Embeddable AI Runtime stable

LocalAI

Drop-in OpenAI API replacement running locally

28.0K stars 100 contributors Since 2023
Website → GitHub

Drop-in OpenAI API replacement running locally

License
MIT
Min RAM
2 GB
Min CPUs
1 core
Scaling
single_node
Complexity
intermediate
Performance
medium
Self-hostable
K8s native
Offline
Pricing
fully free
Docs quality
good
Vendor lock-in
none

Use cases

  • Drop-in OpenAI API replacement running locally
  • Run multiple AI models (LLM+TTS+STT+Image)
  • Privacy-preserving AI API endpoint
  • Development without API costs

Anti-patterns / when NOT to use

  • Slower than vLLM for pure LLM serving
  • Model compatibility varies
  • Configuration can be complex

Replaces / alternatives to

  • OpenAI API

Technical specs

Language
GoC++
API type
SDK
Protocols
HTTPgRPC
Deployment
dockerbinary
SDKs
pythonjavascriptgo

Community

GitHub stars 28.0K
Contributors 100
Commit frequency weekly
Plugin ecosystem none
Backing Mudler
Funding community

Release

Latest version
Last release
Since 2023

Best fit

Team size
solosmallmedium
Industries
general

Tags

  • openai-compatible
  • local-inference
  • llm
  • image-generation
  • tts
  • stt
  • embeddings
  • grpc