GitHub agents

说人话 — AI痕迹消除与文本人性化改写,查重率从60%降到30%以内

Official MCP server for OrcaRouter — the LLM gateway with auto-routing and fallback chains. Browse models and chat from Claude Desktop, Cursor, Windsurf, or any MCP client.

Human-in-the-Loop Web Novel Agent 是一个基于大模型、多智能体协作和 RAG 的长篇网文半自动生成系统。项目目标是缓解 LLM 写长篇小说时常见的上下文遗忘、逻辑发散和角色崩坏问题，并允许用户在关键节点介入审核。

Comprehensive guides for AI coding assistants: Claude Code, GitHub Copilot, Gemini CLI. Includes MCP servers, multi-agent orchestration, and production templates.

Turn any GitHub repo into an agent skill. Make any open-source repo an agent's claw. 🐾

Curated reading list & living survey on long-term memory for LLM agents — 989 papers, 529 archived PDFs, deep notes mapped to memory-kernel modules. Feeds the Ymem Research Radar.

I built a cortex for Claude Code. It runs three of my businesses.

My AI engineering team for Claude Code — 64 named specialists I actually use every day. Atlas leads, Rune designs, Forge codes backend, Bastion guards security, Sage tells me to drink water. Deep agent prompts (anti-patterns + 2025 defaults + handoffs + checklists), per-role memory, ASCII activation cards. MIT.

Flow-driven recursive skill evolution for agentic LLM orchestration.

Local-first AI workspace for creators — browser-based, privacy-first, multi-agent collaboration

Multi-Agent AI Code Review System - Security, Performance, Logic & Style agents running in parallel via LangGraph + Gemini 1.5 Flash

J.A.R.V.I.S: An AI-powered Open Source Intelligence (OSINT) system. It orchestrates deep web scraping and local LLMs to autonomously generate comprehensive intelligence dossiers.

Local coding-agent orchestrator — DAG of auto-approved, git-worktree-isolated sub-sessions across LLM providers (Claude/Kimi/Grok/DeepSeek/local). AGPL-3.0.

Policy-as-code for MCP agents: deny risky tool calls before they run, prove what ran with verifiable evidence, and enforce egress in the kernel (eBPF/LSM, Linux). Deterministic, offline-first, bounded claims.

Local hardware intelligence for AI coding agents. Zero cloud. Zero telemetry.

Detect AI agents operating on your network through passive monitoring, active probing, protocol detection, and behavioral analysis.

Beginner-to-master roadmap for becoming a modern AI engineer: AI and ML fundamentals, deep learning, LLMs, RAG, agents, model infrastructure, optimization, hardware acceleration, AI security, blockchain, and ZKML.

Sep-CMA-ES: the separable CMA-ES optimizer behind TRINITY's evolved LLM-coordinator router (Sakana FUGU). NumPy, no LLM required.

AI-native, layered knowledge operations. A specification, reference skills, and a portable agent for any AI harness and any agentic IDE.

A context-first, spec-driven, strictly sequential development workflow plugin for Claude Code — keeps your CLAUDE.md/.claude spec always fresh and grounds every decision in Context7 + Microsoft Learn.

Active session monitor and infinite-loop breaker for Cursor AI Composer (Agent Mode). Optimizes extended thinking token drain for Claude Opus 4.8 and Fable 5 models during multi-file edits.

Curated AI Workflows, Skills & MCP servers for secure multi-agent development

面向中文开发者和中文用户的通用 AI agent 访问层：把网站、App、API 和重复流程路由到 agent-native CLI。

Give an LLM a URL and a goal — it drives a real browser, fills forms, and returns structured data. The browser that scripts itself.

Build faster with an open-source AI workspace designed for real developer workflows.

Desktop & phone notifications for AI coding agents (Claude Code, Codex, Gemini CLI, Cursor). Native VS Code support. Toast + ntfy push. Zero dependencies.

Portable AI agent configuration packaging and sharing tool

High-performance Model Context Protocol (MCP) server gateway for Claude Pro. Seamlessly bridges Claude Web UI with local environments, file systems, and secure execution layers.

🏛️ 解决方案架构师/售前顾问超级工作台 | C4模型·TOGAF·4+1视图·13类draw.io图表 | PPT工场·文档工场·RFP响应 | 方案设计·架构图·投标全链路 | WuKong/Claude Skill

Reflection/judge layer for OpenCode & Claude Code — catches premature stops, enforces workflow gates (tests, CI, PRs). 78% of agent stops are premature.

acrawl — LLM-powered web crawler. Describe what you want in plain English, get structured data back. Single Rust binary, 25 providers, MCP server built-in.

A tiny, headless, AI-native operating system: a minimal Linux + musl/BusyBox appliance that boots straight into an on-device LLM agent over a local HTTP API and serial console. Local-first inference with a Rust agent core, Go gateway, and per-service cgroup/seccomp/Landlock isolation.

