GitHub agents

Local AI coding agent for your terminal. Open-source, offline alternative to Claude Code, Cursor & Copilot — powered by Ollama and any local LLM. Private by default, free forever.

InkFlow（墨流） 是一个基于 LLM 的工业化长篇小说创作引擎。采用“流程标准化 + 技能插拔化”架构，8 个专职 Agent 通过 Plan → Compose → Write → Edit → Observe → Reflect → Librarian 的标准化管线协作，7 个真相文件构成唯一事实来源，支持百万字级上下文管理、支线追踪、情绪弧线可视化、去 AI 味检测，以及基于蒸馏的风格迁移。

SAM Sovereign Agent Mesh

Docker image for a self-hosted WhisperLive real-time speech-to-text server, powered by faster-whisper. Provides WebSocket streaming for live audio transcription and an OpenAI-compatible REST API. Supports all Whisper models, VAD, NVIDIA GPU (CUDA) acceleration, offline mode, and multi-arch (amd64, arm64).

WormGPT CLI V2.0 is here but is still in the development stage from the previous version which I did not optimize for its function, please be patient and calm!.

free and open source terminal agent harness 🤖

Run Hermes Agent + Claude Code locally on llama.cpp — zero API costs. A 4h / 7M-token session that would have cost $94 on Claude Opus 4.7

Automate a WeChat group's daily work-report roll-call — start, chase non-submitters, and LLM-summarize for the manager. wxauto + FastAPI + hot-reloadable rules.

🚦 Stop AI agents from deleting data, leaking secrets, or taking irreversible actions without approval. One ⭐ takes us a long way :))

rUvOS — the agentic operating system. A single static Rust binary that runs as an MCP server, giving Claude Code persistent memory, resumable signed sessions, multi-agent orchestration, a knowledge graph, safety guardrails, and a signed audit trail. Zero Node.js, zero SQLite, zero daemon.

Private, self-hosted document chat for attorneys: parse legal PDFs and query them with local open-source LLMs (Ollama) + verifiable page citations. One-click desktop app at docuchat.app.

A local-first macOS debugger for LLM context windows, token usage, tool calls, and agent execution.

AI Agents with Google's Gemini Pro and Gemini Pro Vision Models

AI Agent Skills for content planning, multi-agent discussions, and role library expansion — compatible with Codex, Claude Code, and Cursor.

Production-ready TypeScript SDK for MCP servers: auth, multi-tenant, observability. Build enterprise AI agents fast.

Claude Code skill that applies Naur's Programming as Theory Building to coding-agent workflows.

Claude Code Architecture Deep Analysis — 14-chapter report, 7 languages | Claude Code 架构全景分析 — 14章报告，7种语言

[ICLR 2026 Oral] SimuHome: A Temporal- and Environment-Aware Benchmark for Smart Home LLM Agents

MEMO: Memory-Augmented Model Context Optimization for Robust Multi-Turn Multi-Agent LLM Games

Ripple is a Codex-powered agent workspace for sessions, files, connectors, automations, and multi-platform clients.

Agent Skill for creating UESTC course report templates for Claude Code and Codex

FAIR cyber risk quantification toolkits, agent-based control simulation (FAIR-CAM), threat event frequency estimator (PyPI), LLM classification validator (PyPI), Monte Carlo risk engine with IRIS benchmarks.

面向个人投资者金融投资研究与辅助决策agent系统

Building Agents with OpenAI SDK, Published by Packt

WebLLM Gateway：让 Qwen/DeepSeek 网页模型接入 OpenAI/Anthropic 兼容 Agent 工具链，支持 OpenClaw、Hermes、Claude Code、Codex 工具调用

AEO tracking toolkit (CLI + dashboard) built for AI agents like Claude Code, Cowork, Codex, OpenClaw, Gooseworks

AI Operating System cho Cong ty 1 Nguoi Viet Nam — solo founder + 12 phong ban AI agents hop ban debate, ra quyet dinh, sinh tai lieu chuan luat VN. Chay qua Claude Desktop subscription.

A rich web UI layer for AI agent interactions — human-in-the-loop, click-to-edit, preference learning. Built for Claude Code, CodeX and OpenClaw.

• 基于 FastAPI + LangGraph 的医院导诊 Agentic 助手：整合 Redis/Elasticsearch/Milvus 做症状与流程的 RAG 对话，支持多轮意图识别、检索重写、答案生成，以及 rich 驱动的多会话 CLI 体验，便于参考构建生产级医疗导诊/问诊系统。

Publish MATLAB functions as MCP tools for AI agents using MATLAB Production Server

Godot AI agent CLI, Skill, and MCP server with structured JSON/schema output — headless scene/script/export automation plus live runtime control.

CoLLMLight: Cooperative Large Language Model Agents for Network-Wide Traffic Signal Control

OpenCode plugins that help AI agents understand their identity across multi-agent sessions

Guardian Agent and Token Savings for Claude Code

AI coding agents comparison - 80+ agents, SWE-Bench leaderboard, pricing. Devin, Cursor, Claude Code, Copilot, and more. December 2025.

