mool dashboard — zsh
mool dashboard ········ ██ ██▓▓██ ██▓▓▓▓▓▓██ ██▓▓▓▓▓▓▓▓▓▓██ ██▓▓▓▓▓▓▓▓▓▓▓▓▓▓██ ██████████████████ M O O L M E S H congregating scattered signals into shared understanding v1.6.0 Claude Code: watching 17 files Codex (GPT-5): watching 3 files Qwen CLI: watching 5 files OpenCode: watching 1 files Cursor: watching 2 files Dashboard http://localhost:5200 Press Ctrl+C to stop

MoolMesh

Congregating scattered signals into shared understanding. Unified observability for autonomous agents — running entirely on your machine.

View on GitHub Read the Philosophy
$ pip install moolmesh && mool dashboard

Four views, one surface

Everything your agents are doing — in a single browser tab.

AI Sessions

Live event feed from all agents. Messages, tool calls, token usage, models — as they happen.

Analytics

Token consumption by provider, hourly activity, top tools, top projects. See where the spend goes.

Project Pulse

PR kanban, issues, milestones, GitHub Projects v2. The state of the work, human and AI alike.

Code Timeline

Commit feed, author stats, hot files, daily and weekly digest narratives powered by LLM.


Agents supported

Auto-discovered on startup. No configuration, no API keys, no cloud.

Claude Code JSONL
Codex (GPT-5) JSONL+SQLite
Qwen CLI JSONL
OpenCode SQLite
Cursor SQLite
Aider
Pi
GitHub Copilot CLI
Antigravity CLI
Shipping Planned

Built on four principles

State as truth

If it matters, it lives in SQLite. If it's in SQLite, it's queryable. No volatile caches, no ephemeral memory.

Radical agnosticism

No corporate loyalties. Adding a new agent is an adapter, not a rewrite. The tool serves the developer, not the vendor.

Zero cloud lock-in

Python standard library and SQLite. No accounts, no API keys, no data leaving your machine. Privacy is the architecture.

Zero friction

Session discovery is automatic. If setup takes more than a minute, something is wrong.


Under the hood

Built for developers who care about what runs on their machine.

<200MB RAM footprint
0 External dependencies
651 Tests passing
~1s Cold start

MCP Server & headless mode

MoolMesh works with a dashboard or without one.

MCP stdio server

Read-only access to session data via the Model Context Protocol. Any MCP-compatible agent can query active sessions, token usage, tool stats, and project activity. Runs as a separate process (~15 MB RAM), independent from the dashboard.

Headless CLI

Generate Markdown reports, discover sessions, and manage repos — all without launching the dashboard. Ideal for CI pipelines, cron jobs, or scripting into your existing workflow. Every command exits cleanly with structured output.


Technical details

Python 3.11+ stdlib only

No pip packages at runtime. tomllib, sqlite3, http.server, threading. That's the stack.

SQLite persistence

Two databases: events.db for sessions, github.db for repos. WAL mode, transactional offsets, crash-safe. Schema migrates automatically on startup.

SSE live streaming

Server-Sent Events with id: fields for zero-gap reconnection. Browser disconnects and reconnects get replayed from SQLite — no events lost.

macOS + Linux

macOS uses kqueue for instant file detection. Linux falls back to polling (~1s). Both work out of the box, no configuration needed.