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.
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
#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.
Never stop coding. Free AI gateway: one endpoint, 231+ providers (50+ free), connect Claude Code, Codex, Cursor, Cline & Copilot to FREE Claude/GPT/Gemini. RTK+Caveman stacked compression saves 15-95% tokens, smart auto-fallback, MCP/A2A, multimodal APIs, Desktop/PWA.
Multi-Agent Harness for Production AI
TypeScript AI agent orchestration framework with dynamic workflows. Describe the goal, not the graph: a coordinator plans the task DAG at runtime and runs it on any LLM (Claude, ChatGPT, Gemini, DeepSeek, or local models).
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
Continual harness optimization