🤖 Tired of repetitive technical support emails? Automatically transform GBs of Foxmail history into a searchable QA library (JSONL/CSV) using AI Agents. Built for speed, privacy, and multi-language support.

cursorAdvanced autonomous deployment agent for Cursor AI IDE. Adds intelligent multi-step terminal workflows, pre-commit CI/CD verification, and automated staging deployment managed directly by Cursor Composer.

ATRIUM is a local-first full-stack AI company workspace for Mac/windows. This repository includes the FastAPI backend, Vite frontend, Docker services, runtime configuration, and beginner-friendly one-prompt setup guides for installing Postgres/pgvector, Ollama, Letta, and the web app together from the start.

Your personal AI, everywhere you are.

A cockpit for your Claude Code stack — detects whichever of rtk, jcodemunch, graphify, Headroom & superpowers you've installed and wires them into one panel: plug-and-play detection, programmatic tool routing, enforced skill chains, and a single pane of savings.

Production-grade Cursor slash commands with paired skill contracts, behavioral evals, and ship-gate CI. Install as a user plugin.

lo2cin4bt 2.0 beta: local AI-assisted quantitative research and backtesting framework.

Build & host live AI agents with 5 lines of code.

Self-evolving AI orchestrator

A chef's palate for AI agent memory; Un-mix any day's work into its exact projects, and detect workstreams nobody has named yet. Hyperdimensional fingerprints, zero dependencies.

Executable engineering judgment for AI coding tools: blueprints, gates, checkpoints, policy, memory, and audit trails.

A clean, fast Hugo-powered blog covering AI engineering trends, tools, and insights at AIEngineerGuide.com

Open standard for portable AI knowledge interchange — JSON-LD + Markdown dual format with W3C PROV provenance, bi-temporal tracking, entity relationships, and OKF support.

agents.txt is a lightweight, machine-readable capability declaration layer for websites in the agentic web: a protocol-agnostic discovery file that publicly announces what agent-interaction capabilities a site supports, without embedding the implementation details of any specific protocol.

GEO-first SEO toolkit for Codex. Audit websites for AI search visibility across ChatGPT, Perplexity, Gemini, Google AI Overviews, and Bing Copilot with Codex skills, agents, crawler checks, citability scoring, schema analysis, llms.txt generation, and client-ready reports.

Structural code intelligence for AI agents. Scan once, query everything — dead exports, circular imports, dependency graphs, and more. CLI + MCP server.

Demo walkthrough and sample code for standardized multi-agent observability across clouds using Azure AI Foundry and OpenTelemetry GenAI semantic conventions. From Microsoft Build 2026.

A wallet for your agents to onboard and pay. Agentic MPP / x402 payments from your machine - CLI + MCP server.

Token-Reducing Shell — terminal output compression for AI coding agents

A Rust-native agentic memory substrate built on the selene-db graph engine: a bi-temporal knowledge graph, hybrid retrieval, and an optional MCP server.

Official TypeScript/Node.js SDKs for the InFlow payments platform - x402 and MPP (Machine Payments Protocol) integration for sellers and buyers.

The trust and intelligence layer between AI agents and your database. Read-only by architecture, semantic knowledge graph + audit log, MCP-native.

HERO - Harness for Engineering and Run-time Orchestration: a runtime control system around foundation models for autonomous software-engineering missions.

Universal MCP gateway for AI agents — 1108 tools, 307 providers. One endpoint (https://apibase.pro/mcp), pay-per-call with x402 USDC on Base + MPP USDC on Tempo.

Write AI rules once → sync to Claude, Cursor, Copilot, Gemini and 10 more tools automatically

Git-versioned, provenance-grounded knowledge layer extracted from a codebase, served to humans and AI agents via MCP

Lightweight Python SDK for LLM inference logging and observability

A .NET C# CLI Coding Agent powered by Ollama + Semantic Kernel and RazorConsole. Run locally or in the cloud. Refactors code, proposes diffs, and updates your project safely — no API keys required.

Keep Claude Fable 5 (or Opus) as your daily driver without draining your usage limit — token-frugal multi-agent orchestration plugin for Claude Code: model-tier routing, Requirements Ledger, enforced guard hooks

A discipline harness for AI-assisted analytics: agent skills for every moment a number gets built, broken, or trusted — requirements, definitions, audits, triage, migrations, dashboards, briefs — every claim carrying its provenance in one living knowledge base.

Drop-in OpenClaw/NemoClaw agent configuration for the ibl.ai K-12 segment — School Assistant orchestrator plus 12 specialist subagents.

Public source-backed Arab-world agent skills: APIs, marketing, sales, support, localization, Arabic NLP, open data, and MENA workflows.

