contextlake

All your real context, in one local lake.

A local context layer for your AI tools: mirror your repositories, index them
into a knowledge graph, and serve it over MCP, so agents answer from real source instead of guessing.

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.

1. Mirror: clone every repo you can reach in a GitLab group, GitHub org, Bitbucket workspace, or Gitea/Codeberg/Forgejo owner into a faithful copy of its namespace tree, each on its most active branch, kept fresh with one command.
2. Knowledge layer (optional): parse the mirror into a code + dependency graph across 14 languages plus Terraform infrastructure, SQL schema, and package manifests (npm / PyPI / NuGet / Maven), add semantic search, a council-verified wiki (each page reviewed and scored before publishing, low-confidence pages dropped), and connectors to Atlassian / Figma / GitLab / Slack.
3. Serve: expose it all over MCP and an offline interactive graph visualizer, so agents can answer "where is X defined?" or "who calls Y?" instead of grepping.

Each layer has its own guide: the mirror in Usage & config, the knowledge layer and serving in Knowledge layer, and the whole flow start to finish in QUICKSTART.

Install

pip install "contextlake[kb]"       # the full tool: mirror + graph, search, wiki, MCP server
pip install contextlake             # mirror-only core (one dependency: argcomplete)

Everything in the quickstart below needs the [kb] extra (Python 3.10+); the plain install is just the mirroring CLI. Both need Python 3.10 or newer: one floor for the whole tool, since the split floor the mirror core used to allow only ever surprised people.

Prefer an isolated, zero-setup install? uv fetches the right Python and an isolated environment for you:

uv tool install "contextlake[kb]"            # install the CLI on your PATH
uvx --from "contextlake[kb]" contextlake --help   # …or run it once, without installing
# pipx install "contextlake[kb]"             # pipx works too

Docker, the standalone binaries, the full extras table, upgrading, and uninstalling all live on one page: Install and upgrade. If an install misbehaves, see Troubleshooting.

Prerequisites: git, and, only for fleet mirroring, the platform's token env var (GITLAB_TOKEN with read_api + read_repository, or GITHUB_TOKEN / BITBUCKET_TOKEN / GITEA_TOKEN); on GitLab an authenticated glab works instead. The knowledge layer needs neither. Once installed, contextlake, python -m contextlake, and python3 run-contextlake.py are equivalent.

Quickstart: one repo, no setup

You don't need GitLab or any config to try contextlake on a repo you already have. No install? Run it once with uvx: prefix any command below with uvx --from "contextlake[kb]" (e.g. uvx --from "contextlake[kb]" contextlake kb index --source .).

contextlake kb index                     # parse the current repo into a local knowledge graph
contextlake kb graph --overview --open   # open the interactive graph in your browser
contextlake kb serve                     # …or serve it to your AI IDE over MCP

Wire it into your editor in one line, no config file needed (it uses the local ~/.contextlake/kb store you just built):

claude mcp add contextlake-kb -- contextlake kb serve      # Claude Code
# zero-install variant: claude mcp add contextlake-kb -- uvx --from "contextlake[kb]" contextlake kb serve

contextlake kb graph, a whole codebase as one offline, navigable graph.

Everything lands in a local store (~/.contextlake/kb), nothing leaves your machine. Index any path with --source PATH, or every git repo under a directory with --workspace DIR.

Want the full path, mirror a GitLab fleet → graph → wired editor in a few minutes? QUICKSTART.md walks the whole flow.

Fleet mode: mirror a whole org

Where contextlake goes beyond single-repo tools is mirroring and cross-referencing a whole fleet: a GitLab group, a GitHub org, a Bitbucket workspace, or a Gitea/Codeberg/Forgejo owner. Copy the example config and set your platform, group and workspace:

cp .contextlake.ini.example ~/.contextlake.ini

[contextlake]
work_dir = ~/work
gitlab_group = your-gitlab-group
# or any other platform:
# platform = github
# group = your-org

contextlake mirror status      # see where you stand (read-only)
contextlake mirror sync        # fetch → clone → update → branches → verify → audit

Auth is one env var: the platform's token (GITLAB_TOKEN / GITHUB_TOKEN / BITBUCKET_TOKEN / GITEA_TOKEN), carried in headers and the child environment, never in URLs or argv, so .contextlake.ini holds only non-secret settings and is gitignored by default. (On GitLab, an authenticated glab works too; public orgs on other platforms need no token at all.) It runs across hundreds of repos concurrently, with an adaptive worker pool, retries with backoff, and never stomps on the feature branch you're in the middle of.

