# mudler/LocalAI — health index 85/100 (Excellent)

> Inspection of the public repository mudler/LocalAI by inspect.software. It holds a health index of 85 out of 100, placing it in the Excellent band. The index is a signal derived from publicly visible practice, not a warranty, a security audit, or an endorsement, and it is independent of payment.

- Repository: https://github.com/mudler/LocalAI
- Report page: https://inspect.software/software/mudler/LocalAI
- Full JSON report: https://inspect.software/api/repositories/mudler/LocalAI/report
- Badge: https://raw.githubusercontent.com/inspect-software/badges/main/v1/m/mudler/LocalAI.svg
- Inspected: 2026-07-15
- Methodology: metrics 1.13.0, report schema 0.11.0 (https://inspect.software/methodology.md)

## Category summary

| Category | Weight | Index | Band |
|---|---|---|---|
| Vitality | 22% | 100/100 | Excellent |
| Community & Adoption | 18% | 89/100 | Excellent |
| Sustainability & Governance | 24% | 70/100 | Good |
| Engineering Quality | 20% | 93/100 | Excellent |
| Security | 16% | 73/100 | Good |
| AI Readiness | not counted | 91/100 | Excellent |

## Repository facts

| Field | Value |
|---|---|
| Description | LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required. |
| Homepage | https://localai.io |
| Primary language | Go |
| License | MIT |
| Stars | 47,552 |
| Forks | 4,238 |
| Created | 2023-03-18 |
| Last push | 2026-07-15 |
| Latest release | v4.7.1 |
| Commits (last year) | 2,767 |
| Bus factor | 2 |
| Topics | llama, ai, llm, stable-diffusion, api, tts, musicgen, mamba, audio-generation, image-generation, text-generation, rerank, distributed, libp2p, decentralized, object-detection, mcp, agents |

## Published packages

| Registry | Package | Latest | Monthly downloads |
|---|---|---|---|
| go | github.com/mudler/LocalAI | v1.40.0 | — |
| npm | tech-doc-hugo | 0.0.1-security | 13 |

## Vitality — 100/100 (Excellent)

Is the project alive — is code being written and are releases shipping? Weight: 22% of the overall index.

### Development activity — 100/100 (Excellent)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Push recency | met | 36 / 36 | last push 0 days ago |
| Commit cadence | met | 36 / 36 | 52/52 weeks with commits |
| Commit volume | met | 18 / 18 | 2767 commits in the last year |
| OpenSSF Scorecard: Maintained | excluded | 0 / 10 | OpenSSF Scorecard unavailable |

### Release discipline — 100/100 (Excellent)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Ships releases | met | 27 / 27 | 100 releases published |
| Release recency | met | 36 / 36 | latest release 1 days ago |
| Release cadence | met | 27 / 27 | a release every ~2 days |
| OpenSSF Scorecard: Signed-Releases | excluded | 0 / 10 | OpenSSF Scorecard unavailable |

### Abandonment — 100/100 (Excellent)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Project is still maintained | met | 100 / 100 | maintenance record not established from the collected data |

## Community & Adoption — 89/100 (Excellent)

Does the project have users, downloads, attention, and a welcoming setup for contributors? Weight: 18% of the overall index.

### Popularity & adoption — 99/100 (Excellent)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Stars | met | 60 / 60 | 47,552 stars |
| Forks | met | 25 / 25 | 4,238 forks |
| Watchers | partial | 13.7 / 15 | 288 watchers |

### Community health — 77/100 (Good)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| README | met | 22.5 / 22.5 | — |
| License | met | 22.5 / 22.5 | recognized license (MIT) |
| CONTRIBUTING guide | met | 18 / 18 | — |
| Code of conduct | not met | 0 / 13.5 | — |
| Issue template | not met | 0 / 7.2 | — |
| PR template | met | 6.3 / 6.3 | — |

## Sustainability & Governance — 70/100 (Good)

Will the project survive its people — bus factor, responsiveness, who backs it, and package upkeep? Weight: 24% of the overall index.

