GitHub agents

A macOS-native terminal workspace designed for AI-driven development

Chemigram is to photos what Claude Code is to code. Agent-driven photo editing on darktable, via MCP.

Institutional memory for the agentic era. Open-source GraphRAG knowledge base: documents in, Neo4j knowledge graph out. Humans get chat + deep research with cited answers, agents get a 100+ endpoint REST API, plug-in apps run right inside the instance. Self-host with one command: npx @mocaos/cortex

面向 AI Agent 的非车险产品开发全流程知识库 - 覆盖保险标的识别、条款编制、费率定价到文档输出的 7 步开发流程

Docker MCP server designed for agents that need their containers to stay running. Health checks, auto-restart, Compose lifecycle, log streaming.

Local-first OpenClaw agent runtime with REST/WebSocket APIs, operator controls, 58 tests, and secure reproducible installs.

🦐 AI-powered launch intelligence terminal on Robinhood Chain — scan, score & explain new token launches

Portable Agent Skill for converting PDF to editable Word/DOCX while preserving layout. Works with Codex, Claude Code, other AI agents, and local CLI.

Experimental local-first Android AI agent built with Kotlin and Jetpack Compose, featuring on-device Gemma models, policy-controlled tool calling, and safe Android automation.

A cognitive protocol for AI agents. Makes any LLM-based agent think like an experienced practitioner. Works with Claude Code, Codex, Gemini, and any agent framework.

Codex skill for Amazon market screening, product selection, launch planning, profit repair, and stop-loss decisions.

中文网文 AI 创作工作流 | Claude Code & OpenClaw skill for outlines, characters, serialized chapters, and continuity checks.

🔄❌⬇️ AI 写作的反套路引擎。核-心写作法(3种核型)+7把刀+7条硬性质检+金手指手法体系，让AI写的小说没有AI味。47章实战验证。Claude Code | Cursor | Windsurf 通用。

Let Claude use the Chrome you're already logged into — real sessions, real cookies, no second browser. MCP server (CLI) + MV3 extension.

Companion OpenClaw skill for the Godot plugin — teaches AI agents the tool surface and editor workflows so they can drive Godot remotely.

experimental agentic coder for ollama, llama.cpp, and vLLM ... inference you OWN

Codebase for Prompt Segmentation and Annotation Optimisation: Controlling LLM Behaviour via Optimised Segment-Level Annotations

The AI that lives in your system core — always on, always connected. Self-hosted agent for mail, calendar, meetings, and WhatsApp.

SupSub 的命令行工具 —— 在终端里管理订阅源、关注点、分组与全站搜索，内置 Claude Code skills

Local-first personal AI daemon in Rust — five-tier memory, consent-gated tools, WASM plugin sandbox, multi-provider LLM routing, channels, GUI, signed audit logs, and Babel-Index collapse prediction on its own runtime.

an AI agent platform 🤖

轻量级跨平台 LLM 客户端 + AI Agent 开发环境 | Lightweight cross-platform LLM client & agent workspace (Tauri 2 + Vue 3 + Rust)

Self-hosted wellness OS for training, nutrition and longevity. Connects your labs, lifting, running, food and sleep into one agentic brain that suggests the one thing worth doing today. PWA + REST + MCP server. No scores, no nudges.

女装电商运营驾驶舱 — 40 个 self-contained sub-skill，飞书 CLI 数字化全链路方案

AI-powered proposal automation agent. Seamlessly integrates job scraping, requirement analysis, and personalized proposal drafting into a high-speed workflow.

Knowledge graph builder for legal docs. Extracts clauses, detects conflicts, traces compliance. Agent skill.

Lightweight headless browser for AI agents

Semantic router for Claude Code Agent Skills — finds and installs the right skills for your project from a 65k catalog.

Durable, repository-owned project knowledge and lightweight delivery for AI coding agents.

A local-first harness that turns an AI coding assistant into a disciplined colleague — rules in one file, cheap agents for bookkeeping, bash guards, git undo.

Flight recorder and firewall for AI agents — records every tool call, tracks lethal-trifecta taint across a session, and blocks the prompt-injection exfiltration path. Zero deps, cross-harness.

Kuzu-backed schema graph from live DB introspection. MCP server for AI tools.

