Rare find

LocalAI. :robot: Self-hosted, community-driven, local OpenAI-compatible API. Can be used as a drop-in replacement for OpenAI, running on CPU with consumer-grade hardware. API for ggml compatible models, for instance: llama.cpp, alpaca.cpp, gpt4all.cpp, rwkv.cpp, whisper.cpp, vicuna, koala, gpt4all-j, cerebras

github.com/ishandutta2007/LocalAI

Vaya's read on this project

Problem, audience, market, and the verdict — sign in to see it.

Updates

June 2026
  • chore(model-gallery): :arrow_up: update checksum (#10585)
  • fix(oci): retry layer downloads on transient network errors (#10579)
  • fix(fish-speech): allow invalid_reference_casting so tokenizers build…
  • fix(distributed): missing agent NATS permissions (#10571)
  • fix(launcher): robust binary download/upgrade (resume, rate-limit, UX…
  • fix(kokoro): add explicit click dep so spacy CLI works on intel build…
  • feat(backends): add voice-detect + face-detect ggml backends (replace…
  • fix(ik-llama): port multimodal path to mtmd API and bump to f96eaddb …
  • chore: :arrow_up: Update ggml-org/llama.cpp to `0ed235ea2c17a19fc8238…
  • chore: :arrow_up: Update CrispStrobe/CrispASR to `6514c9da00b03a2f0f1…
  • chore: :arrow_up: Update ggml-org/whisper.cpp to `0ae02cdb2c7317b5099…
  • fix(openresponses): bound resume-stream buffer and enforce response o…
  • chore: :arrow_up: Update leejet/stable-diffusion.cpp to `9956436c925a…
  • feat(distributed): add LOCALAI_DISTRIBUTED_SHARED_MODELS to skip stag…
  • fix(distributed): return empty backend list for agent nodes instead o…
  • fix(gallery): match mmproj/model quant as a whole token so F16 no lon…
  • ci(vibevoice): skip the ASR transcription e2e on release tag builds (…
  • fix(config): fall back to DefaultContextSize for unparseable GGUFs; p…
  • chore(fish-speech): drop the darwin/metal build target (#10561)
  • feat(distributed): SyncedMap component + migrate finetune/quant/agent…