# TabbyML/tabby

Self-hosted AI coding assistant

Repository: https://github.com/TabbyML/tabby
Canonical: https://ross.abutalabs.com/products/tabbyml-tabby
Homepage: https://tabbyml.com
Language: Rust
License: NOASSERTION
License Family: other
Topics: ai, codegen, coding-assistant, coding-language, developer-experience, developer-tools, gen-ai, llms, ide
Last push: 2026-06-30T20:38:02+00:00

## Health v2 (maintenance only)
Score: 82/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 90, release rhythm 67, longevity 90
- inputs: {"age_days": 1266, "days_push": 64, "days_rel": 220, "gap_med": 10.0, "n_releases_24m": 35}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 33838, forks 1785 (observed 2026-08-28T04:11:58.512392+00:00)

## What it is
Tabby is a self-hosted, open-source AI coding assistant that serves as an on-premises alternative to GitHub Copilot. It provides LLM-powered code completion, an answer engine, and inline chat, deployable with consumer-grade GPUs and no external database or cloud service.

## Use cases
- self-hosted github copilot alternative
- run ai code completion on my own server
- set up llm code completion for my team
- ai coding assistant that works with consumer gpus
- integrate ai code suggestions into vscode
- private on-premises ai assistant for code
- chat with my codebase using local llm

## When to choose
- you need code completion and AI chat without sending code to third-party clouds
- you want to run on consumer-grade GPUs with no external DBMS dependency
- you need OpenAPI integration with existing infrastructure like Cloud IDEs
- you want to use your own coding LLMs (CodeLlama, StarCoder, etc.)

## When to avoid
- you prefer a fully managed cloud service with zero setup
- you have no GPU or hardware to run local model inference
- you need enterprise features like SSO on a free tier
- you only need occasional one-off code generation rather than integrated IDE assistance

## Facets
- artifact type: service
- maturity: active
- function: llm-inference, rag, search-engine, http-server, api-framework, auth, chatbot
- domain: developer-tools, large-language-models, artificial-intelligence, self-hosted, apis
- platform: windows, self-hosted, rust, editor-plugin
- tags: ai-coding-assistant, code-completion, copilot-alternative, on-premises, ide-extension, code-llm, answer-engine, linux, macos, docker, gpu

## Member repositories
- TabbyML/tabby (main) score 82

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:58.512392+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:28:08.399730+00:00, confidence not recorded.
  - readme: https://github.com/TabbyML/tabby (fetched 2026-08-28T04:11:58.512392+00:00, sha d0e591891cd4)
  - homepage: https://tabbyml.com (fetched 2026-08-29T07:48:33.816331+00:00, sha 5c3d73264a36)
  - site_page: https://tabby.tabbyml.com/docs/welcome (fetched 2026-08-29T07:48:33.828482+00:00, sha ceaafdaa4cf0)
  - site_page: https://www.tabbyml.com/pricing (fetched 2026-08-29T07:48:33.826337+00:00, sha 7958d8488bf6)
- Data as of 2026-08-30T08:39:29.467469+00:00.