Awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration.

🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23

Skills for Real Engineers. Straight from my .claude directory.

SmartEngine is a lightweight business orchestration engine.

SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.

Cross-LLM sub-agent orchestration as an Agent Skills. Route tasks to Codex, Claude Code, Cursor, or Gemini from any compatible tool.

24h AI/tech news radar with GitHub Actions, live web UI, and Scout Skill for AI sources.

Create best skills based on best books

Painless E2E Automation for Mobile and Web

open source agent engineering platform: traces, evals, and metrics to debug and improve your AI agents. Integrates with LangGraph, CrewAI, Claude Agent SDK, and more.

DingTalk Workspace is an officially open-sourced cross-platform CLI tool from DingTalk. It unifies DingTalk’s full suite of product capabilities into a single package, is designed for both human us…

Drop-in OpenAI API wrapper for Qoder CLI. Supports chat completions, streaming, automatic tool execution, and model name mapping — with a built-in web dashboard and one-line Docker deployment.

Qoder Reverse engineering & Qoder2api demo

Anthropic-compatible API proxy for Qoder via qodercli

The AI framework that adds the engineering to prompt engineering (Python/TS/Ruby/Java/C#/Rust/Go compatible)

The Rust OpenTelemetry implementation

A comprehensive observability solution for monitoring Claude Code usage, performance, and costs.

Fast and Lightweight Observability Data Collector

A request monitoring system for Claude Code that captures and visualizes all API requests and responses in real time. Helps developers monitor their Context for reviewing and debugging during Vibe …

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

LangSmith plugins for Claude Code

The open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, evaluate, monitor, and optimize production-quality AI applications while control…

Claude Code Trace - Export Claude Code chat sessions into markdown and XML

An open-source trace viewer for Claude Code sessions.

A slide framework built for agents.

Map Nintendo Switch Joy-Con controllers to keyboard shortcuts on Windows 11 via Bluetooth, with auto-detection for left/right/dual mode and hot-swappable profiles.将 Nintendo Switch Joy-Con 手柄映射为 Wi…

Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-rep…

GitNexus: The Zero-Server Code Intelligence Engine - GitNexus is a client-side knowledge graph creator that runs entirely in your browser. Drop in a git repository (Github, Gitlab, Azure, Local) or…