### Maintainer resilience (bus factor) — 56/100 (Moderate)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Bus factor | partial | 25.2 / 54 | 2 contributor(s) cover half of all commits |
| Commit distribution | partial | 12 / 22.5 | top contributor authored 47% of commits |
| Contributor breadth | met | 13.5 / 13.5 | 100 contributors |
| OpenSSF Scorecard: Contributors | excluded | 0 / 10 | OpenSSF Scorecard unavailable |

### Issue & PR responsiveness — 82/100 (Good)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Issue resolution | partial | 42.5 / 46.8 | 91% of issues closed |
| PR acceptance | partial | 26.9 / 38.2 | 6185/8787 decided PRs merged |
| OpenSSF Scorecard: Code-Review | excluded | 0 / 15 | OpenSSF Scorecard unavailable |

### Ownership & stewardship — 74/100 (Good)

Excluded from scoring (no data or not applicable): Verified domain. Remaining weights renormalized.

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Ownership backing | partial | 10 / 30 | personal (user) account |
| Verified domain | excluded | 0 / 20 | not applicable to user accounts |
| Owner reach | partial | 24.2 / 25 | 2,347 followers of mudler |
| Track record | met | 25 / 25 | 304 public repos, account ~13 yr old |

### Package maintenance — 69/100 (Moderate)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Published & resolvable | met | 25 / 25 | 1 package(s) on go |
| Publish recency | partial | 4 / 35 | latest publish 989 days ago |
| Version history | met | 20 / 20 | 50 published versions |
| Not deprecated | met | 20 / 20 | active, not deprecated or yanked |

## Engineering Quality — 93/100 (Excellent)

Are baseline engineering and documentation practices in place? Weight: 20% of the overall index.

### Engineering practices — 88/100 (Excellent)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| CI workflows | met | 24 / 24 | 40 workflow(s) |
| Tests present | met | 24 / 24 | — |
| Linter config | met | 16 / 16 | .golangci.yml, eslint.config.js |
| Pre-commit hooks | not met | 0 / 9.6 | — |
| .editorconfig | met | 6.4 / 6.4 | — |
| OpenSSF Scorecard: CI-Tests | excluded | 0 / 20 | OpenSSF Scorecard unavailable |

### Documentation — 100/100 (Excellent)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| README | met | 30 / 30 | — |
| Documentation directory | met | 25 / 25 | — |
| Documentation / homepage site | met | 15 / 15 | https://localai.io |
| Repository description | met | 10 / 10 | — |
| Topics | met | 10 / 10 | 18 topics |
| Wiki | met | 10 / 10 | — |

## Security — 73/100 (Good)

Are visible security and supply-chain practices strong, with no malicious dependency and no unresolved high-risk jurisdiction exposure? Weight: 16% of the overall index.

### Security posture — 73/100 (Good)

Excluded from scoring (no data or not applicable): Dependency lockfiles. Remaining weights renormalized.

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Security policy (SECURITY.md) | met | 30 / 30 | — |
| Dependabot config | met | 25 / 25 | — |
| Dependency lockfiles | excluded | 0 / 25 | published library — lockfiles are an application concern, not expected |
| CodeQL workflow | not met | 0 / 20 | — |

### High-Risk Jurisdiction Exposure — 100/100 (Excellent)

Only high-confidence self-published location evidence affects this multiplier. Ambiguous matches are review-only; country evidence is not proof of nationality, citizenship, legal registration, malicious intent, or sanctions status.

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Policy exposure multiplier | met | 100 / 100 | no confirmed policy-scope location match |

## AI Readiness — 91/100 (Excellent)

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.

### Agent context & guidance — 75/100 (Good)

Excluded from scoring (no data or not applicable): Legible commit history. Remaining weights renormalized.

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Agent instructions | met | 45 / 45 | AGENTS.md, CLAUDE.md, docs/content/features/agents.md |
| Machine-readable docs (llms.txt) | not met | 0 / 15 | — |
| Legible commit history | excluded | 0 / 40 | no data |

### Verify loop (build / test / typecheck) — 96/100 (Excellent)

Excluded from scoring (no data or not applicable): Demonstrated agent practice. Remaining weights renormalized.

