v2.1.2 · MIT
The agentic meta-harness — freeze the model, evolve the harness. An open runtime that routes each query to the cost-optimal model, evolves its own harness (planner/context/reviewer/retry/tool/memory/score policy) and autonomously repairs code, then orches
— · MIT
Turn human SOPs into deterministic, gated agentic workflows — a Claude Code plugin.
— · MIT
The framework that powers your Agentic Company
v1.2.0 · MIT
ERPAVal — autonomous software development. Six-phase Explore/Research/Plan/Act/Validate/Compound workflow with classifier-driven routing and a compounding lessons store.
v2.5.0 · MIT
Self-Optimizing Neural Architecture (SONA) for Claude Flow — adaptive learning, trajectory tracking, pattern reuse, 7 RL algorithms (PPO/A2C/DQN/Q-Learning/SARSA/Decision Transformer/Curiosity), Flash Attention, MoE routing, LoRA, EWC++ for continual lear
v5.9.1 · MIT
🥇 The strongest free web search plugin for DeepSeek Harness, and the search bridge for every model without native web access. Free, no signup, no API key. Ask the web or X, get structured JSON evidence. | 🥇 全网最强的 DeepSeek Harness 免费联网搜索插件,免费免注册免 API key。为不能联网的模型补上搜索,问网页或 X,拿回结构化 JSON 证据(搜索、抓取、引用)。
v0.6.25 · MIT
Achieve extraordinary results with claude code across a variety of tasks
v0.20.0 · MIT
Idea-to-store harness for Flutter/Flame games
v2.4.2 · MIT
A Claude Code plugin whose workshop of expert agents learns as it builds: repeated fixes become permanent rules, loved tweaks become taste it remembers - and every change waits behind a write gate you control.
v0.3.0 · MIT
Claude Code plugin for autonomous AI research — multi-agent loops take a bare topic all the way to running experiments, with no human-written experimental code.
— · MIT
AI agent 通用任务治理框架:对齐目标与事实,规划和调度能力,守住授权与风险边界,治理任务执行到真实验收与交付。Governance framework for evidence-driven planning, orchestration, and verified delivery.
v2.33.0 · MIT
Claude Code-first opinionated workflow framework: instructions, skills, rules, and SDLC workflows that govern AI coding assistants.
— · MIT
Runtime guardrails for Claude Code. Auto-approve what's safe, gate what's risky, block what's dangerous. Dual enforcement, full audit trail. MIT.
v1.0.0 · no license
One capabilities.yaml wires skills, tools, rules, sub-agents, MCP servers, and plugins into Cursor, Claude Code, Codex, Windsurf, GitHub Copilot, and 30+ other AI coding agents
v1.0.0 · MIT-0
AI-DLC (AI-Driven Development Life Cycle) claude code plugin
— · MIT
MCP servers for the UniFi suite of applications, Network, Protect, Access, and Drive
v0.41.0 · no license
Open-source alternative to Claude Cowork — a local-first AI agent desktop app · multi-model · self-evolving skills · privacy-first · multi-Harness roadmap · DeepSeek Harness integration in progress
— · no license
🚀 Universal SDK for building next-gen MCP servers
— · MIT
One command to cut token usage by up to 50%+
v1.2.0 · no license
🌋 Build AI agents that seamlessly combine LLM reasoning with real-world actions via MCP tools — in just a few lines of TypeScript.
v5.0.0 · Apache-2.0
Process transparency for agentic work.