GitHub agents

Reasoning agent that triages inherited Power Automate estates: maps dependencies, finds the landmines, and outputs an evidence-grounded remediation plan. Built on Microsoft Foundry + Foundry IQ.

Codebase for Project ECHO: Video Transcription and Annotation Pipeline

中西命理 AI Agent · 7 路代理合议 + Planner-Executor 运行时决策 + 主动追问 + 跨系统涌现联结 + 反思镜可验证推理。八字 / 紫微 / 易经 / 风水 / 占星 / 塔罗 / 数字命理 一卷合参。

面向长期陪伴与自我理解的隐私优先 AI 记忆平台，融合 RAG、人生图谱、多模型路由与 MCP 能力网关。

让 Codex 秒级、低 token、安全地读写 macOS 微信 | Fast, token-efficient WeChat bridge for Codex

Local-first autonomous agent: Hermes speed plus Rust determinism, gated actions, checkpoints, evidence receipts, MCP, skills, and multi-model freedom.

A Claude skill that runs a proven X (Twitter) growth playbook — rewrites your bio, finds trends to ride, surfaces who to reply to, and drafts native-style posts by reading your own logged-in X. Based on a real +1,000 followers in 2 weeks.

Lark/Feishu bot framework powered by Claude Code — real-time chat, cron task scheduling, auto-diagnosis, and built-in safety filters.

Memory-native coding Agent with episodic memory, and both semantic/verbatim recall. Shipped as an Opencode fork and comes with Hermes-native memory integration.

Cross-language football transfer rumor verification skill for Claude Code and Codex — truthfulness × timeliness, checked separately.

A Python + Tkinter desktop travel guide powered by GPT-4o-mini that explores landmarks, restaurants, and local events for any city worldwide, with an interactive map and auto-fetched Wikipedia images.

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

Offline single-file screensaver/PWA that simulates an AI coding agent at work — fake terminal, fake dashboards, zero real code, all theater, zero dependencies.

Build and backtest Upbit trading strategies by chatting with an AI agent (Claude Code, Codex, Cursor). Backtest-only, beta.

MCP Server for WordPress with Undo. Connect ChatGPT, Claude Desktop, and other MCP clients via OAuth 2.1 and safely roll back AI changes.

The Middle East's first open source agentic harness. Designed for governed self-evolution.

An AI ETL tool you drive with natural language.

说出想法，Aura 用本地语音识别、可配置 LLM、任务模式和 Skill 匹配，将它整理成可直接交给 AI Agent 执行的清晰任务。

将Codex、Claudecode、Hermes、Workbuddy、Feishu...CLI Agent 综合发挥的平台

MAX messenger (max.ru) channel plugin for OpenClaw

Grok Build, beyond the terminal — native macOS workspace with full agent visibility, shared CLI sessions, and quota-aware multi-account routing.

Open-source coding agent that produces tamper-evident, CI-verifiable proof for every code change

Do Context Files Help Coding Agents? Two-agent (Claude Code + Codex) ablation on whether AGENTS.md/CLAUDE.md change coding-agent correctness & efficiency.

Organize Simple API — turns a receipt, invoice or card statement PDF into structured JSON. NestJS, Prisma, LangChain, Poppler.

A terminal cockpit for AI agents. Observe, evaluate, intervene.

AI-powered ERP agent for Odoo. Features a 21-node LangGraph backend with safe CRUD confirmation gates, SSE streaming. Includes real-time analytics with auto-generated Excel/PDF exports and proactive monitoring. Next.js 16 + FastAPI + PostgreSQL

Core hub for LLM orchestration, AI agent development, and prompt engineering frameworks. Implementing advanced workflows, RAG systems, and autonomous agent logic for intelligent automation.

Generic Codex orchestration with deterministic TaskGraphs, bounded parallelism, model routing, and targeted review remediation.

Multi Agent Cognition Protocol -- real-time cognitive collaboration between AI agents

Multi-agent orchestration for Claude Code: MCP server + skill that keeps Claude as lead engineer while delegating backend work to OpenAI Codex and frontend/design work to Kimi

Disciplined software engineering for coding agents: plan → review → build loops that actually terminate, with bounded rounds, fresh-reviewer exit gates, and TDD. Plugin for Claude Code and Codex.

Evidence-traceable, point-in-time multi-agent research for China A shares

Spec-driven multi-agent teamwork for any skills-capable agent (Claude Code, Codex, and more) — plan, dispatch, monitor, QA. No framework lock-in.

Graph-native multi-agent orchestration for OpenCode. One agent owns the goal; workers extend its reach through supervised, adaptive workflows.

Native Windows terminal multiplexer with cross-pane AI agent communication — no WSL2 required.

Durable task planning for Codex/AI coding agents: recovery, bug memory, Mermaid-first design, verification evidence, and safe multi-agent collaboration. 为 GPT-5.6 深度优化，也兼容其他模型。

Evidence-based review loop for iterating AI agent skills and subagent role briefs.

