Zero-config tracing
Context manager and @trace decorator capture steps with one import and no framework lock-in.
Visualizes and debugs multi-step LLM agent workflows with interactive graphs and local inspection
pip install flowtraceAI agents chain dozens of LLM calls, tool invocations and memory reads yet failures are opaque. Existing observability is cloud-only, framework-specific or noisy. FlowTrace is a lightweight local dashboard that auto-instruments any Python agent code, rendering clean interactive graphs so developers can instantly understand and fix behavior.
Everything you need, nothing you don't.
Context manager and @trace decorator capture steps with one import and no framework lock-in.
SVG node-link diagram shows execution flow, nesting, timing and step types using a strict grid layout.
Click any node to view raw prompts, responses, token counts, latency and metadata in side panels.
Lists every tool invocation with input, output and the exact code location that triggered it.
Traces saved to SQLite; browse history, compare runs and filter by duration or success.
Re-execute a saved trace with mocked tools to experiment without hitting real APIs.
Simple POST endpoint accepts traces from non-Python agents or remote services.
Aggregate view shows token usage, success rate, slowest steps and common failure patterns.
From install to result in seconds.
Three steps. Full docs live in the README.
pip install flowtraceflowtrace servepytestStars help other developers discover FlowTrace. Issues and PRs are very welcome.
Star on GitHub