mcp-test-harness
HN: An automated CI/CD testing harness for Model Context Protocol servers
Open-source projects. Clever little tools. Big ideas.
Unearthed from the Hacker News community.
HN: An automated CI/CD testing harness for Model Context Protocol servers
Ruflo: An agent meta-harness for Claude Code and Codex
MemU – Personal Memory Shared by Codex, Claude Code, and Hermes
Auto-continue Claude Fable 5 the second your 5-hour limit lifts
Contextrot– Analyze where Claude Code degrades from its own session log
Coordination layer for AI coding agents, built on Git
Proxy for OpenAI Codex and Claude Code, use any LLM with those apps
Use Any Agent as an Orchestrator
Jackrong LLM Fine-Tuning Guide
CLI that helps AI agents avoid vulnerable dependencies
Running over 80M tokens in one agent session with no compaction
OpenLore: Deterministic, local-first memory and guardrails for AI coding agents
What broke when I let an AI agent modify its own Python code for 144 cycles
I built a tiny proxy that gives GLM 5.2 vision (or any text LLM) – MIT
Looma – turn coding-agent history into resumable project context
How to Build a Coding Agent
Make your terminal pulse orange when Claude Code needs input
Local Search Agent – RAG replacement, no embeddings, free tier