Governance MCP server for agent-maintained knowledge bases (OKF): git-backed writes, search, lint.
io.github.BeppeTemp/cartographer β Governance MCP Server
This MCP server supports agent-maintained knowledge bases (OKF) using git-backed writes, search, and linting. It is identified as a Governance MCP server, with topics covering Go, knowledge-base management, LLM agents, and the MCP ecosystem.
π οΈ Key Features
Git-backed writes for knowledge bases (OKF)
Search capabilities
Linting support
π Use Cases
Maintaining an OKF knowledge base with agent-driven updates
Searching within an OKF repository for relevant content
Running lint checks as part of knowledge base upkeep
β‘ Developer Benefits
Integrates governance-focused operations for OKF via MCP
Supports a workflow of write β search β lint
β οΈ Limitations
Only the following functions are described: git-backed writes, search, and linting. Additional capabilities are not specified.
Shared memory for your team's AI agents β one wiki they all read and grow, and none of them can break.
What a colleague's agent works out on Monday, yours already knows on Tuesday β even on another client.
Cartographer is the platform: Meridian (server), Compass (client), Atlas (web UI) and Surveyor (maintenance agent), one Go binary, git underneath.
Claude Code, Codex, OpenCode, Kiro, Antigravity, Crush, Copilot, Pi, Cline and [any MCP client](docs/mcp-clients.md).
A film of about 80 seconds: four teammates, each with their own coding agents, share one Cartographer wiki. On Monday Alice's agent writes down why staging breaks; on Tuesday Marco's agent, on another laptop and another client, finds her note and answers; every day the others add to it. The film ends on the four components of the one binary: Meridian, Surveyor, Atlas and Compass.
Drawn by the Atlas's own graph engine.
Why
AI agents start every session from zero, and on a team every colleague's agent starts from its own
zero: what one learns stays on that person's machine, in that client. The usual fixes each solve
a third of the problem:
RAG retrieves, but nothing accumulates β the agent never gets to write down what it learned.
A folder of Markdown the agent edits freely ends in broken links, lost history and silent
corruption.
Skills, subagents and instructions get hand-copied into .claude/, .codex/, .kiro/β¦
and drift apart on every machine.
Cartographer puts all three in one place: your agents read and grow a knowledge base only
through MCP tools, behind a server that enforces the rules, and the same knowledge base carries
how your agents are set up.
Try it now
Open the static Atlas demo: a finished, read-only
knowledge base on astronomy, with nothing to install. To give your agents a knowledge base of their own,
see the Quick start.
The four components
One binary, deployed as four components that you pick from:
Component
What it is
Command
Deploy it when
Meridian
The server: the only writer of a KB, MCP over HTTP (or stdio for one local client)
cartographer serve
Always: it holds the KBs
Surveyor
A headless maintenance agent for one perimeter of KBs
cartographer surveyor
You want the wiki kept in order without a person asking
Atlas
The read-only web UI, served by Meridian
none (a switch of Meridian)
You want to see the graph, the changes and the findings
Compass
The client next to the agent: configures every agent client, syncs, runs the local bridge, hosts client plugins
cartographer connect, sync
On every machine where an agent runs
Three rules hold them together: components talk only through documented interfaces; each does only its
job; you deploy only what you need. Details: docs/deployment.md.
The deployment film: the four components with their role, then everyone with their own installation, many people on one server, any MCP agent with no client, and all together: one KB cloned by several servers, with people and agents on each.
Four scenarios: everyone on their own laptop, a team on one server, any MCP agent with no client, and all of them around one KB. See the deployment scenarios.
What you get
π§ Memory that compounds (Meridian). A wiki the agent builds over time (Karpathy's LLM Wiki pattern): plain Markdown + YAML in a git repository you own, readable in Obsidian or any editor. No lock-in.
π‘οΈ Guardrails, not good intentions (Meridian). Agents write only through MCP tools, and Meridian is the only writer of a KB: schema and link checks, lint, optimistic concurrency, one commit per write, a signed audit log. The agent cannot leave the KB broken.
π₯ Built for teams (Meridian). Several KBs behind one server, per-KB and per-map access with bearer-token roles, git as the sync layer, conflicts turned into a guided workflow, SOPS-encrypted secrets.
πΊοΈ See it all (Atlas). A read-only web UI in the same binary: a living 3D graph, search, what the agents changed, what the KB ships to them, and what needs fixing.
The embedded Atlas: a knowledge base drawn as a living 3D graph β searched, a concept opened with its links, recoloured by map, the skills it ships to agents, the findings that need attention and the Surveyor settings.
The Atlas, served by Meridian, on a generated demo KB.
π Keeps the wiki in order while nobody is looking (Surveyor). Its tasks ingest from feeds and polled sources, repair and review the KB and write syntheses, through the same MCP tools, with its own model budgets. Recipes: docs/surveyor-recipes.md.
The Surveyor at work in the Atlas: a source is declared in Settings, a Surveyor run starts, the Activity page shows the run, the graph gains the new concepts, and one source that fails raises an alarm in the Work panel.
π Extend it with plugins. A plugin is a git repository or a folder that extends every component: clients, skills, subagents, hooks, commands and script tools on Compass; roles and presets on Meridian; recipes and connectors on the Surveyor; branding, views and apps in the Atlas. A client Cartographer does not know yet (a fork, an in-house build) is one plugin away. It is installed with one command, pinned to a commit and enabled only after you approve what it does: docs/plugins.md.
The plugins film: a plugin adds to each component; one plugin for a company; installed with a preview, approved per version, and stopped when one byte of a script changes.
Install and quick start
bash
# macOS (Homebrew)
brew install beppetemp/tap/cartographer
# Windows (PowerShell; no administrator rights)
irm https://raw.githubusercontent.com/BeppeTemp/cartographer/main/install.ps1 | iex
# Linux / macOS without Homebrew
curl -fsSL https://raw.githubusercontent.com/BeppeTemp/cartographer/main/install.sh | sh
# From source (Go 1.26+)
go install github.com/BeppeTemp/cartographer/cmd/cartographer@latest
Pre-1.0: breaking changes bump the minor version and are called out in the changelog.
Windows runs natively; WSL is covered in docs/deployment.md.
Then, with git and an empty git repository you own (GitHub, Gitea, any host) to hold your first KB:
bash
cartographer setup # server, first KB and your agents, in one guided step
setup shows its plan before touching anything, then installs the local service, creates the KB,
connects every agent client it detects and verifies the result. Everything it writes is listed, and
removable, in docs/getting-started.md.
Restart your agent sessions and ask for something worth keeping:
Explore this repository and write a concept page about its architecture in the wiki.
Then open the Atlas (by default http://127.0.0.1:39273/ui/) and watch the page appear. Next session,
ask something related: the agent finds what it wrote and builds on it.
Your KB stays your git repository: Meridian, the only writer, pushes to the remote you gave it.
Cartographer calls no model itself (only the Surveyor does, if you run one), and on loopback no token
is needed; a shared server uses bearer tokens (docs/transport-auth.md).
Prefer to let your agent install it? Paste this:
text
Set up Cartographer on this machine by following
https://raw.githubusercontent.com/BeppeTemp/cartographer/main/docs/agent-install.md
My first knowledge base is at: `<git remote URL>`
If you are an agent asked to install Cartographer: follow that runbook, not the Quick start.
Plugins β add clients, commands and MCP tools, approved per version
Contributing
Bugs and ideas go to issues; a
question starts from the FAQ. PRs are welcome: CONTRIBUTING.md
covers building, testing and the PR flow. Cartographer is a personal project maintained on a best-effort basis.
Security reports: SECURITY.md.