<p align="center" <img src="https://raw.githubusercontent.com/sayak-sarkar/contextlake/main/docs/img/readme-banner.jpg" alt="contextlake, all your real context in one local lake. Pebble the otter surfacing from a misty lake cradling a glowing pebble of context." width="820" </p <h1 align="center"contextlake</h1 <p align="center"<strongAll your real context, in one local lake.</strong</p <p align="center" A local context layer for your AI tools: mirror your repositories, index them<br into a knowledge graph, and serve it over MCP, so agents answer from <emreal source</em instead of guessing. </p
<p align="center" <a href="https://github.com/sayak-sarkar/contextlake/actions/workflows/ci.yml"<img src="https://github.com/sayak-sarkar/contextlake/actions/workflows/ci.yml/badge.svg" alt="CI"</a <a href="https://pypi.org/project/contextlake/"<img src="https://img.shields.io/pypi/v/contextlake?color=137A8B" alt="PyPI"</a <img src="https://img.shields.io/badge/python-3.10%2B-blue" alt="Python 3.10+" <img src="https://img.shields.io/badge/offline-first-2BB3A3" alt="Offline-first" <img src="https://img.shields.io/badge/license-MIT-green" alt="License: MIT" </p
---
Why contextlake
Your AI assistant is only as good as what it can actually see. Point it at one file and it's sharp; ask it about the system, which service calls this API, who depends on that package, where a symbol is really defined across dozens of repos, and it starts guessing.
contextlake gives your tools the real source to read. It mirrors your repositories to your machine, indexes them into a queryable knowledge graph, and serves that graph to your editor over MCP. Everything runs locally and offline, no code leaves your machine, and it carries no credentials of its own.
How it works
contextlake is three layers you adopt one at a time. The mirror is useful on its own, and each layer above it is optional.
<p align="center" <img src="https://raw.githubusercontent.com/sayak-sarkar/contextlake/main/docs/img/architecture.png" width="860" alt="contextlake architecture. On the left, your repos: a GitLab group, plus optional Figma, Jira, and other MCP connectors. In the centre, contextlake indexes and mirrors them into a graph and embeddings, a wiki, and connectors. On the right, it serves the result over MCP to your AI tools: Claude Code, Windsurf, Kiro, Cursor, and Postman." </p
- Mirror. Clone every repo you can reach into a local copy of its namespace tree. Works
with a GitLab group, a GitHub org, a Bitbucket workspace, or a Gitea, Codeberg or Forgejo owner. Each repo lands on its most active branch. One command keeps them fresh, and contextlake schedule install measures a run and installs a background job entry that does it on its own.
- Knowledge layer (optional). Turn the mirror into a graph you can query.
- Code and dependencies across 27 languages, plus Terraform, SQL and PL/SQL schema,
XML Schema, XSLT, ProC embedded SQL, and package manifests (npm, PyPI, NuGet, Maven).
- Semantic search, so you can find code by what it does, not just by its name.
- A wiki, reviewed and scored page by page. Pages that score low are dropped.
- Connectors to Atlassian, Figma, GitLab, Slack and Zendesk.
- Non-code content: Markdown and text, a PDF's text layer, text read out of images by a
local OCR engine, and a video's slides and spoken track.
All of it runs locally. All of it is optional.
- Serve. Expose the result over MCP (the protocol AI tools use to call external tools),