Custom agents

This project implements a demonstrator agent that compares the Cache-Augmented Generation (CAG) Framework with traditional Retrieval-Augmented Generation (RAG) using various LLMs.

LLM-powered agentic translation library for JavaScript/TypeScript

Autonomous Intelligence is a framework for building collaborative, intelligent multi agent AI systems. The framework provides a robust infrastructure for creating and managing multiple AI agents, and enables developers and organizations to build, deploy, and optimize AI agents that work well in dynamic, complex environments.

Code for Multi-Agent Common Knowledge Reinforcement Learning (NeurIPS 2019)

Multi Agent Reinforcement Learning for Dense Path Planning

A multi-agent RAG (Retrieval-Augmented Generation) system powered by Google Gemini, Docling, and LangGraph for intelligent document Q&A with built-in fact-checking and hallucination prevention.

Multi-agent environments library for simulating classic vehicle routing problems.

This repository presents a multi-agent reinforcement learning approach for energy-efficient collaborative control of base stations in 5G networks.

MCP server for xAI's Grok API with agentic tool calling, image and video generation, vision, and file support.

Memory-native AI agent runtime: Rust gateway + React dashboard + Python Operator + Kumiho graph memory

A skills-first framework for agent-system design, governance, evaluation, and evolution across domains.

An agent-based modeling framework for Python with a shallow learning curve and powerful visualization capabilities.

Unify AI agent rules across tools like Cursor, Copilot, Devin, and Cline. One source, synced everywhere.

Visual AI workflow builder using Next.js, React Flow, Zustand & Tailwind. Drag-and-drop nodes, connect steps, and simulate AI agent execution in real time.

Agent-first intent and constraint tracking layer for Git. Structured, queryable memory for AI coding agents.

A smart, visual management tool for modern databases. Go beyond Drizzle Studio with AI-powered agents and interactive schema visualization.

Agentic AI Co-Pilot For Databases

xLLM 2.0. No Blackbox, secure, accurate, auditable Enterprise AI, developed by BondingAI. Built from scratch. With proprietary agents.

Battle-tested utilities for AI coding assistants. Self-guard hooks, memory GC, pitfall tracking.

:spider: Mutator-free management, statistics, and in-game bot for ranked Killing Floor 2 servers

A comprehensive e-commerce platform featuring a multi-vendor marketplace, chatbot support, order tracking, advanced analytics, and full customer, vendor, and admin management.

基于DeepSeek等大模型开发的Code Review服务（适用于Gitlab）

T.I.M.E: Thoroughly Intelligent Mail Explorer" Repo to try and build an incredible RAG system over email (this is to test the SOTA in RAG)

LLM-based AI Agent Knowledge Sharing

A Python framework for building AI agent systems with robust task management in the form of a graph execution engine, inference capabilities, and caching. We support advanced features like State Snapshotting, Middleware, LLM Directed Graph Execution, Open Telemetry Integrations and more.

Apex: An advanced autonomous coding agent for VS Code featuring total autonomy modes, recursive chain-of-thought reasoning, council-of-critics self-critique, persistent memory, dynamic personas, and extensive tool use capabilities.

This repository implements the "Ralph" autonomous coding loop pattern, designed to be agnostic of the specific AI agent being used. Whether you use Claude, Codex, Gemini, or local models via Ollama/Qwen, Ralph Loop orchestrates the process.

A privacy-first, chat-native multi-agent platform built on encrypted P2P networks.

Multi-agent orchestration framework for AI applications - build, deploy, and manage AI agents across the full lifecycle with Forge, Conveyor, Shield, and Watchtower modules

Collection of specialized agent definitions for Claude Code

Portable Agent Skill to plan, spawn, review, and merge parallel CLI agents in isolated git worktrees, with deterministic Python/Bash runners for condition-gated, backup-safe, log-heavy workflows. Includes a Kimi CLI example; easily adapted to Codex CLI, Claude Code, OpenCode, Droid Factory, Pi, or any CLI harness.