Agentic AI assistant built on the OpenAI Responses API, featuring image generation, support for user-defined MCP tools, billing and user management, and secure execution of untrusted commands within microVM sandboxes.

Turn your ChatGPT account into a local software factory. Four browser tabs plan, write, review and audit real projects, then install, run and screenshot them. No API key.

A System 2 Cognitive Middleware that replaces static data pipelines with runtime code generation. Features Gemini 3 Pro, E2B Sandboxing, and Self-Correcting Triangulation.

An interactive, chat-driven learning system and production reference architecture for recommendation-system engineering with layered LLM guardrails, built with FastAPI, LangGraph, Ollama, and pgvector, fronted by a modern Next.js / React 19 App Router lab UI.

phone as a native device for AI Agents

The open standard for cryptographic identity and trust verification of autonomous AI agents.

Agent-You-MustKnows 是一个面向 AI Agent 领域的系统化学习与研究知识库，旨在整理 Agent 方向的重要论文、技术报告、经典方法与前沿探索。项目围绕 LLM-based Agent 的核心发展脉络，涵盖智能体基础理论、推理与规划机制、工具调用、记忆系统、多智能体协作、RAG+Agent、Agent 架构设计以及未来 Agentic AI 等关键方向。该项目不仅关注论文收集，更致力于构建从概念理解、技术演进到系统实践的完整知识体系，帮助研究者和开发者快速掌握 Agent 领域的重要思想、核心技术与发展趋势，探索从“能够生成文本的语言模型”到“具备感知、推理、行动与持续学习能力的智能体系统”的演进路径。

Project management as flat files in your repo. YAML tasks, a computed roadmap, driven by your AI agent. No database, no SaaS. MIT.

Salience-gated memory for Claude Code — captures what matters, forgets what doesn't, consolidates patterns while sleeping

Artificial intelligence (AI) chat bot for Discord written in Python 3

ShuttleAI API Info - FREE GPT-5

🔥优雅魅力御姐 Skill，高级妩媚气质氛围感，合规安全的成熟女性 AI 人格｜Claude Code Skill

The multi-tenant WhatsApp API platform — REST API, webhooks, isolated sessions, and native n8n integration.

Cross-platform (Linux/macOS/Windows) terminal + tray usage tracker for Claude Code, Codex, and other AI coding subscriptions

Cuts what your coding assistant spends per task, and shows you the numbers. Works with Codex, Claude Code, Hermes, GG Coder and any command-line agent.

Portable /goal-writer agent skill for Claude Code and OpenAI Codex — drafts goal+rider document pairs (≤4,000-char goal + phased rider) per goal-engineering best practices

Universal engineering judgment for Claude Code. Read before editing, reuse before writing, verify before shipping.

Claude Code skill: pick the right loop type (/goal, /loop, /schedule) and write stop conditions that actually hold. From the Claude Code team's loops taxonomy + real overnight autonomous runs.

macOS menu-bar app that watches your Claude & Codex usage and auto-switches accounts before you hit a rate limit.

A cute desktop pet with a live Claude token usage meter - session & weekly rate limits in a thought cloud above your Windows taskbar. Free, open source, one-press install.

Self-hosted AI gateway for agents — route providers, virtual models, limits, and usage from one console.

Lunar Vault is a self-contained memory infrastructure for Codex. Features zero-dependency ONNX embeddings, advanced reranking, and secure one-click installation without leaking personal data

Kotlin Multiplatform semantic cache for LLM calls: eleven guards against false cache hits, measured on blind corpora, coroutine-first.

working on something and tweaking somethings to just get a better clarity on the internal changes in lang graph, crew Ai, tool calling and setting up multi agent using RAG: Primary focus HEALTHCARE, Mostly Synth data

Swift-first toolkit for shipping on-device AI on iOS, macOS, visionOS, tvOS and watchOS — Core ML LLM runtime with SwiftUI prefabs, structured output, tool calling, RAG and speech.

Multiplatform 3D chess app powered by Stockfish, featuring on-device AI move coaching and cloud-based RAG for position chat.

Corpus poisoning attacks against RAG-based cybersecurity/IoT threat-intelligence assistants, with a lightweight, edge-deployable provenance defense. Evaluated on TF-IDF and dense-embedding retrievers over a CVE/MITRE ATT&CK/vendor-advisory knowledge base.

Knowledge of special interest to AI: nine datasets of concepts, relationships, constants and measurements, each one clean file, aligned into a single 544,279-node map, plus a reasoning benchmark. Artificial knowledge for artificial intelligence.

LoRA fine-tuning of bi-encoder retrievers with hard negatives and cross-encoder distillation, evaluated on NFCorpus.

RagTrack is a lightweight Git-like version control layer for RAG knowledge bases. It basically helps you track changes across different documents in your RAG Application

Desktop client for Svoi's external RAG ('My PC') — indexes local folders and uploads them end-to-end-encrypted over a blind relay. The server holds no keys.