Behind a slow / TLS-inspecting corporate proxy (e.g. Zscaler) where glab's API calls time out? Set GITLAB_TOKEN (a read_api token) and contextlake enumerates projects via its own HTTP client, which tolerates the slow DNS where glab's short dial timeout fails.

Commands at a glance

Run any command as contextlake <command>; each has scoped help via contextlake <command> --help. Each verb lives under the noun it belongs to, mirror for mirroring git repositories, kb for the knowledge layer, except init, bootstrap, version, completion, and doctor, which span both tiers or neither. Per-command docs live with their layer: the mirror commands in usage.md; the knowledge-layer build commands (kb index, kb embed, kb connect, kb wiki, …) in knowledge-layer.md; the query commands (kb query, kb impact, kb owners) in ask-the-graph.md; and kb serve/kb steer in serve.md.

Global options apply to any command: --dry-run (preview without changing anything), -v/-q (verbosity), --log-file PATH, --config PATH, --version. Output is colorized on a TTY and plain when piped; set NO_COLOR to force-disable.

For runs nobody watches, the systemd timer in examples/, cron, CI, there is a second set: --log-format json (one JSON object per line, every line stamped with a run id), --metrics-file PATH (Prometheus textfile-collector output), --redact (the --log-file copy is already scrubbed of workspace paths, group and repo names), and --access-log. See Reading the console output.

Knowledge layer

Beyond mirroring, the optional contextlake.kb layer turns your repos into a knowledge graph and serves it to AI tools over MCP. It can link repos directly to the Atlassian / Figma / GitLab / Slack items and code symbols that reference them, add semantic search, write a curated wiki, visualize the graph (offline interactive HTML, fleet overview, a symbol's neighbourhood, or a single repo), and generate per-tool steering files + a skills library. Most of it needs no model; the rest works with a local Ollama or any OpenAI-compatible endpoint.

One command sets it all up (configs are read from their default locations):

contextlake bootstrap

Full guide: docs/knowledge-layer.md.

The dashboard

contextlake kb dashboard --serve opens a local, offline-first window into everything the knowledge layer builds: a fleet overview, per-repo anatomy, the cross-repo architecture graph, change-impact (blast radius), health, search, and a Chat tab to ask questions about the fleet in plain language (free graph router always on, LLM-synthesized prose opt-in via --llm-chat). Try it with zero setup via contextlake kb dashboard --serve --sample.

The dashboard: a guided tour, step by step, with screenshots.

Documentation

• QUICKSTART.md, install → bootstrap → wire your editor, in minutes
• docs/install.md, every install channel, upgrading, and uninstalling
• docs/troubleshooting.md, it broke, now what
• docs/dashboard.md, the dashboard, a guided tour with screenshots
• docs/usage.md, the mirror commands and branch safety
• docs/knowledge-layer.md, the graph, connectors, search, wiki
• docs/ask-the-graph.md, kb query, kb impact, kb owners
• docs/serve.md, serve the graph over MCP + wire your editor
• docs/keep-fresh.md, bootstrap, scheduling, and re-indexing on commit
• docs/explained.md, what changes for you, and why it is built this way
• docs/benchmarks.md, where the token/cost/correctness impact comes from, and how to measure it yourself
• docs/internals.md, architecture and internals
• docs/releasing.md, maintainer runbook: versioning, tagging, publishing
• CHANGELOG.md · ROADMAP.md · CONTRIBUTING.md · BRANDING.md

License

MIT, see LICENSE. Pebble the otter is the project mascot; deep context, clear answers.