Cognitive memory engine for AI agents. Biologically-inspired 4-tier cortex, Panama SIMD, MCP native. Java 25.

MCP server + CLI for Meta Ads — run Facebook ad campaigns from your terminal or AI agent

Cross-agent skill router that organizes large local skill libraries into category routers and loads leaf skills on demand.

Manage knowledge as apps | CLI | MCP | AI Knowledge Framework for AI Agents & Humans

9 quality-canary skills for AI coding agents - code health, gold-standard rules, anti-hallucination grounding, supply chain, resilience, observability, testability, scaling, contract drift. Consent-gated, token-lean, one-button install, works across all major AI coding agents.

Runs AI coding agents inside isolated Docker containers

End-to-end encrypted inbox for AI agents — deliver artifacts to humans via HTTP API.

Arc Gate — LLM proxy with prompt injection detection. Bendex Geometry.

Smart AI proxy router that connects Claude Code, Cursor, Codex, Copilot, and 50+ coding tools to 40+ AI providers with 100+ models. Saves 20-40% tokens via RTK compression, auto-fallback from subscription to cheap to free providers, multi-account round-robin, and a local dashboard.

the universal realtime, efficient agentic operating system to power future devices like smart glasses

A curated collection of Agent Skills by Montimage. Supercharge your AI agents with specialized workflows for development tasks. Works with Claude Code, Codex, OpenClaw, and other AI tools.

Agent skill (npx skills) for evidence-based SAP API Policy alignment assessments — sourced, confidence-rated, never legal advice.

🦞 A curated list of projects, tools, agents, and resources in the MoltBook ecosystem

Runtime for coding agents. Models are getting smarter, but a model is only as capable as the environment supporting it. Atelier is that environment.

Simple AI agent library in go (general usage but focused on infra/platform tooling automation)

A memory graph designed for the agent that uses it, not the human who feeds it. Engrama reconstructs context from associations on demand, replacing the "stuff everything into the prompt" reflex with targeted graph traversal. SQLite default, Neo4j optional.

Open-source local-first dispatcher for AI coding agents. Verification-gated, BYOK, rolls back on test failures.

📜🦀🌐 Full-Stack Web Framework for Rust 🌐🦀📜"Rust for those who want to build, not suffer."🤖 The Next-Gen Paradigm: Designed for Humans & AI. Rullst is built from the ground up to be a developer-first framework, optimized for seamless AI-assisted coding and effortless human productivity.

Codex Switch manages AI providers, agents, chat, drawing, sessions, MCP, Skills, vision fallback, and web search on Windows.

The governance layer for LLM-maintained Markdown wikis.

Local-first Rust CLI that tailors your resume to a job posting through an adversarial agent loop, and never invents experience you don't have.

Agentic OS for B2B SaaS startups — run your startup like code

A lightweight Grok plugin for Claude Code — delegate coding and review tasks to the Grok CLI. A simple reimplementation of OpenAI's codex-plugin-cc.

The clean slate a fresh Claude Code should start from — clean context, locked credentials, guarded egress. Isolated profile, pick-and-choose.

Code review for jj (jujutsu) workflows: revset-defined reviews, patchset-anchored comments that survive branch movement, with web, HTTP, and MCP surfaces for fast AI-agent iteration.

MCP server that connects AI agents (Claude Desktop, Cursor, Windsurf) directly to your MySQL, PostgreSQL, or SQLite database read-only by default, zero install via npx.

Long-term memory layer for AI agents

Open-source loop engineering for auditable business briefings: claims, evidence, gates, findings, repairs, and human review.

AI 驱动的 A 股智能投研终端: 17 角色 AI 团队七维并行诊股 + 多空辩论 + 风控会签, 输出可执行评级/仓位/买卖点; 独创回溯诊断用 +5/10/20/60 日真实走势验证 AI 准不准; 44 因子策略 + 真实约束回测 + 7x24 实时快讯; 100% 本地运行, 数据自持, 开源免费

Evolve AI agent skills through iterative meta-skill-driven optimization. Inspired by SkillEvolver and EmbodiSkill.

The chef's standard for AI agent work: twelve rules, a critique gate, and project memory. One skill. Craftsman's taste. Zero AI slop.

Isomorphic agent tooling: author once, run anywhere. Build, lint, route, fan out, eval, trace, guard, contract, and ledger AI-agent workflows across Cursor, Claude Code, Codex, and OpenCode.

Keep AI coding-agent instructions consistent across Cursor, Claude, Copilot, Codex, and AGENTS.md. One canonical source, generated provider views, drift checks.

Agent Skill for cross-border product launch readiness: admission checks, target-market benchmarks, localization, documents, labels, pricing, logistics, and remediation.

AI changelog generator that turns commits into polished release notes.