GitHub agents

llama-stack-client-swift brings the inference and agents APIs of Llama Stack to iOS.

Mobile control plane for AI agents. Rust + GPUI + QUIC. Available on iOS/Android

Vulnerability impact analyzer that reduces false positives in SCA tools by performing intelligent code analysis. Uses agentic AI with open source models to understand CVEs and verify actual vulnerability impact in your codebase. Keeps your code secure with on-premises execution and human-in-the-loop verification.

Verbosity control for AI agents

an implementation of the ideas in Erik Meijer's "Guardians of the Agents: Formal Verification of AI Workflows" (Communications of the ACM, January 2026)

Permguard is the authorization engine for both worlds: enforce policies on today's systems, enforce continuity on tomorrow's. One engine for governance, AI agents, and distributed execution.

OMF is a compact, user-friendly specification that defines a lightweight API contract between client and server for building conversational agents, and defines a standard schema for the "messages" object, which contains user and assistant interactions.

Dynamic multi-cell selection for cooperative multipoint (CoMP) using (multi-agent) deep reinforcement learning

Code for "Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning" ICML 2021

The implementation of AAAI 2022 paper "Multi-Agent Incentive Communication via Decentralized Teammate Modeling".

Empire Chain is a Python framework that orchestrates all your AI needs by seamlessly integrating LLMs (OpenAI, Anthropic, Groq), vector stores (Qdrant, ChromaDB), document processing, speech-to-text, web crawling, data visualization, and interactive chatbots into a unified interface, making it easy to build powerful AI applications like RAG systems

NeurIPS 2025: Structural Entropy Guided Agent for Detecting and Repairing Knowledge Deficiencies in LLMs

Automated Deep Research with LLMs, web search, paper parsing, and didactic summarization.

The Future of AI-Powered Development: Orchestr8 Transforms Claude Code Into a Complete Software Engineering Team

Unofficial Kotlin multiplatform variant of the Anthropic SDK

Science-driven chatbot development

Pocket AI: OpenAI GPT-3.5 powered free chatbot android app in Flutter similar to Chat-GPT

An open-source implementaion for fine-tuning SmolVLM.

Medusa AI Assistant admin widget that turns human language into returns within seconds.

Custom 3D TShirt designer. Design your own T-shirts from scratch, customize its colors, logo etc. Made using ThreeJS, ReactJS and Custom Hooks.

An AI assistant built with PHP, Solr and LLM backend of choice. Proof of concept mostly.

Too many docs? Quickly search over any PDF or Markdown documents

[SOICT 2024] LLM-Powered Video Search: A Comprehensive Multimedia Retrieval System

PDF Parsing Tool: GOT's vLLM acceleration implementation, MinerU for layout recognition, and GOT for table formula parsing.

A sample project to showcase agentic AI development with Power BI

A blueprint for AI development, focusing on applied examples of RAG, information extraction, analysis and fine-tuning in the age of LLMs and agents.

ContextX: Context-driven AI development framework powered by Claude Code. Transform documents into complete projects with intelligent agent workflows.

[IROS 2024] Official implementation of paper: DriVLMe: "Enhancing LLM-based Autonomous Driving Agents with Embodied and Social Experience"s

Multi-Agent eXchange simulator developed at Oxford-Man Institute

Ready-to-run examples showing NoPII PII protection with OpenAI, Anthropic, LangChain, LlamaIndex, and more

A curated list of efficient, open-source, OpenClaw-inspired AI assistant agents.

A command-line chatbot built with Spring AI that demonstrates Retrieval-Augmented Generation (RAG) and conversational memory capabilities.

KGB-RAG是一个基于neo4j图数据库和其他图数据库的知识图谱检索系统，它可以根据用户的自然语句提问，从原数据库获取相关实体信息，并通过知识图谱检索技术以及结合大模型自身能力来增强回答用户的自然语言提问。

Hands-on hackathon challenges for developing intelligent multi-agent systems with Azure AI services, featuring insurance claim processing workflows and agent coordination.

自适应智能客服项目（Agentic agent）。不用coze/dify，适合程序员的智能客服，自己编程做一个可控的能够完成工作的客服，只需要2个简单文件，稍微配置一下就实现.适合wordpress /其他的

BioDSA: Framework for Vibe Prototyping of AI Agents for Biomedicine

FileGram: Grounding Agent Personalization in File-System Behavioral Traces

villager is an extensible agent based modeling (ABM) framework for the R language. It supports agents, agent aggregations and their associated resources, as well as flexible data management.

