Developer Tools / Testing & Debugging
A local-first TypeScript toolkit for crash-testing AI agents and MCP servers, replaying failures deterministically, and turning broken traces into regression tests.
The page clearly describes a real developer tool for AI-agent and MCP testing, with concrete workflows, commands, and example outputs. It shows how to record traces, inject faults, replay failures, audit MCP servers, and generate regression tests, which makes it useful for an AI-builder directory listing.
The crawl gives a strong README and quick-start, but it does not show broader adoption signals such as releases, screenshots of results, package publishing status, or real-world case studies. The visible text also cuts off before the end of the generated-test section, so a visitor cannot see the full scope of that workflow from this snapshot alone.
Last evaluated 31 days ago. Current rank #207. Down 3 spots in the rankings.
CodeGraph is a local code knowledge graph for AI coding agents like Claude Code, Cursor, Codex, OpenCode, and Hermes Agent. It aims to cut token use, tool calls, and runtime by letting agents query pre-indexed code structure instead of scanning files repeatedly.
Traccia is an AI agent observability and governance platform with OpenTelemetry-native tracing, runtime policy enforcement, prompt registry, evals, cost attribution, and compliance evidence export.
Single-binary CLI that builds an AI agent knowledge base from git repos, Claude Code/Codex sessions, and saved links. It generates a portable markdown wiki, runs on cron, supports local Ollama mode, and exposes the result for agents via CLAUDE.md/AGENTS.md and MCP.
A lightweight React Markdown renderer with built-in LaTeX, syntax highlighting, streaming-safe rendering, and security-focused defaults.