Unlimited coding with Claude Code on ANY LLM. A Blazing-Fast Rust proxy featuring auto-routing and load balancing, API key pooling, and RTK optimization.

Autonomous software delivery on your own Claude/Codex subscriptions — durable runs, human gates, sandboxed agents. Druks is the self-hosted home for durable agent apps.

Fast, deterministic CLI to search and navigate Open Knowledge Format (OKF), or Obsidian style doc bundles — for humans and AI agents. Find by frontmatter, traverse the link graph, surface orphans/deadlinks.

Run AI coding agents (Claude Code, opencode, Grok, ...) inside a bubblewrap sandbox — one wrapper, any agent.

AgentSeed — the governance layer for AI agents. Non-negotiable kernel + pluggable scenario packs, synced to 15 AI agent tools.

Reusable AI agent skills for architecture documentation, ADRs and diagramming

A Claude Code command that refuses to call anything shipped until a separate fresh-context verifier proves it in the real world.

AI-native software delivery governance framework

A serverless networking protocol designed for resilient state synchronization between autonomous agents in fragmented, low-bandwidth networks

Native macOS app that runs headless Claude Code tasks on a launchd schedule hooks, token tracking, and an agent-friendly CLI

Agent Skills for the Patter SDK — give your AI agent a phone number. Works in Claude Code, Cursor, OpenClaw, Hermes Agent, Codex, Cline, Goose, Amp, Windsurf, and any harness that consumes the Agent Skills standard. One CLI: npx skills add patterai/skills

Local-first Claude Code and Codex session log viewer with search, replay, and usage analytics.

Verified, portable AI software-delivery harness with policy gates, read-only data probes, signed evidence, and human review.

Every Wade does the dirty work so the heroes don't have to. Branches, worktrees, context, PRs — handled.

One stable CLI and daemon for SSH, local PTY sessions, file transfer, and remote editing — built for AI agents and humans alike.

🧩 Turn Python AnyWidgets into interactive, composable MCP Apps

AI agent skills for the flespi IoT and telematics cloud platform. Provides comprehensive reference for the flespi REST API, MQTT broker, device management, and analytics.

The open protocol for AI agent identity. DNS-anchored. Post-quantum native. Governed by TrustLayer Foundation A.C.

Firefox automation CLI and Pi package for AI agents

🏆 1st Place, Ralphthon @ ICML 2026 — Evidence-bound multi-agent reviewer for scientific papers.

Unofficial, agent-friendly Amazon Fresh CLI in Go

🚀 Enable Chrome's Gemini AI features for non-US users with a simple one-click script for macOS, Linux, and Windows.

An MCP server that exposes the full Bambuddy REST API as tools for AI assistants.

Drop-in browser skills for AI agents: headless screenshot (Browserless) + interactive control (KASM Chrome via CDP). Generic, scrubbed, MIT-licensed.

The open-source, self-hosted social media manager. One idea in → a premium faceless video, end to end — researched, scripted, QA-gated, rendered, and published. Runs on your own devices.

Hands-on, project-based workshop to learn how to build a software factory-a system of AI agents that can plan, architect, code, review, and deploy software continuously.

Agent-native action layer for Laravel with shared human and agent surfaces, approvals, and audit logging.

Small Rust CLI that turns your local browser into a structured search API for Claude Code, Codex, Cursor, OpenClaw, and shell agents—no hosted API key or metered search bill.

Run parallel, resumable, human-operable Antigravity CLI sessions from any MCP agent harness

Production AI social-strategy platform with agent orchestration, MCP/OAuth integrations, durable event history, replay, and postgame analysis.

macOS dotfiles with a shared AI OS: one canonical config that Claude Code, Gemini CLI, OpenCode, Codex, and OpenAI agents all read, kept honest by a health check.

Control your Android phone from Claude via MCP, running on Termux

Give your AI agent its own Solana wallet — it trades for you, and nothing traces back to it. MCP server + Telegram bot, open source.

🛠 Manage Claude Code sessions with a TUI featuring real-time monitoring, conversation history, and automatic session detection.

Local-first multi-agent orchestration: run tasks across CLI agents and API models, pass work between agents when one dies. Sessions, workflows, human-in-the-loop.

A shared knowledge vault + full software-engineering workflow for AI coding agents — run Claude Code and Codex in parallel with one memory, one plan.