Chatbot flow builder using React and try to make the code extensible to easily add new features.

TOON — Laravel AI package for compact, human-readable, token-efficient data format with JSON ⇄ TOON conversion for ChatGPT, OpenAI, and other LLM prompts.

Watchtower — monitor, inspect, and debug all API traffic between AI coding agents (Claude Code, Codex CLI) and their APIs, with a real-time web dashboard.

A real-time shared memory layer for multi-agent LLM systems.

Multi-column chat interface for OpenClaw agents

Composable Google Sheets CLI for humans and agents. Read, write, update cells by key—with Agent Skills for Claude Code and OpenAI Codex.

Local AI chatbot for Matrix with infinite personalities, tool calling, and MCP — powered by Ollama

A local-first AI engineering agent that learns from your codebase using DSPy.

👍 👍 👍 集成了目前最为成熟的 SpringAI，并支持 Ollama、OpenAI、DeepSeek、阿里百炼 多种 AI 模型。并通过 MCP、Function Calling 与大麦项目进行联动，可以让 AI 智能的帮助用户执行操作。实现 只需聊天就能全部搞定！

Official code for the paper: WALL-E: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents

Structured project lifecycle plugin for Claude Code — from idea to production with discipline, parallel agents, and quality gates.

Iterative specification refinement tool: feeds your docs through GPT Pro Extended Reasoning via Oracle for multiple revision rounds until production-ready

a unix-like du command line tool to count token usage per files and directories

A comprehensive collection of CrewAI quickstarts and feature demos designed to help developers learn and master the CrewAI framework through hands-on examples.

Agent Network Protocol White Paper

Build validated web research processes through self-annealing loops. 138 patterns tested, 90%+ accuracy. Works with Claude Code, Clay, any AI agent.

AI-powered ESP32 pentesting device with RF replay, RF jammer, IR control and BadUSB capabilities. Built for LilyGO T-Embed CC1101 & LilyGO T-Watch-S3

Binary Ninja plugin to provide LLM assistance analyzing binaries.

DataSciBench: An LLM Agent Benchmark for Data Science (Findings of ACL 2026)

EmbodiedAgents is a fully-loaded ROS2 based framework for creating interactive physical agents that can understand, remember, and act upon contextual information from their environment.

Local first Second Brain RAG for any Obsidian Vault (works with any Markdown). Works with DuckDB. Also includes a web-app👇.

Digital archaeology skill for cataloging rare hardware, archiving software assets, and bridging to Beacon agent identities and RustChain Proof-of-Antiquity attestations. Based on Echoes of the Silicon Age research.

codex cli hooks - adding voice on each hook

思維模型工具箱 — 200+ mental models across 10 domains for AI-assisted thinking. Agent Skill for Claude Code.

Voice-powered AI assistant platform — connect any LLM, any TTS, with a live web canvas, music generation, and agent orchestration using openclaw. Install: npx openvoiceui setup

AI-ML Companion: an interactive platform to learn AI & ML by watching it work - 22 tracks, 300+ modules, live visualizations - plus 10 end-to-end portfolio projects from classical ML to production LLM & multi-agent systems.

Ralph is a suite of autonomous agents that orchestrate Claude CLI for backlog-driven SDLC automation. Each agent acts as a specialized team member, picking up tasks from your backlog based on specific criteria.

推荐使用usdt支付链接： https://payforcard.com/auth?invite=INV7309B065 ，visa虚拟卡，虚拟信用，vcc购买平台，虚拟货币信用卡，万事达虚拟卡，万事达虚拟信用卡，虚拟预付卡，ChatGPT 开通，海外虚拟信用卡，虚拟信用卡注册，币圈出入金，虚拟卡安全出入金

IRIS 是一个基于 Agentic Workflow（智能体工作流）的自动化深度调研与报告生成系统。它摒弃了传统的单向 RAG 问答模式，通过构建多节点状态机（State Machine），实现了从意图识别、路径规划、动态检索（混合/本地）、深度撰写到自我审查与局部修改的全自动闭环。

An [Agent Skill](https://agentskills.io) that enables AI coding agents to tackle complex, long-running implementation tasks autonomously.

Open source Claude Managed Agents template. Build your own agent.

