Siddhant-K-code/agent-trace
strace for AI agents. Capture and replay every tool call, prompt, and response from Claude Code, Cursor, or any MCP client
It captures detailed session telemetry beyond LLM calls, including file operations, decision points, and error recovery, which can be exported to observability platforms like Datadog. The tool functions via injected hooks for full session capture in clients like Claude Code, an MCP stdio/HTTP proxy for general MCP clients, or direct Python decorators for custom agent implementations. It offers features like plain-English session summaries, token cost estimation, and diffing between sessions.
Stars
10
Forks
1
Language
Python
License
MIT
Category
Last pushed
Mar 15, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/Siddhant-K-code/agent-trace"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Compare
Higher-rated alternatives
truera/trulens
Evaluation and Tracking for LLM Experiments and AI Agents
traceroot-ai/traceroot
Find the Root Cause in Your Code's Trace
future-agi/traceAI
Open Source AI Tracing Framework built on Opentelemetry for AI Applications and Frameworks
VishApp/multiagent-debugger
Multi-Agent Debugger: An AI-powered debugging system using CrewAI to orchestrate specialized...
evilmartians/agent-prism
React components for visualizing traces from AI agents