LLMs & AI Infra AI Coding stable

Tabby

Self-hosted AI coding assistant

25.0K stars 100 contributors Since 2023
Website → GitHub

Self-hosted AI code completion server built in Rust with support for multiple models, GPU acceleration, and IDE extensions.

License
Apache-2.0
Min RAM
4 GB
Min CPUs
2 cores
Scaling
single_node
Complexity
intermediate
Performance
medium
Self-hostable
K8s native
Offline
Pricing
fully free
Docs quality
good
Vendor lock-in
none

Use cases

  • Private self-hosted code completion for enterprises
  • GPU-accelerated code suggestions
  • Air-gapped development environments

Anti-patterns / when NOT to use

  • Needs GPU for good performance
  • Smaller model ecosystem than Continue
  • Setup more complex than cloud alternatives

Integrates with

Compare with alternatives

Replaces / alternatives to

  • GitHub Copilot

Technical specs

Language
Rust
API type
REST
Protocols
HTTP
Deployment
dockerbinary

Community

GitHub stars 25.0K
Contributors 100
Commit frequency weekly
Plugin ecosystem none
Backing TabbyML
Funding vc_backed

Release

Latest version
Last release
Since 2023

Best fit

Team size
solosmallmedium
Industries
development

Tags

  • ai-coding
  • self-hosted
  • code-completion
  • rust
  • gpu