| Criterion | Status | Points | Detail |
|---|---|---|---|
| One-command bootstrap | met | 18 / 18 | Makefile, backend/cpp/ds4/Makefile, backend/cpp/grpc/Makefile, backend/cpp/ik-llama-cpp/Makefile, backend/cpp/llama-cpp/Makefile, backend/cpp/privacy-filter/Makefile, backend/cpp/turboquant/Makefile, backend/go/acestep-cpp/Makefile, backend/go/ced/Makefile, backend/go/cloud-proxy/Makefile, backend/go/crispasr/Makefile, backend/go/depth-anything-cpp/Makefile, backend/go/face-detect/Makefile, backend/go/local-store/Makefile, backend/go/localvqe/Makefile, backend/go/locate-anything-cpp/Makefile, backend/go/moss-transcribe-cpp/Makefile, backend/go/omnivoice-cpp/Makefile, backend/go/opus/Makefile, backend/go/parakeet-cpp/Makefile, backend/go/piper/Makefile, backend/go/qwen3-tts-cpp/Makefile, backend/go/rfdetr-cpp/Makefile, backend/go/sam3-cpp/Makefile, backend/go/sherpa-onnx/Makefile, backend/go/silero-vad/Makefile, backend/go/stablediffusion-ggml/Makefile, backend/go/supertonic/Makefile, backend/go/vibevoice-cpp/Makefile, backend/go/voice-detect/Makefile, backend/go/voxtral/Makefile, backend/go/whisper/Makefile, backend/python/ace-step/Makefile, backend/python/chatterbox/Makefile, backend/python/common/template/Makefile, backend/python/coqui/Makefile, backend/python/diffusers/Makefile, backend/python/faster-qwen3-tts/Makefile, backend/python/faster-whisper/Makefile, backend/python/fish-speech/Makefile, backend/python/insightface/Makefile, backend/python/kitten-tts/Makefile, backend/python/kokoro/Makefile, backend/python/liquid-audio/Makefile, backend/python/llama-cpp-quantization/Makefile, backend/python/longcat-video/Makefile, backend/python/mlx-audio/Makefile, backend/python/mlx-distributed/Makefile, backend/python/mlx-vlm/Makefile, backend/python/mlx/Makefile, backend/python/moonshine/Makefile, backend/python/nemo/Makefile, backend/python/neutts/Makefile, backend/python/outetts/Makefile, backend/python/pocket-tts/Makefile, backend/python/qwen-asr/Makefile, backend/python/qwen-tts/Makefile, backend/python/rerankers/Makefile, backend/python/rfdetr/Makefile, backend/python/sglang/Makefile, backend/python/speaker-recognition/Makefile, backend/python/tinygrad/Makefile, backend/python/transformers/Makefile, backend/python/trl/Makefile, backend/python/vibevoice/Makefile, backend/python/vllm-omni/Makefile, backend/python/vllm/Makefile, backend/python/voxcpm/Makefile, backend/python/whisperx/Makefile, backend/rust/kokoros/Makefile, tests/e2e/mock-backend/Makefile |
| Automated tests | met | 22 / 22 | — |
| Lint / format config | met | 11 / 11 | .golangci.yml, eslint.config.js |
| Static type checking | met | 11 / 11 | docs/assets/jsconfig.json |
| Reproducible environment | met | 10 / 10 | devcontainer, Dockerfile, Nix, lockfile |
| Demonstrated agent practice | excluded | 0 / 10 | no data |
| Automated maintenance | partial | 5 / 8 | dependency automation configured, none observed in the sampled commits |
| OpenSSF Scorecard: Pinned-Dependencies | excluded | 0 / 10 | OpenSSF Scorecard unavailable |

### Code legibility for models — 99/100 (Excellent)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Type-checkable code | met | 45 / 45 | Go (statically typed) |
| Manageable file sizes | partial | 54.3 / 55 | 23/1764 source files over 60KB |

### Machine-readable interfaces — 100/100 (Excellent)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| API schema (OpenAPI/GraphQL/proto) | met | 40 / 40 | backend/backend.proto, swagger/swagger.json, swagger/swagger.yaml |
| MCP server | met | 20 / 20 | — |
| Runnable examples | met | 40 / 40 | examples |

## Collection warnings

- npm package 'tech-doc-hugo' points at a different repository (npm/security-holder); excluded from ecosystem scoring
- OpenSSF Scorecard timed out after 240s; skipping Scorecard checks

## What this report is

inspect.software measures public repositories against a single published, versioned methodology and reports the result as a 1–100 health index. Findings are signals derived from what is visible in public repository data — they are not a security audit, a warranty, or an endorsement, and no result depends on payment.

- Methodology, formulas and weights: https://inspect.software/methodology.md
- What a result does and does not claim: https://inspect.software/wiki/signals-not-warranties.md
- Rating bands: https://inspect.software/wiki/scoring-bands.md
- Corrections: https://inspect.software/contact.md
- Index of all documents: https://inspect.software/llms.txt