tma1-ai/

TMA1 / AGENT OBSERVATORY

Close the loop
around your agent.

Sessions, tool calls, and token usage in one local workspace. Inspect what happened, compare runs, and feed observations back into the agent.

Claude Code · Codex · Copilot CLI · OpenCode

One view across agents
Overview · activity, recent sessions, and recorded tool outcomesScreenshots and video use demo data.

From activity to the details

Follow the conversation alongside tool calls and file activity. Search recorded messages and open the matching event.

Session replay
Watch a session walkthrough

Screenshots and video use demo data.

Observations the agent can read

Context for the next turn

Claude Code and Codex hooks provide session context and advisory findings. Prompt review can use a configured model to suggest changes backed by conversation excerpts.

Search across sessions

MCP tools and the /tma1-peer and /tma1-search skills retrieve earlier conversations, including work from other agents on the same project.

Run locally

Paste this instruction into Claude Code or Codex

Read https://tma1.ai/SKILL.md and follow the instructions to install or upgrade TMA1 for your AI agent

Manual installation
# macOS / Linux
curl -fsSL https://tma1.ai/install.sh | bash

# Windows (PowerShell)
irm https://tma1.ai/install.ps1 | iex

OpenTelemetry SDKs: send OTLP/HTTP to http://localhost:14318/v1/otlp. GenAI traces use the OpenTelemetry GenAI semantic conventions.

OpenCode imports sessions through a plugin or an exported snapshot. Import does not install hooks or inject context. Copilot CLI session logs are discovered automatically.

OpenCode setup →

Local storage. Explicit model access.

Traces and conversations are stored in ~/.tma1/data/, backed by GreptimeDB. Optional model reviews send selected prompts and conversation excerpts to the configured provider.

Read the integration docs →