Local-first shared memory for AI agents: persistent AI memory across Claude Code, Codex, Hermes Desktop, and any MCP client. Automatic record, recall, consolidation, forgetting, and backup. Self-hosted on Qdrant + LlamaIndex; one-command install.

Detect prompt regressions before they reach production — per-category accuracy scoring, deterministic validation, and False Improvement detection. Pure Python, zero dependencies.

Full-stack AI English coaching app built with React, Node.js/TypeScript & Express 5. Features Gemini-powered level-aware chat, WebSocket voice coaching, PostgreSQL + pgvector RAG help bot, and vocabulary bank.

Semantic gravity database in Rust: related records live together on disk, so graph traversal is a range scan and vector search is exact — never approximate. Runs in 256 MB, with a built-in MCP server for agents.

AI-powered repository intelligence platform that analyzes GitHub repositories, explains beginner-friendly issues, generates contribution roadmaps, and produces structured PDF guides for open-source contributors.

A modular, local AI companion featuring a RAG pipeline with FAISS and SentenceTransformers for semantic long-term memory. Powered by GGUF models via llama-cpp-python

⚡ Blazing-fast GPU vector search for PostgreSQL powered by NVIDIA cuVS.

Compare embedding models locally with LM Studio — cosine similarity UI for RAG workflows

Self-hosted knowledge for humans and agents.

Code Navigation for AI

Spinosa is a local framework for working with LLMs. It features a set of sub-agents coherent with modern SKILL and AGENTS protocols to streamline research and build better practices.

Claude Code 技能：客户端软件全维度防破解安全审计（7大通用维度 × 9个平台专项）

原生 macOS AI 安全智能体：漏洞情报、知识图谱、多语言代码审计与报告交付 | SwiftUI + FastAPI + LangGraph

Official DSers MCP Server documentation and metadata for AI-powered dropshipping automation.

Farming Code is a self-hosted browser workspace for running and supervising Codex, Claude Code, OpenCode, and other AI coding agents.

Turn AI agents into team members: assign objectives with a definition of done, talk in channels, and review every LLM call — self-hosted. Claude Code and OpenAI Codex runners included.

AI Business OS: multi-agent platform with RAG, OCR, speech & workflow automation. FastAPI + LangGraph + Celery + Flutter. Production-grade, Dockerized

Multi-Agent Coding Harness with pluggable AI-SDLC: switch sessions across claude, codex, gemini, export/share coding sessions, save tokens, multi-frontend (TUI · web · Telegram).

Official implementation of "Learning to Assist: Physics-Grounded Human-Human Control via Multi-Agent Reinforcement Learning" (CVPR 2026)

Claude agent skill that plans multi-step work as a dependency graph. Subagent fan-out, layered fan-in, model tiering, verification retry loops, human approval gates. No framework, just instructions.

An autonomous AI chatbot built for WhatsApp using Node.js, Baileys, and the Vercel AI SDK powered by OpenAI. Designed to act like an active, context-aware participant in group chats and direct messages, Quart goes far beyond traditional command-and-response bots by actively listening and engaging in human conversations.

Stateless CLI giving AI coding agents persistent identity, a typed lifecycle, and crash-recovery. Self-hostable, AGPL-3.0.

A version-controlled lakebase for the next generation of AI applications.

Self-hosted agentic AI for strategy & business intelligence — market research, competitive analysis, and executive-level recommendations, reachable via Telegram, Discord, WhatsApp, or Slack. Model-provider agnostic, deployable 24/7.

Go SDK for Dakera AI agent memory — self-hosted, 88.2% LoCoMo. Vectors, hybrid search, knowledge graphs, sessions.

Agentic gateway providing persistent LLM memory via a markdown wiki. Open-source core of Kortexio.

Business OS — un sistema operativo de negocio agéntico, white-label y AI-first. Clónalo, conéctale tu Supabase y tu agente, y opera tu negocio hablándole a tu copiloto. Next.js + Supabase + Tauri.

Self-hosted EVE Online AI assistant for Telegram, Discord, and CLI — EVE SSO/ESI, local SDE, and OpenAI Responses API.

Paste clipboard images into Claude Code on Windows - fixes the broken Ctrl+V image paste. Converts any screenshot or clipboard image into a file path Claude Code auto-attaches.

Unofficial Model Context Protocol server for iFood — browse, search, cart and order food via AI. Two transports (stdio + HTTP/OAuth 2.1) with real iFood OTP login.

Personal collection of Claude Code plugins and skills: development workflows, cross-model review, issue-to-PR automation. The same marketplace installs in Codex CLI.

Connect your Facebook Ads, Pages, Instagram and lead forms to Claude Code. Ask about spend, cost per lead and your best-performing ad in plain English. Meta Marketing API via curl, no MCP server required. Built by Irfad Imtiaz at My Legal Academy.