How data is stored
TMA1 stores traces and conversation logs on your local disk in ~/.tma1/data/. Nothing is uploaded to remote services, and you can inspect or delete the data at any time.
TMA1
Know what your agent is doing and what it costs
Tokens, cost, latency — every LLM call, recorded locally. Click a spike to see which conversation is burning money.
_
AGENT ONBOARDING
Read https://tma1.ai/SKILL.md and follow the instructions to install and configure TMA1 for your AI agent
Manual install
terminal
# macOS / Linux
$ curl -fsSL https://tma1.ai/install.sh | bash
# Windows (PowerShell)
> irm https://tma1.ai/install.ps1 | iex
localhost:14318
See what happened
An agent ran for 20 minutes. What did it do? Open the dashboard, click a trace, read the full conversation.
Catch the expensive calls
That $40 session last Tuesday — was it one huge context window or a runaway retry loop? Now you know.
Nothing leaves your machine
Your agent sees your codebase, your env vars, your keys. That data stays in ~/.tma1/, never uploaded anywhere.
Features
Observability without the overhead
Seven views for Claude Code, Codex, Copilot CLI, OpenClaw, OTel GenAI, Sessions, and Prompts. The dashboard picks the right one from your data. No Grafana, no cloud, no YAML.
Cost breakdown
Which model costs the most? Which conversation burned through your budget? Token counts and estimated cost per model, plus burn-rate over time and cache hit ratios.
localhost:14318
Anomaly detection
An agent stuck in a retry loop can burn hundreds of dollars. Each agent view has an Anomalies tab. Click any flagged request to jump straight into that session and see what went wrong.
localhost:14318
Sessions
Your agent ran for 25 minutes across 4 turns. What happened? Open the session overlay: left side shows file activity, context breakdown, and API calls. Right side is the full event timeline. Or watch the live canvas while your agent works.
localhost:14318
Tool analytics
When your agent feels slow, is it the model or the tool calls? p50 and p95 latency per tool, call counts, success rates, and trend lines.
localhost:14318
Security monitoring
Your agent can run shell commands, fetch URLs, and be fed injected prompts. TMA1 flags all of it. For OpenClaw it also tracks webhook errors and stuck sessions.
localhost:14318
Full-text search
Type a keyword in the Sessions search tab and it finds matching conversations, tool calls, and results across all sessions. Click a result to open the session at that exact event.
localhost:14318
How it works
Setup
Paste the onboarding instruction into your agent and it handles the rest. Or do it yourself:
[1]
Install
One command. Downloads everything into ~/.tma1/. No Docker, no system packages.
[2]
Configure your agent
Point the OTel endpoint to http://localhost:14318/v1/otlp. Works with Claude Code, Codex, OpenClaw, or any OTel SDK. GitHub Copilot CLI needs no config — TMA1 auto-discovers its session logs.
[3]
Open the dashboard
Browse to localhost:14318. Traces show up seconds after your agent’s next LLM call.
Security
Security & Privacy
Your agent reads your codebase, your API keys, your infrastructure. Sending that to a cloud observability service defeats the purpose. Everything stays local.
No network calls
After first launch (which downloads the embedded database engine once), TMA1 makes no further network calls. No analytics, no crash reports, no update checks.
Fully open source
TMA1 is Apache-2.0. Read the code, audit the build, and run it air-gapped.
Single binary
tma1-server runs as one local process and manages its embedded storage engine. No Docker, no system packages, no runtime dependencies.
Your data, your disk
Delete ~/.tma1/ and everything is gone. No orphaned cloud state, no remote accounts to close.
FAQ
Common questions
Which agents are supported?
Any agent that emits OpenTelemetry data, plus a few via JSONL auto-discovery. Claude Code sends metrics and logs. Codex sends logs and metrics, and session JSONL is auto-parsed for conversation replay. GitHub Copilot CLI is zero-config: its session JSONL at ~/.copilot/session-state/ is auto-discovered. OpenClaw sends traces and metrics, and session JSONL is auto-parsed for conversation replay. Any OTel SDK app with GenAI semantic conventions works out of the box. The dashboard auto-detects the data source and shows the right view.
Can I query the data with SQL?
Yes. Run mysql -h 127.0.0.1 -P 14002 to connect to the local SQL endpoint, or open localhost:14000/dashboard/ for the built-in query UI. Traces are in opentelemetry_traces, logs in opentelemetry_logs, session data in tma1_hook_events and tma1_messages, and OTel metrics get auto-created tables.
How much disk space does it use?
It depends on traffic and conversation length. A typical setup uses a few hundred MB per month.
Quick start
Try it now
Paste this into your agent. It reads the skill file and handles the rest.
AGENT ONBOARDING
Read https://tma1.ai/SKILL.md and follow the instructions to install and configure TMA1 for your AI agent
Or install manually
terminal
# Install TMA1 (macOS / Linux)
$ curl -fsSL https://tma1.ai/install.sh | bash
# Install TMA1 (Windows PowerShell)
> irm https://tma1.ai/install.ps1 | iex
# Start TMA1
$ tma1-server
# Configure your agent (example: OpenClaw)
$ openclaw config set diagnostics.otel.endpoint http://localhost:14318/v1/otlp
# Or any OTel SDK
$ export OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:14318/v1/otlp
# Open dashboard
$ open http://localhost:14318