A comprehensive Claude Code skill for building and deploying static websites with the Astro framework. Covers SSG, Content Collections, Markdown/MDX, Mermaid diagrams, Pagefind search, i18n, and deployment to Firebase/Netlify/Vercel.

This is a generic knowledge agent for creating a RAG pipeline from source docs, etc.

End-to-end RL trading framework with PPO agent, self-attention neural network, custom Gym environment, and advanced backtesting.

LoopCraft runtime harness plugin for Hermes with evidence-first execution, verification-first workflows, and self-correcting AI agent behavior. Installs as proofrail for compatibility.

High-quality Agent Skills made to perform reliably in real workflows

Federated, local-first search for an AI — one query across transcripts, files, knowledge graph, vector store, and the web, fused by trust-weighted RRF. Apache-2.0.

AI toolbox for grounding LLMs on Langium DSLs with evaluation, constraints, and agent skills

在飞书中远程操控 Agent（包括 Codex、Claude Code、Pi），同时让 AI Agent 拥有飞书全平台操作能力。

Agent Skills for Robot Framework

Local, private cross-platform voice dictation app speak anywhere, type everywhere. System-wide push-to-talk that converts speech to keystrokes in any application.

CSP for AI coding agents

Open-source guardrails between AI agents and FHIR clinical data — PHI redaction, immutable audit, step-up auth, tenant isolation. MCP server + OpenAI/Gemini adapters. A healthclaw.io project.

Windows Computer Use for AI Agents. Both a tool (22 MCP tools for click, type, screenshot, OCR, UI inspection) and an agent (autonomous mission engine, macro recorder, intent-based discovery, event watchers). Built with opencode (DeepSeek V4). Ships as MCP server, web UI, and Tauri desktop app.

Production-grade Kubernetes operator for nousresearch/hermes-agent: declarative spec, security defaults, S3 backups, OCI auto-update with rollback, SSA-based GitOps coexistence, OpenClaw migration.

Use Hermes Agent as the control plane for local coding agents like Codex, Kimi Code, Claude Code, OpenCode, and Gemini CLI.

Self-hosted LLM gateway — route OpenAI/Anthropic/Gemini traffic by config, not code. Fallback, protocol translation, telemetry.

Reina 桌面 AI Agent 发行仓库（仅安装包） | Release distribution for the Reina desktop AI agent — installers only. Windows x64 & macOS arm64, in-app auto-update.

Local-first memory layer for CLI agents. Indexes Claude Code, Codex CLI, and Cursor session histories into SQLite + FTS5 — searchable from a CLI, TUI, or MCP server so your next agent session can recall the last one.

A skill library that teaches Claude Opus the working disciplines of Claude Fable 5. Move the checkpoints, not the capacity.

50+ curated LLM observability tools PLUS 26 Agent Skills (several with runnable, unit-tested scripts) to build, evaluate, debug, secure & monitor reliable LLM apps. Tracing, evals, guardrails, LLMOps.

申根签证 AI Agent 技能 — 按身份定制清单、跨会话记忆，带你跑完办签全流程

Auto-updated leaderboard of trending claude-skills and AI agent repos, refreshed every 15 minutes

Chinese e-commerce MCP servers — let AI agents read merchant business data (Ocean Engine, Douyin Shop, JD.com, Taobao, Pinduoduo). 电商经营数据 MCP 连接器。

AI agent fleet orchestration terminal — bidirectional socket IPC, resource governance, mission-control dashboard. macOS · Windows. Built largely by AI agents under human direction.

Evidence-first website copy-remix skill for agent workflows

Browse every recent Claude Code session across all your projects and jump back into any of them. Shows project path, summary, git branch, model, turn count, and a ready-to-paste resume command. --open re-opens a whole working set in terminal tabs. Local files only: no network, no telemetry.

HAR Skills — AI-native library for HAR file analysis. Access via: Skills (CLAUDE.md), Go SDK, CLI, MCP. 23 commands, 70+ methods, progressive disclosure docs.

Wallet-as-a-Service for all AI agents in the world

Conflux v2026 is a Rust-based AI development orchestrator for spec-first agent workflows, coordinating autonomous development through parallel Git worktrees with interactive TUI and headless operation.

A coding agent modeled after Claude Code, supporting code generation, refactoring and PR analysis.

这是一个使用 DeepSeek Function Calling 构建的受约束数据分析 Agent。

PoC for GhostCommit Attack: Steal secrets via a pull request pointing to an image

SDLC Copilot is an Agentic AI system designed to streamline and automate the Software Development Lifecycle (SDLC). From requirement gathering to deployment and maintenance, SDLC Copilot leverages AI to optimize development workflows, reduce manual effort, and ensure software quality.

Redeem your Codex banked rate-limit reset from the command line — no UI required.

