Every thought. Every tool call. Every error. Captured live as your agent runs — in a dashboard that updates in real time.
Free up to 5,000 events/mo · No credit card required · 2 lines of code
I need to check the user's subscription status before processing the refund request.
get_subscription(user_id: "usr_4829")
{"status": "active", "plan": "pro", "eligible_for_refund": true}
User is eligible. Processing refund now
Works with any agent — LangChain, CrewAI, raw OpenAI calls, or your own loop.
from traceagently import TraceAgently
ta = TraceAgently(api_key="ta_live_...")
with ta.trace(agent_id="support-bot",
task="Refund order #123") as t:
t.thought("Checking order status")
t.tool_call("get_order", {"id": 123})
t.tool_result({"status": "delivered"})
t.final_response("Order was delivered")import { TraceAgently } from 'traceagently'
const ta = new TraceAgently({ apiKey: 'ta_live_...' })
const trace = await ta.startTrace({
agentId: 'support-bot',
task: 'Refund order #123'
})
await trace.thought('Checking order status')
await trace.toolCall('get_order', { id: 123 })
await trace.end('Order was delivered')Built for developers who ship autonomous agents to production.
Watch every event stream live as your agent thinks, calls tools, and responds. No refresh needed.
Automatically groups recurring errors across all your agent runs so you can spot systemic failures fast.
One click sends your full trace to Claude, which diagnoses what went wrong and gives you an exact fix.
Token usage and estimated cost per trace. Know exactly how much each agent run is costing you.
SHA-256 hashed keys. Multiple keys per project, labeled so you always know where they're used.
Works with LangChain, CrewAI, raw OpenAI, Claude, Gemini, or any custom agent loop you've built.
Start free. Upgrade when you need more.
From zero to live traces in under 2 minutes.
Install the SDK
pip install traceagently # Python
npm install traceagently # TypeScriptGet your API key from the dashboard
ta_live_••••••••••••••••••••••••••••••••Wrap your agent
from traceagently import TraceAgently
ta = TraceAgently(api_key="ta_live_...")
with ta.trace(agent_id="my-agent", task=user_task) as t:
# your existing agent code here
t.thought(llm_response)
t.tool_call(tool_name, args)
t.final_response(result)Free forever for side projects. No credit card required.
Get started free