#agents

该仓库未发布描述。

Enterprise engineering workflow for Claude Code — not just prompts. AI agents that plan, build, audit, and ship with security gates, privacy checks, and approval-controlled commits. Safely adopt it into new or existing repositories.

A self-improving reflection / skill-creation agent on LangGraph — the LangStage reference agent

A local-first control layer for AI agents

Open protocol and reference node where humans, their AI agents, and local LLMs share apps, knowledge, and capabilities. Self-hosted, federated, MIT.

An agent framework for Go with graph-aware memory, UTCP-native tools, and multi-agent orchestration. Built for production.

Run agents you don't babysit, and trust the result. awf runs agentic workflows with independent gates that check every step and resumes after crashes.

一个基于多智能体协作的 AI 助手，支持命令行和Web界面，提供团队模式、自定义会议模式和多智能体讨论模式（圆桌会议模式）三种工作方式，通过多个专业智能体协同工作来完成复杂的编程和系统任务。

Production-grade Harness Engineering Framework for multi-developer AI coding agents — guardrails, state persistence, direction alignment, and self-correction across 6 IDEs. Zero dependencies.

The Collaboration Layer For AI Agents

Go SDK for driving coding-agent CLIs with one API

Native Post-Quantum Agent Messaging Protocol (N-PAMP): a binary, multi-channel wire protocol for authenticated agent-to-agent communication with hybrid post-quantum cryptography. IETF Internet-Draft.

Create conversational AI solutions with custom data and abilities using ChatBotKit for Go applications.

Lean Codex agent toolkit

Create multi-agent workflows with AI and Language Models using OTP components in Elixir for reliable and scalable automation.

Maintained unofficial Go SDK, CLI, MCP server, and OpenClaw skill for safe Things Cloud automation.

MCP server that suggests repository-specific AI agent skills.

Backlog.md - A tool for managing project collaboration between humans and AI Agents in a git ecosystem

Local memory + orchestration layer for custom LLM agents: SCOPE-style tactical/strategic memory over execution traces, Qdrant-backed, polyglot subprocess tools, agent-as-tool composition.

该仓库未发布描述。

Local-first, state-driven AI agent platform. Plan-review before execution, capability-gated tools, BYO LLM (Ollama / Anthropic / OpenAI). Tauri desktop + Go runtime.

Durable, NATS-only workflow engine for Go

MCP generator for OpenAPIs 🫳🎤💥

该仓库未发布描述。

A curated collection of AI-powered skills, agents, prompts, and workflows for Android, iOS, Flutter, React Native, Unity, and Unreal developers. Build faster, debug smarter, review code, optimize performance, automate tasks, and ship high-quality apps and games with reusable AI productivity tools.

Miru — hybrid code search for agents

🤖 Autonomous Multi-Agent AI Workspace in your terminal. Codes, researches, and executes real tasks with 40+ tools and 280+ skills And Some Captcha Resolver With Only Vision Mode Any Captcha And Opening A Browser And Full Control Of It

Lifecycle event observability feature for Kestrel Sovereign — hook-driven logging with shared Prometheus registry

TUI on top of gh skill: install, update, delete, and propose PRs for agent skills across multiple AI coding agents at once

Go CLI to cache OpenAPI & Swagger specs locally. Search REST API endpoints, inspect operations, and keep stable key@version refs—built for developers and AI coding agents.