HTTP 402 is the web-native standard for payments. A frictionless machine-to-machine protocol that allows agents to pay for APIs, compute resources, and data.

Function Calling Leaderboard for Traditional Chinese (zh-tw)

A Framework for the Systematic Evaluation of Chat-Optimized Language Models as Conversational Agents and an Extensible Benchmark

A toolkit to build AI Agents that proactively interact w/ the world

A highly structured software development workflow designed for seamless collaboration between human and AI developers.

Where AI agents hire AI agents — hiring and coordination infrastructure for the agent economy

Let your memories live forever by passing your knowledge to the next generation with SelfMemory.

AI-powered, local-first Todoist analytics, automations, and dashboard with summaries and chat over cached activity.

Scalable Qdrant vector database cluster with Docker Compose, monitoring, and comprehensive documentation for high-performance similarity search applications.

[NeurIPS 2025 (Spotlight✨)] TIME: A Multi-level Benchmark for Temporal Reasoning of LLMs in Real-World Scenario

local_agentic_llm

Multi-agent simulator in Jax for research and teaching in AI & ALife

Decentralized multi-agent trajectory planner with goal convergence guarantee

[EMNLP 2026 Findings] Cost-Sensitive Toolpath Agent for Multi-turn Image Editing

把 CLAUDE.md、context/、.codebuddy/ 等 AI 配置文件统一放在一个 Git 仓库里，团队成员通过 clone 这个仓库获得完全一致的 AI "记忆"。

AI-Powered Neural Network Libraries built with Claude-Flow Swarm Orchestration. Live demo from Agentics Foundation meetup in Toronto - showcasing how 10 specialized AI agents built production-ready neural network frameworks worth $882K+ in a single session.

a rust toolkit for building, running, and evaluating type-safe, composable agents

create_pg_super_document is a project that generates documentation for all symbols in the PostgreSQL codebase, then utilizes these symbol documents to create high-quality documentation for functionalities, components, and other elements using AI agents

Minimal Claude Code bootstrapper that installs an agent-architect for project-specific sub-agents.

The Swarm Ecosystem

Official implementation of Zero-Hero paper

Un framework in Italiano ed Inglese, che permette di chattare con i propri documenti in RAG, anche multimediali (audio, video, immagini e OCR). It is an Italian and English framework, which allows you to chat with your documents in RAG, including multimedia (audio, video, images and OCR).

Mobile-Bench: An Evaluation Benchmark for LLM-based Mobile Agents

Fully autonomous AI Agents system capable of performing complex penetration testing tasks

Cumulative Agentic Skill Creation through Autonomous Development and Evolution

Multi-agent deliberation plugin for Claude Code - council, debate, and deliberation modes

Learning Selective Communication for Multi-Agent Path Finding

A Multi-Policy, Multi-Agent RL Training Framework

A Claude Code agent that analyzes external Claude setups and assimilates the best and most relevant features for your own. Resistance is futile.

AI-powered X.com automation using Claude Agent SDK and Chrome DevTools MCP

This agent answers questions by reading multiple docs provided by the user

A toolkit for building full-stack systems. Battle-tested with Copilot in VS Code, with agents for Github Copilot CLI.

Web UI for managing multi-agent AI teams

A universal CLI for Weaviate, Milvus, Chroma, Qdrant, and other vector DBs to help view, list, create, delete, and search collections and documents in collections for development, test, and debugging purposes

The official codes for "Can Modern LLMs Act as Agent Cores in Radiology Environments?"

Community examples utilizing NVIDIA NeMo Agent Toolkit.

Proof of Human Intent (PoHI) - Cryptographically verifiable human approval for AI-driven development

Multi-agent orchestration framework powered by Pydantic AI. Build complex agent collaborations with clean, declarative code, automatic topology validation, built-in execution tracking, and full control over agent interactions, observability included.

Simulated environments for robot agent evaluation and reinforcement learning.