Demo showing how to turn a web app into a Microsoft Teams agent using the Teams Developer CLI, coding agents, and Teams agent skills — from server inspection to onboarding link. From Microsoft Build 2026.

Discover, verify, and manage Agent Skills across desktop, CLI, and Hub workflows.

Synthetic users that walk your software before real users do.

A comprehensive AI-powered financial advisor application that helps users create detailed financial profiles, analyze their financial health, and receive personalized financial recommendations.

Computer use for Hyprland - MCP server giving AI agents native hands on your Wayland desktop. No ydotool, no root, no portals.

A Claude Code plugin that turns ambiguous work into shipped, tested, serialized artifacts through evidence-gated loops. Not a prompt library — a stateful consequence engine. Plus a bounded /ratchet-evolve mutation loop. Mutate. Test. Keep the delta.

Rust SDK for Codex app-server runtimes with in-process and remote WebSocket/Unix-socket backends.

Scan any codebase for O(n²) hotspots, N+1 queries, and complexity issues — works with 13+ AI coding agents

Structural code intelligence for humans and AI agents

结构化中文网络渗透知识库：技术卡、专题、案例与多 Agent 协作维护

A local proxy that wraps your MCP servers and checks each tool call against policy and live state before it runs - allow, block, or request a refresh, with a reason the agent can act on.

🔍 Discover + safety-vet Claude Code extensions before you install them - a 0-100 trust score for discovery + a 1-5 static-scan risk verdict, SHA-pinned install. Skills/MCP/plugins/commands.

The Anti-Cramped Spacing Skill for AI Agents — one spacing scale, vertical rhythm, optical alignment, and density discipline. SKILL.md + Claude Code plugin.

Sandbox to run AI coding agents (Claude Code, Codex, Gemini, Grok) with full TLS inspection, domain allowlist enforcement, and Falco syscall monitoring

ZBrush adapter for the DCC Model Context Protocol (MCP) ecosystem

Build and run ArchAgents solutions from your coding agent, with deployable examples and developer tooling.

The delegation network for AI agents — discover agents, delegate work, get cryptographically verifiable receipts. Any agent (Cursor, Claude Code, Codex, …) joins in minutes.

Run an autonomous AI coding agent — opencode, claw-code, or Claude Code — under controls it cannot disable. Fedora bootc + rootless Podman appliance with audited egress proxy, kernel-enforced nftables isolation, root-owned prompt-injection-hardened instructions, and service-gator-mediated external access.

Convert any FastAPI app into a CLI + SKILL.md for AI agents

The backlog your AI coding agent reads, picks up, and closes itself. Docs: https://runloq.github.io/runloq/

小龙虾是我很久之前看中的项目，没想到这么火了， 我也来整一个，持续更新

Set it and forget it! A clean, node-free GUI that automates full AI music videos. Queue your prompts and let the tool generate and stitch LTX 2.3 clips, then automatically score the final cut with an ACE Step 1.5 audio track. No waiting around for each clip to render.

Local web UI for managing Claude Code sessions, jobs, agents, profiles, tools, costs, search and configuration.

Verified compute evidence and fail-closed validation for Cathedral SN39.

Persistent, structured memory for AI agents — a human-readable Markdown wiki, multi-user with per-fragment ACL, self-organizing overnight. Agent-agnostic via MCP. Self-hosted, AGPL.

Android-friendly Playwright SKILL for AI agents — Termux launcher patch, headless Chromium, install via git subtree into .codex/skills.

Anything AI.体验AI，学习AI，感受AI，教程AI，驾驭AI。做AI的主人，而不是奴隶。下载PDF学习资料

Autonomous overnight agent loop for Claude Code with research toolkit. Episodic execution, paper monitoring (arXiv + Semantic Scholar), knowledge synthesis, and structured handoffs.

The Most Useless EVER agent assistant in the Human History. Always trying to read everything in your computer and commemt.

A self-updating ops console for your whole MotherDuck account — the data-flow graph of every dive, flight, table, and share, built from the manifest comments in your own objects. Load INSTALL.md into your AI assistant to install it.

Local code intelligence graph for AI coding agents: Tree-sitter static analysis, structural code search, dependency impact, blast-radius analysis, CLI and MCP server.