agent-tracing 开源项目推荐（61 个）

FailproofAI /failproofai

为 AI agent harness 提供可观测性与强制执行。借助策略执行捕获每一次运行，并保障运行时可靠性。

Continuum-AI-Corp /OrcaReplay

OrcaReplay — Time travel for AI agents. Record, replay, fork, and debug any agent run with any model. Built by the OrcaRouter.ai team.

zjunlp /MemTrace

MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems

gaoshoupaper-code /EvoWriter

Self-evolving multi-agent writing platform — trace-driven evolution loop with human-gated releases

Cognipeer /console

Open-source, self-hosted AI gateway and control plane: OpenAI-compatible LLM routing, RAG, an MCP hub, guardrails and agent tracing for multi-tenant teams.

ungaaaabungaaa /qeth

Local CLI for document quality checks, agent trace reports, bounded web crawling, and offline survey-route planning.

yusuf-eren /openai-agents-tracing

OpenAI Agents Tracing | Open-Source Tracing Dashboard including Costs & Usages

linyp /dsh-plugin-langfuse

Langfuse observability for DeepSeek Harness (dsh): exports agent sessions as OpenTelemetry trace trees (GenAI semconv) to Langfuse's OTLP endpoint

substructureai /subs

subs is an agent harness for the cloud. It runs an unprivileged agent loop and uses MCP servers for executing tools. Use it locally, remotely and with your team. You can customize everything.

SKE-Labs /lightrace

A lightweight tracing platform for agent development

vladkol /agent-evaluation-lab

Evaluation of Multi-Agent Systems on Cloud Run with the GenAI Client in Vertex AI SDK

acailic /agent_debugger

Local-first agent debugger with replay, failure memory, smart highlights, and drift detection.

Cognipeer /console-sdk

Official TypeScript/JavaScript SDK for Cognipeer Console — OpenAI-compatible chat, batch, realtime voice, embeddings, RAG, MCP, agent tracing, and guardrails for multi-tenant AI products.

royhasenfratz /CorruptChain

Trace how a silent tool failure taints a whole agent run: dependency graph, taint paths, and grounded or tainted verdicts.

aaronlab /browsertrace

Local replay debugger for Browser Use failures with screenshots, model I/O, failed-step timelines, and public-safe HTML exports.

silouone /clens

Claude Code session capture and analysis. Trace tool calls, detect backtracks, analyze decisions, track edit chains, and measure plan drift. Local-first, zero-dependency observability.

z7ping /agent-lens

看清 AI 编码智能体的每一次可观察行动。 · Trace your agents, down to every tool and MCP.

tanujbolisetty /google-adk-observability

Comprehensive agent analytics suite for AI agents built with the Google Agent Development Kit (ADK) , LangChain or other popular frameworks, powered by BigQuery Agent Analytics plugin and Grafana

ronsse /trellis-ai

Shared context substrate for AI agents. Retrieval that learns what's useful. Runs local or cloud.

Fujo930 /ORP

Open Reflection Protocol — Turn agent failures into regression tests, reusable lessons, and measurable improvements. Built on OpenTelemetry.