate.ai
P2P multimodal agent orchestration harness and universal automation system
Apache-2.019 jul 2026 · métricas 2.10.0