Open highlighted repo slot
Put your repository first
Promote a GitHub repo at the top of Awesome repository list views for 7 days.
Awesome List
Awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration.
GitHub stars and default-branch commits for ai-boost/awesome-harness-engineering.
Open highlighted repo slot
Promote a GitHub repo at the top of Awesome repository list views for 7 days.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
Never stop coding. Free MIT AI gateway: one endpoint, 359 providers (150+ free), 1200+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by hundreds of contributors
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
Multi-harness agentic plugin marketplace for Claude Code, Codex, Cursor, OpenCode, GitHub Copilot, and Google Antigravity
Teams-first Multi-agent orchestration for Claude Code
#1 Persistent memory for AI coding agents based on real-world benchmarks
Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.
Practical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (inspired by Addy Osmani and Boris Cherny). Includes loop-audit, loop-init, loop-cost.
Multi-Agent Harness for Production AI
Self-hosted TypeScript agent runtime with durable approvals and verifiable run records. Own it, approve it, audit it.
The missing DevTools for Claude Code — inspect session logs, tool calls, token usage, subagents, and context window in a visual UI. Free, open source.
a recursive self-improving harness designed to help your agents (and future iterations of those agents) succeed on any task
MCP Fusion - The TypeScript framework for secure MCP servers.
Continual harness optimization