Run the engine, open the dashboard, and see your first trace in five minutes
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
curl -sSL https://raw.githubusercontent.com/AgentX-ai/AgentX-trace-eval/main/install.sh | bashexport PATH="$HOME/.agentx/bin:$PATH" # the installer prints this line but doesn't apply itagentx-server --dev
pip install agentx-pythonagentx-trace-eval --dev
git clone https://github.com/AgentX-ai/AgentX-trace-eval.git && cd AgentX-trace-evaldocker build -t agentx-selfhost .docker run -d -p 4700:4700 -v agentx-data:/data agentx-selfhostdocker logs $(docker ps -lq) 2>&1 | grep "API key" # the key your SDK will use
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):
{"level":30,"time":"2026-09-13T09:41:07.213Z","msg":"Default project API key: agtx_local_..."}
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:
export AGENTX_API_BASE_URL=http://localhost:4700/api/v1export AGENTX_API_KEY=agtx_local_... # from the startup log
Then wrap your agent - a decorator for the simple case, a context manager for full control:
from agentx import AgentXclient = AgentX.from_env()@client.tracer.trace("my-agent")def answer(query: str) -> str: # your agent logic - args become the input, the return value the output return run_my_agent(query)answer("How do I reset my password?")client.tracer.flush(timeout=10) # send queued traces before a short script exits
from agentx import AgentXclient = AgentX.from_env()query = "How do I reset my password?"with client.tracer.trace("my-agent", input={"query": query}, model="gpt-4o-mini") as span: answer = run_my_agent(query) span.output = answerclient.tracer.flush(timeout=10)
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.
A traced LangGraph run: graph nodes, LLM calls, and tool calls as one tree.
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.