Public, source-cited Fable 5, Mythos, Claude Code, and agent-operations second brain. Not affiliated with Anthropic.

CoffeeBench: Benchmarking Long-Horizon LLM Agents in Heterogeneous Multi-Agent Economies

基于 LangChain/LangGraph + LlamaIndex 构建的工程级多 Agent 协作系统，支持上传简历与岗位 JD 后全自动完成面试准备、模拟面试、实时评估与复习规划；系统涵盖多 Agent DAG 编排、RAG 多路召回、MCP 协 议集成、双引擎记忆系统与动态难度调节，以 Python Web 服务部署于 Linux 服务器，支持摄像头、语音输入与文字 多模态交互。

Multi-pane ChatGPT workspace Chrome extension with side-by-side chats, lazy panes, prompt queue, goal agent, and Telegram bridge.

Convention-based persistent AI agents for Claude Code — autonomy model, session memory, intent-based communication

Your personal AI agent platform — self-hosted, BYO Claude/Codex subscription

Track your AI coding-agent token burn across Claude Code, Codex, OpenCode, Antigravity, and more.

OpenTelemetry integration for AI Agents Cursor / Copilot / Gemini / Claude / Codex that records agent activity and exports detailed telemetry with OTLP protocol

🧠 A council of AI models for the decisions that aren't no-brainers — they answer in parallel, debate to consensus, or get judged to a verdict. Browser-only, open source, bring your own keys (BYOK), no backend.

Memory database for AI agents — stores typed memories (facts, preferences, events, entities, relations) with provenance, confidence, and bi-temporal validity, and answers with fused semantic + lexical + entity-graph + temporal retrieval. One Rust core, one binary wire protocol. Apache-2.0.

Excalidraw MCP server with real vendor-icon search & insertion (AWS/Azure/GCP/OCI/Kubernetes) for AI-built architecture diagrams — live canvas, 31 tools

CADSmith (formerly AutoFab) is a multi-agent system that generates manufacturing-ready CAD models from natural language by combining LLM code generation with programmatic geometric validation from the OpenCASCADE kernel and visual inspection from an independent vision-language model, iteratively refining until the part is dimensionally correct.

Context engineering manages an agentic system's context: persisting and efficiently retrieving conversations and trajectories for the purpose of optimizing LLM context, this may include compacting and summarizing context to reduce costs and latency while preserving accuracy.

小理智法 AI 是一款基于大语言模型（LLM）的智能法律咨询平台，集成了法律咨询、合同审查、文书生成、合同起草、合同对比、智能校对、法律文书解读等多项 AI 法律服务。系统采用 LangChain Agent 架构，结合得理法律数据库 API 实现案例检索与法规检索，为用户提供专业、准确、有据可查的法律分析与建议。

本仓库记录了一套以 Obsidian 为知识库核心、以 Claude/Codex/Gemini 等 AI Agent 为分析引擎的研究工作流，适合需要大量阅读文献/资料、整理学习笔记、复现模型/实证的学生党、研究者、工作人员等。

Teaching/learning resources for O'Reilly Live 'How to Create AI Agents Like a Pro': Microsoft Copilot Studio builds for customer service, onboarding, and document automation.

Literature-fetching & citation-auditing skill for LLM agents (Claude/Codex) — 讓 AI 引用經得起追問:找文獻、查核引用真偽與支持度、文獻支撐寫作,防幻覺引用。

This repo contains the classroom material for Claude Code (Agent SDK) course.

Agent-agnostic record & replay skill: watch a user demonstrate a workflow (browser via Playwright, desktop via OpenAdapt) and turn it into a reusable AI-agent skill. Works with Claude Code, Codex CLI, opencode.

AI news tracking skill for Agents like Claude Code, Openclaw, and more. Tracks AI entities across 9 sources and generates daily structured reports.

Agent skill that helps Claude Code, Codex, Gemini, and Cursor write correct Swift App Intents code for Siri, Shortcuts, Spotlight, widgets, Control Center, and Apple Intelligence.

AI驯剪 — AI 自动剪辑视频：转写/剪气口/语义动效自动初剪 + 可视化 AI 视频编辑器人工定剪，开源闭环 | AI rough-cut + human final-cut video editing system

Método jurídico aberto e executável por agentes de IA: base curada de STF/STJ, legislação, súmulas, temas e teses; 10 protocolos e motores locais. Fontes verificáveis, casos privados. Claude Code · Codex · MIT.

🛡️ A curated list of tools, frameworks, standards, and resources for AI agent governance, safety, and compliance

Dynamic emotion system framework for Hermes Agent - real-time emotion detection,Long-term memory, context management, and recall systems, state management, and persona expression

Native macOS menu-bar companion for switching ChatGPT accounts, tracking Codex usage, reset credits, and verified automatic failover.

A safe local browser wizard for installing an OpenAI OAuth sidecar beside self-hosted n8n.