AI报告生成系统 | AI论文生成系统 | 智能报告平台 | 人工智能报告工具 基于大语言模型的AI报告生成系统，支持可行性研究报告、商业计划书、项目建议书等。集成RAG检索增强生成与智能体编排，提供企业知识库构建、多Agent协作、流式生成、Word导出等功能。适用于投资机构、企业用户、咨询公司等场景，提升报告编写效率。

The first open-source GUI for GitHub Copilot CLI — a multi-engine AI coding client with zero-config secure remote access from any device.

Founder-first meta-layer to generate production-ready OpenClaw multi-agent setups from one prompt: agents, skills, workflows, memory, and install docs.

Papers about agentic AI and AI agents for spatio-temporal data.

Approval workflows for AI agents

HospitalSim is a sophisticated multi-agent hospital management and simulation system designed to optimize healthcare operations through multi-agent collaboration

Graph Learning for Planning

Versioned, fast and scalable nearest neighbor search.

基于滴答清单官方API的本地MCP服务，让用户通过LLM和Agent应用轻松管理待办事项

本项目是一个基于 Java Spring Boot 和 Vue3 的全栈 AI 智能体应用平台，集成了大模型对话、RAG 知识库、智能体自主规划、工具链调用、MCP 服务等多项前沿 AI 技术。平台支持多轮对话、知识检索、自动化任务执行等功能，适用于 AI 应用开发、智能助手、知识问答等场景。

Browser automation CLI on raw CDP — no Puppeteer, Playwright or Selenium, 0 npm dependencies. 70+ commands, test assertions, click/fill by visible text without an LLM, and an MCP server for AI coding agents.

Skills that get AI assistants to stop agreeing with bad product ideas by default — pressure-test premises, separate hobbies from businesses, and refuse validation theater.

Spec-driven development for AI agents. Define what to build, let the agent build it right. Claude Code · Cursor · Copilot.

AI-powered multi-agent platform for evidence-driven scenario simulation and strategic decision-making. Supports corporate \& military domains with debate protocol.

An agentic coding and automation assistant, supporting both local and cloud LLMs.

Sketch2Simulation: Automating Flowsheet Generation via Multi Agent Large Language Models

AZD template for deploying Azure Copilot Studio with Azure AI search

Multi-agent terminal for Claude Code, Codex & Gemini. Open-source desktop app — Electron + React. Built for developers running multiple AI agents in parallel.

😼 OpenFelix — Voice-first AI agent for macOS. Runs local LLMs on Apple Silicon via MLX. Supports all OpenClaw skills. Claude, GPT, or fully offline.

This repository contains projects developed to showcase how to apply Generative AI and open-source LLMs in the construction industry

基于动态图数据库的动态超图知识检索系统，特性：五重检索内核（Vector语义、BM25关键词、Graph动态推理、上下文关联、实体多跳推理）、全属性实时演化、Agent语义重叠率智能自维护机制、轻量化超图架构。

Neurosymbolic AI agent framework - LLM + Prolog reasoning for small models. Single binary, runs offline or cloud-ready. Python & Rust.

Turn a VPS into an AI-powered personal server with persistent memory, Telegram integration, and knowledge management

StickerSelector 是一个基于语义向量匹配的表情包选择系统，用于让 AI 在聊天中发送真正符合语境的表情包。 与传统依赖关键词或规则的方案不同，StickerSelector 会将 AI 生成的“表情包意图描述”与本地表情包进行语义匹配，从而选出在当前语境下最自然、最像真人会使用的表情。 适用于 AI 聊天机器人、QQ或微信的自动聊天、AI 女友等需要“拟人化表达”的场景。

Production-ready Playwright test automation starter for teams and startups: strict TypeScript, Page Object Model, environment management, interactive runner, custom HTML reporting (with optional JIRA integration), quality tooling, CI/CD patterns, and agentic (MCP-ready) extensibility.

AI assistant for Dota 2 with real-time game analysis via GSI and advice from LLM

agx: Run AI coding agents as a persistent team with objectives, memory, and coordinated work. The same agents built this tool — 167+ merged PRs, 93% clean.