Skip to main content
By the end of this page you’ll have the engine running locally, the dashboard open, and a real trace from your own code on screen.
1

Install and start the engine

The curl and pip paths download prebuilt binaries, and the Docker build compiles the engine inside the image and downloads the prebuilt dashboard bundle from the latest release - no local Node, Go, or Bun needed on any path. The curl path installs into ~/.agentx/bin and prints the export PATH line above without applying it, so run it (and add it to your shell profile) before agentx-server resolves. The startup log prints the key you’ll need in step 3 - the engine logs structured JSON lines (pipe through npx pino-pretty for a readable form):
2

Open the dashboard

--dev opens http://localhost:4700 in your browser (with Docker, open it yourself). In the default no-login mode the engine hands the dashboard the Default project’s API key automatically, so you land directly on the Overview tab - nothing to paste. To confirm you’re connected, the corner of the Platform Settings page shows the engine and dashboard versions.
No login is the deliberate local-testing default: anyone who can reach the port gets the key. For a shared or network-exposed engine, set AGENTX_AUTH=enabled to require sign-in - see Self-Host Configuration.
3

Trace your agent

Point the SDK at the engine with the same key:
Then wrap your agent - a decorator for the simple case, a context manager for full control:
Both snippets exit silently on success - tracing is fire-and-forget by design and never raises into your agent. flush() returns True once the queued trace has been sent.Using LangChain, OpenAI Agents, CrewAI, or another framework? A one-line integration captures the full execution tree automatically - see Framework Integrations.
4

See it in Observe

Open Observe → Live Traces. Your trace appears within seconds - click it for the full detail: input/output, latency, tokens, estimated cost, and (for multi-step agents) the Execution Timeline and Graph views of every step.
screenshot of the trace detail dialog showing the stat strip (duration, tokens, cost), the Trajectory metrics row, and the Execution Timeline with an agent span, tool span, and LLM span nested under the root.

A traced LangGraph run: graph nodes, LLM calls, and tool calls as one tree.

Where to go next

Full tracing guide

Tool calls, sessions, span trees, async agents

Evaluate with a dataset

Score your agent with an LLM judge in one script

Monitor production

Scorers and signals on live traffic

Gate releases in CI

Block merges when quality drops
Provider keys (OPENAI_API_KEY, ANTHROPIC_API_KEY, GEMINI_API_KEY, or OPENROUTER_API_KEY) unlock the LLM-judge features - evaluation scoring, live judge scorers, semantic patterns. Set them as environment variables on the engine or later from the dashboard’s Platform Settings page (a key set there takes precedence over the env var). Tracing itself needs none.