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.
Record and analyze every interaction of your AI agent to improve its performance and responses.
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytimeLocal-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.
tma1 has 116 stars on GitHub. It has been forked 14 times. tma1 is written mainly in Go. It has been in active development since 2026. tma1 is available under the Apache-2.0 license. Its main topics are agent-loop, agent-observability, ai-agents, claude-code.
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.
tma1 is an open-source project. It is released under the Apache-2.0 license.
Yes. tma1 is free and open source — you can use, modify and self-host it.
tma1 is available under the Apache-2.0 license.
tma1 is written mainly in Go.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/tma1-ai-tma1.html)
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.