☕️ Prevents your computer from sleeping while Claude Code works hard

Local-first Windows tray app for monitoring Claude Code and Codex tokens, costs, sessions, and rate limits

Zero Code Studio 是一个工程化 AI 代码生成平台，基于 Spring Boot、LangChain4j、LangGraph4j，支持工具调用、Workflow 编排、任务计划规划、三层上下文压缩、SSE 过程可视化、定点修改与一键本地部署。

Skills, MCP servers, and tools for producing video with Claude Code. Covers programmatic video (Remotion, Manim), screen recording, YouTube clipping, and FFmpeg post-processing.

RedTeam-Agent: AI-Powered Autonomous Red Team Framework via Model Context Protocol. AI红队与内网渗透自动化框架，支持 gogo, fscan, httpx, nuclei, impacket, playwright 等 15+ 渗透工具，让 LLM 直接化身安全审计黑客。

Glyphic gives you a visual interface to configure, manage, and use Claude Code -- the AI coding assistant from Anthropic. Instead of editing JSON files and markdown by hand, Glyphic lets you manage everything through a modern desktop app.

🔥 构建高质量的AI编程Skills库，利用AI来学习编程技术。Collect and build high-quality skills to enable AI to serve you better.

Visual Studio 2026 vide-coding extension: works with Claude, supports auto mode, bash/greb/glob, smart read/write/edit tools, sub agents, theming and more

27 scope-enforced AI agents that run the full pentest kill-chain (recon → exploit → post-ex → DFIR → report) as a one-command Claude Code plugin. Backed by 754 MITRE-mapped skills.

Universal LLM router for AI coding tools. Works with Claude Code, Cursor, Codex, Gemini CLI, Copilot and more. Free-first fallback chain keeps costs 70–85% lower.

The knowledge harness for AI‑native finance — MCP server for LLMQuant Data.

Lightweight Linux sandbox for AI agents. Kernel-native isolation (namespaces, cgroups, seccomp, Landlock) with REST API, MCP bridge, and web dashboard. Single Rust binary.

Open-source email infrastructure for AI agents.

AI Agent的Skills 合集

Platform-agnostic AI agent: one Full-Stack Software Engineer brain, compiled into ready-to-paste adapters for ChatGPT, Claude, Copilot, Gemini & Cursor. Zero-dependency, MIT.

Offline PII firewall for AI agents and LLM apps: fast local detection and redaction, Claude Code hook, LiteLLM guardrail. Zero network calls, one dependency.

Chat with your knowledge base — a conversational RAG agent (LangGraph + OpenRouter) built on Fast Dash's native chat mode. A modern rebuild of the original Embedchain demo.

[ICLR 2026] Computer Agent Arena: Toward Human-Centric Evaluation and Analysis of Computer-Use Agents

A scheduled trend analysis agent built with the OpenAI Agents SDK. It collects Hacker News, Dev.to, and web sources, then generates a structured AI trends report.

The open-source legal AI agent. Documents stay on your machine; redlines land in Word. Fork of OpenCode.

⚡ Translate Markdown without breaking format — code blocks, LaTeX, links all preserved ｜ 翻译 Markdown 不破坏格式，代码块、LaTeX 公式、链接全保留

Agents claim work they did not do. Brigade makes them prove it: a check run through Brigade writes a file with the real exit code. A built-in code graph tells them who calls what and what a change breaks, before they edit. One catalog syncs MCP servers, tools, and skills across harnesses; memory rides a review gate. Local files, no daemon.

AI 命理工程化 — 5 大命理体系（紫微斗数/八字/六爻/印占/奇门遁甲）的工程化 Skill 系统，专为 Claude Code / LLM Agent 设计

A curated collection of ready-to-run automation prompts for real-world workflows.

Pareto-optimal models for cleaning the web — fast, encoder-based main-content extraction from HTML.

An open framework for designing and deploying custom AI-driven HW/SW co-design flows fast

Deterministic spec-orchestration for local LLMs in the pi coding agent — drives prompts through refine→research→grill→compose→critique, with bundled web/docs/fetch worker tools.

Adaptable, accountable AI teams. Visually

An editor for teams of local coding agents (Claude Code, Codex, and friends)

Dispatch less. Deliver more. Multi-agent dispatch governance for reliable delivery.

Autonomous engineering organism — contract-first multi-agent team, 24/7 daemon, persistent memory, git-native safety, Guardian Swarm, MCP + A2A. | Builds production software, not prototypes.