agent-testing 开源项目推荐（233 个）

langwatch /langwatch

面向 AI 平台团队的开源 Agent 可观测性与评估。追踪、测试、路由和治理公司内的每个 Agent 与编码助手。

langwatch /better-agents

Standards for building agents, better

reticlehq /reticle

AI agents can generate code, but still struggle to understand what they build. Reticle brings Jev-style machine-native runtime perception to web & desktop applications.

langwatch /scenario

Agentic testing for agentic codebases

LeoYeAI /myclaw-bench

The definitive benchmark for AI agents on OpenClaw. 45 tasks across 4 tiers. Powered by MyClaw.ai

UiPath /coder_eval

Playwright for coding agents. Test that your skills, MCP servers, and CLIs actually work when an agent uses them — sandboxed YAML suites, A/B experiments, CI gates.

chandralegend /nomos

Ship agents you can audit.

christiangrey922 /multi-agent-workflow-lab

Testing and observability for multi-agent delegation, MCP tools, permissions, sandboxed actions, prompts, and workflow replay.

LambdaTest /rook

rook by TestMu AI: Agent Assurance from the terminal. Test how your AI agents actually behave across workflows, tools, and actions, and catch failures and vulnerabilities before they ship.

najeed /ai-agent-eval-harness

The open-source MultiAgentOps evaluation and verification harness for any industry business workflow.

Aurite-ai /agent-verifier

🔍 Agent Verifier is a coding agent skill that verifies code against organizational policies, code quality patterns, security requirements, and framework best practices — before code ships. Works with Claude Code, Cursor, Windsurf, and 30+ agents.

ProofAgent-ai /proofagent-harness

Open-source test harness for AI agents. Stress-test production agents with adversarial multi-turn scenarios in CI

airtasystems /Genbounty-LLM-Hunter-Community-Free

Toolkit for AI whitehats, internal red teams, llm bug bounty hunters and mlops - Adversarial testing for AI, LLMs, and Agents.

theagentplane /chronicle

Record-and-replay for agent decision graphs: reproduce a prod agent failure as a committed regression test, and re-run your fix without live LLM calls.

DefuzeX-AI /AgentBehaviourBench

AgentBehaviorBench (ABB): A benchmark for evaluating AI agents’ ability to test other agents and detect behavioral defects.

LambdaTest /homebrew-rook

Official Homebrew tap for rook by TestMu AI: agent assurance from the terminal. brew install lambdatest/rook/rook

LeonEvo1103 /surfaceloom

Open-source AI agent testing framework for browser and native desktop apps, with explicit tool effects, evidence, lifecycle, and trace contracts.

arthi-arumugam-git /whatbroke

Diff your AI agent's behavior between two runs. See exactly which tool calls, args, costs and outputs changed when you swap models or edit prompts.

mnvsk97 /agentbreak

infrastructure chaos to test the resilience of ai agents

TaimoorKhan10 /replayd

Turn failed AI agent runs into replayable regression tests. Catch regressions before you ship.