:robot: The free, Open Source alternative to OpenAI, Claude and others. Self-hosted and local-first. Drop-in replacement, running on consumer-grade hardware. No GPU required. Runs gguf, transformers, diffusers and many more. Features: Generate Text, MCP, Audio, Video, Images, Voice Cloning, Distributed, P2P and decentralized inference
COMMITS
/ Makefile March 21, 2026
E
feat: inferencing default, automatic tool parsing fallback and wire min_p (#9092)
Ettore Di Giacinto committed
E
feat(quantization): add quantization backend (#9096)
Ettore Di Giacinto committed
E
feat: add (experimental) fine-tuning support with TRL (#9088)
Ettore Di Giacinto committed
March 16, 2026
R
fix(ui): Add tracing inline settings back and create UI tests (#9027)
Richard Palethorpe committed
March 14, 2026
E
chore: drop AIO images (#9004)
Ettore Di Giacinto committed
March 13, 2026
R
feat(realtime): WebRTC support (#8790)
Richard Palethorpe committed
March 12, 2026
E
feat(backends): add ace-step.cpp (#8965)
Ettore Di Giacinto committed
E
feat: add fish-speech backend (#8962)
Ettore Di Giacinto committed
March 9, 2026
E
feat(mlx-distributed): add new MLX-distributed backend (#8801)
Ettore Di Giacinto committed
March 5, 2026
E
feat(ui): move to React for frontend (#8772)
Ettore Di Giacinto committed
February 27, 2026
L
feat(backends): add faster-qwen3-tts (#8664)
LocalAI [bot] committed
February 9, 2026
E
feat(voxtral): add voxtral backend (#8451)
Ettore Di Giacinto committed
February 7, 2026
E
feat(nemo): add Nemo (only asr for now) backend (#8436)
Ettore Di Giacinto committed
February 5, 2026
E
feat(musicgen): add ace-step and UI interface (#8396)
Ettore Di Giacinto committed
February 3, 2026
E
feat(metal): try to extend support to remaining backends (#8374)
Ettore Di Giacinto committed
February 2, 2026
January 30, 2026
E
chore(cuda): target 12.8 for 12 to increase compatibility (#8297)
Ettore Di Giacinto committed
E
chore: re-enable e2e tests, fixups anthropic API tools support (#8296)
Ettore Di Giacinto committed
January 29, 2026
E
feat(qwen-asr): add support to qwen-asr (#8281)
Ettore Di Giacinto committed
January 28, 2026
E
feat: add VoxCPM tts backend (#8109)
Ettore Di Giacinto committed
January 25, 2026
E
chore: drop bark which is unmaintained (#8207)
Ettore Di Giacinto committed
January 24, 2026
E
feat(vllm-omni): add new backend (#8188)
Ettore Di Giacinto committed
E
chore(exllama): drop backend now almost deprecated (#8186)
Ettore Di Giacinto committed
January 23, 2026
E
feat(qwen-tts): add Qwen-tts backend (#8163)
Ettore Di Giacinto committed
January 13, 2026
E
feat(tts): add pocket-tts backend (#8018)
Ettore Di Giacinto committed
January 7, 2026
E
feat(backends): add moonshine backend for faster transcription (#7833)
Ettore Di Giacinto committed
January 6, 2026
R
chore: Update to Ubuntu24.04 (cont #7423) (#7769)
Richard Palethorpe committed
January 4, 2026
E
chore(Makefile): refactor common make targets (#7858)
Ettore Di Giacinto committed
December 18, 2025
R
feat(whisper): Add prompt to condition transcription output (#7624)
Richard Palethorpe committed
December 11, 2025
R
chore(makefile): Add buildargs for sd and cuda when building backend (#7525)
Richard Palethorpe committed
E
chore(deps): bump stable-diffusion.cpp to '8823dc48bcc1598eb9671da7b69e45338d0cc5a5' (#7524)
Ettore Di Giacinto committed
December 10, 2025
E
feat(vibevoice): add new backend (#7494)
Ettore Di Giacinto committed
December 2, 2025
E
feat: add cuda13 images (#7404)
Ettore Di Giacinto committed
November 7, 2025
S
chore: use air to live reload in dev environment (#7186)
Shohidul Bari committed
October 9, 2025
E
feat(neutts): add backend (#6404)
Ettore Di Giacinto committed
September 24, 2025
E
feat(chatterbox): support multilingual (#6240)
Ettore Di Giacinto committed
September 17, 2025
E
Revert "feat(nvidia-gpu): bump images to cuda 12.8" (#6303)
Ettore Di Giacinto committed
September 13, 2025
E
fix(llama-cpp): correctly calculate embeddings (#6259)
Ettore Di Giacinto committed
September 9, 2025
E
feat(chatterbox): add MPS, and CPU, pin version (#6242)
Ettore Di Giacinto committed
E
feat(nvidia-gpu): bump images to cuda 12.8 (#6239)
Ettore Di Giacinto committed
September 1, 2025
R
chore(ci): Build some Go based backends on Darwin (#6164)
Richard Palethorpe committed
August 26, 2025
E
chore(refactor): cli -> cmd, update docs (#6148)
Ettore Di Giacinto committed
E
feat(mlx-audio): Add mlx-audio backend (#6138)
Ettore Di Giacinto committed
E
feat(launcher): add LocalAI launcher app (#6127)
Ettore Di Giacinto committed
August 23, 2025
E
Add mlx-vlm (#6119)
Ettore Di Giacinto committed
August 22, 2025
E
feat(diffusers): add MPS version (#6121)
Ettore Di Giacinto committed
E
chore(Makefile): small fixup for darwin MLX builds
Ettore Di Giacinto committed
E
feat(mlx): add mlx backend (#6049)
Ettore Di Giacinto committed
August 14, 2025
E
fix(llama-cpp/darwin): make sure to bundle `libutf8` libs (#6060)
Ettore Di Giacinto committed
August 8, 2025
E
feat(diffusers): add builds for nvidia-l4t (#6004)
Ettore Di Giacinto committed