AI Testing & Debugging

Local code review studio for AI agent-generated changes with line comments and MCP handoff

Autonomous web app testing agent that explores flows, finds bugs, and generates self-healing tests from a URL

LLM engineering platform for gateway routing, observability, evaluations, and prompt optimization

Mac tool that turns screenshots into JSON readable by CLI agents

Automated bug tracking, error monitoring, and contextual reporting platform for modern web applications

Expect lets agents test code in a real browser by scanning diffs, generating plans, and running execution workflows from one command

TestSprite is an AI testing agent that can plan, write, execute, debug, and report software tests end to end

Ogoron is an automated testing platform where autonomous agents plan, generate, and maintain tests directly from your codebase

QA.tech uses AI agents to explore web apps, generate complete test suites, and run QA checks on release, schedule, or manual triggers

End-to-end testing and observability for conversational AI. Run pre-production simulations and monitor production conversations for voice and chat agents

Glassbrain helps teams visually debug LLM apps by capturing every OpenAI, Anthropic, and LangChain call and replaying failed runs

Future AGI helps teams build, evaluate, optimize, and monitor LLM and AI agent applications with multimodal quality testing and observability

Coding-agent observability for session costs, tokens, cache usage, tool calls, file edits, and terminal replays across Claude Code, Codex, and more

Waydev is an engineering analytics platform for measuring delivery performance, DORA metrics, and productivity trends

Simple, open-source LLM tracing for AI agents. Track prompts, completions, latency, token usage, and cost

Render AI chat data and Codex logs into filterable browser timelines

Regression testing and semantic diff platform for agent apps to catch behavior changes before release

Open-source debugging and run-inspection tool for AI agent workflows, prompts, tool calls, and runtime state

Open-source agent engineering platform with traces, evals, and metrics for debugging AI agents

AI-assisted release management for release notes, launch checklists, and rollout communication

AI agent that reproduces GitHub issues and returns evidence-backed reports

Debug AI agents by recording, replaying, forking, and sharing runs

Open-source AI agent monitoring and quality platform that detects failure modes and helps developers fix agent issues before production

Dedicated QraftAI agent for generating and running cross-browser QA tests

Product-drift review for AI-written pull requests

Real-time production evaluation for AI agent runs

OpenTelemetry-based tracing and observability for prompts, model calls, tool spans, tokens, latency, and errors in production AI applications

AI agent that monitors production logs, detects incidents, and opens reviewable fix PRs

AI tool that reviews pull requests, analyzes CI failures, and submits fixes

Runs pull requests in ephemeral environments and reviews them with runtime evidence

Lets coding agents and CI publish screenshots, recordings, and ready-to-paste Markdown to pull requests

Local cost observability for 40 AI coding tools, broken down by task, model, project, and pull request

Local LLM proxy that records usage, failures, retries, and billing-integrity receipts per call

Turns website QA checklists from spreadsheets, CSVs, or PDFs into parallel testing agents

Validate integration code inside AI coding assistants with runnable sandbox APIs, webhooks, and failure scenarios

Inspect, explain, stop local port processes, and share localhost from the macOS menu bar

Find and cluster AI agent failures from real conversations and traces, then turn them into actionable evals

AI Agent 驱动的开源视频生成工作台 — 小说→角色/场景/道具设计→剧本→分镜图→视频，跨镜头角色与场景一致 | Open-source AI video workspace powered by AI Agents, Nano Banana 2 & Veo 3.1 / Grok / Seedance / OpenAI

Native AI keying runtime and OFX plugin for DaVinci Resolve, built in collaboration with Corridor Digital

Call MCPs via TypeScript, masquerading as simple TypeScript API. Or package them as cli

Make Any Website & Tool Your CLI. A universal CLI Hub and AI-native runtime. Transform any website, Electron app, or local binary into a standardized command-line interface. Built for AI Agents to discover, learn, and execute tools seamlessly via a unified AGENT.md integration

Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowledge graph + autonomous consolidation

🤖 Type-safe, provider-agnostic TypeScript AI SDK for streaming chat, tool calling, agents, and multimodal apps across OpenAI, Anthropic, Gemini, React, Vue, Svelte, and Solid

Local semantic search for AI agents

Automate software delivery with coding, visual QA, and production monitoring agents

Trace, evaluate, and improve AI agents in production