GraphCanon updated Sep 20, 2026 · GitHub synced Sep 20, 2026
26views this month
Decision brief
TMA1 is specialized in local-first observability by tracking every LLM call and routing this information to the next agent turn via hooks and MCP.
Good fit when
- Use TMA1 if you are operating self-hosted AI agents and require detailed observability over LLM calls that can be routed into subsequent turns for further action.
- Consider TMA1 suitable when your application needs a straightforward install process on both macOS/Linux and Windows, with minimal setup to start using the tool's local-first observability functions.
Avoid when
- Avoid TMA1 if you prefer cloud-based solutions or require real-time collaboration features that it does not inherently support due to its self-hosted nature.
- Do not use TMA1 in environments sensitive to open ports, since it runs a local server and dashboard accessible at default localhost settings which may not suit all security policies.
- Pricing:
- freemium - Free open-source tool with no initial cost to use or modify according to its Apache-2.0 license.
- Requirements:
- TMA1 requires an installation script that auto-configures and sets up GreptimeDB.; Operational requirements are platform-independent, as it supports macOS/Linux install scripts and a PowerShell one for Windows.
Observed Jul 16, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Very active (0d since push)
- As of Sep 10, 2026
- Provenance
- Not a fork · Organization account
- As of Sep 10, 2026
- Security (OSV)
- No MCP manifest
- As of Jul 15, 2026
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
go get github.com/tma1-ai/tma1Similar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
TMA1 provides local observability by recording every LLM call and routing the data through hooks and MCP into the next agent turn. It supports self-hosted operation, integrates with OpenTelemetry for metrics and tracing, and uses GreptimeDB for data storage.
Capability facts
- Languages
- go
Source: github.language · Sep 10, 2026
Categories
Tags
README
Install wires a coding agent's hooks, MCP entry, and skills. Claude Code and Codex require it for context injection and the commands. It is optional otherwise: OTLP traffic to port 14318 is recorded without it, and Copilot CLI sessions are discovered from disk. ```bash
For agents
This page has a .md twin and JSON over the API.