tma1-ai

Tma1 — AI skill for Claude Code

AI community

Local-first observability your agent reads back.

How to install Tma1

This entry records only its repository, not the path inside it, so there is no exact command to give. Open tma1-ai/tma1 and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Tma1 does

Local-first observability your agent reads back. TMA1 records every LLM call, then routes what it sees into the agent's next turn via hooks and MCP.

Alternatives in AI

TokenTracker — Local-first AI token usage & cost tracker for 31 coding tools incl 1.4k ★
Flow Next — Plan-first AI workflow plugin for Claude Code, OpenAI Codex, and Factory Droid 569 ★
New Crud — Generate full CRUD (model, controller, service, views, routes, permissions, hooks) for a module 407 ★

README

TMA1

[![Release](https://img.shields.io/github/v/release/tma1-ai/tma1?include_prereleases&label=release&color=orange)](https://github.com/tma1-ai/tma1/releases) [![CI](https://github.com/tma1-ai/tma1/actions/workflows/ci.yml/badge.svg)](https://github.com/tma1-ai/tma1/actions/workflows/ci.yml) [![License](https://img.shields.io/badge/license-Apache--2.0-blue)](LICENSE) ![Platform](https://img.shields.io/badge/platform-macOS%20%7C%20Linux%20%7C%20Windows-lightgrey)

A monolith for your agent's loop. Silent until it talks back.

TMA1 is local-first observability for LLM agents, powered by GreptimeDB. It records every LLM call on your machine, then routes what it sees back into the agent's next turn through hooks and MCP tools.

One binary. No Docker. No Grafana. No cloud account.

![TMA1 Dashboard](site/public/screenshots/hero-dark.webp)

The name comes from TMA-1 (Tycho Magnetic Anomaly-1) in *2001: A Space Odyssey*: the monolith buried on the moon, silently recording everything until you dig it out.

What TMA1 Does

TMA1 has two jobs:

Show the human what happened.
Tell the agent what it should notice before the next step.

The dashboard gives you token usage, cost, latency, tool activity, full conversation replay, anomaly history, prompt evaluation, and SQL access to the underlying data.

The agent loop gives Claude Code and Codex a compact `` block before each turn, can block `Stop` when a HIGH-severity issue is still unresolved, and exposes seven MCP tools the agent can call on demand.