tabby
View on GitHubSelf-hosted AI coding assistant
Self-hosted AI coding assistant and open-source Copilot alternative: inline code completion, IDE chat, and a RAG answer engine over your repos and internal docs. Ships a Rust server with OpenAI-compatible APIs, supports consumer GPUs, and needs no external DB or cloud.
Use Cases
self-hosted GitHub Copilot alternativeinline code completion in IDEschat with your codebase in side panelon-prem RAG answer engine over internal docs and reposrepository-level code context indexingauto-generated commit messagesteam usage analytics and admin dashboardair-gapped/offline coding assistant deploymentconsumer-GPU model serving for code LLMsGitLab/GitHub MR and SSO integrations
Built With
- Language
- Rust
- Frameworks
- Rust · Tokio · Axum · Juniper GraphQL · llama.cpp · Ollama · llamafile · Tantivy · Next.js · React · Docker · CUDA · ROCm · SQLite
Tags
self-hosted · code-completion · coding-assistant · copilot-alternative · on-premises · ide-extension · vscode · jetbrains · vim · chat-in-ide · repository-context · openapi · gpu-inference · code-llm · enterprise · rust