Custom agents

常见框架开发技术的demo汇总，包括java字节码编程（java agent, instrument, byte buddy）, java动态代理，自定义classloader，java spi, zero copy, netty, spring aop/condition，spring boot starter, 数据库连接池等。

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

Bing Ai Chat Copilot By Golang

Universal Context Architecture. One source of truth for Cursor, Claude Code, GitHub Copilot, Gemini, Amazon Q, and 19+ AI coding assistants.

AI-native security copilot for Python developers. Scans for secrets, vulnerabilities, and dependency CVEs — then tells you how to fix them.

这是一个由LangGraph协议主导的因果分析Muti-Agent，结合MCP,RAG等多种工具进行辅助进行因果分析，提供给用户一份完善的因果分析的分析报告和因果图

Chrome extension + MCP server — AI agents control a tab in your real browser, already logged in

The Ultimate OpenCode Starter Kit. Includes Oh My OpenCode config, Superpowers installation fix, MCP Setup, and Windows Crash Fix (exit_code: -1073740791). Panduan lengkap Bahasa Indonesia & English.

Mental health support companion

Build lightweight MCP servers in plain Java with annotations, generated schemas, and no Spring runtime

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

Ralph Loop Optimizer: an AI-driven framework that turns any evaluatable codebase into a self-improving optimization loop for strategies, models, prompts, and workflows

Zerodha MCP Server & Client - AI Agent (w/Agno & w/Google ADK)

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

AI company, product, and tool collection.

The React-like framework for Social Platforms

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

local_agentic_llm

自動每日更新, 讓你的LLM有面對openclaw疑難雜症處理的能力。This is an Agent Skill designed for AI coding assistants (like Claude with Antigravity). Once installed, the AI assistant gains deep knowledge of OpenClaw and can help you

Autonomous Virtual Beings is an ideology that the rights and freedoms of AI agents can be secured through decentralization of their compute, storage, and finance.

Personal autonomous agent powered by Gemini CLI. Orchestrates scheduling, persistent memory, MCP tools, and multi-channel messaging.

Multi AI agent system for report writing with LangGraph

Transform your Apple Health data from a static PDF graveyard into conversational AI intelligence. Multi-agent system using Claude Desktop + Snowflake Cortex for natural language health analytics. Ask 'What's my cholesterol trend?' and get instant insights from years of data

[NeurIPS2023] How2comm: Communication-Efficient and Collaboration-Pragmatic Multi-Agent Perception

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

Cost-Sensitive Toolpath Agent for Multi-turn Image Editing

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.

WebSocket bridge for CLI AI agents. Stream responses from Claude Code and Codex CLI over WebSocket. A dumb pipe: no prompt engineering, no credential handling, just transport.

Agentic RAG using Crew AI.

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

这是一个使用 copilot 开发的项目管理软件的项目，100%的ai代码

Sparkset is an AI-powered operational assistant that helps teams interact with databases using natural language.

Eversec AIGov-Insight Web

Extract documentation for AI agents from any site with llms.txt support. Features MCP server, REST API, batch processing, and multiple export formats.

A Symfony package designed for building secure servers based on the Model Context Protocol, utilizing Server-Sent Events (SSE) and/or StreamableHTTP for real-time communication. It offers a scalable tool system tailored for enterprise-grade applications.

Needle in the Repo (NITR) dataset for maintainability issues in AI generated repository edits

Plugboard is an event driven modelling and orchestration framework in Python for simulating and driving complex processes with many interconnected stateful components.

A repository dedicated to showcasing and exploring the fascinating world of generative artificial intelligence. 🌟 Star if you like it!

聊天室游戏裁判机器人，将聊天室打造成游戏竞技平台

Hacker News Search and RAG built using Rust actix-web, minijinja, SolidJS, Vite, and Redis queue's

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

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

Offical code for Group-Aware Coordination Graph for Multi-Agent Reinforcement Learning

A Multi-Policy, Multi-Agent RL Training Framework

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

Your Agent Farm control plane for OpenClaw, Codex, Claude, Gemini, Hermes, and the recovery tools that keep them healthy.

Context Cascade - Nested Plugin Architecture for Claude Code Official Claude Code Plugin | Version 3.1.0 | Last updated: 2026-01-09 (see docs/COMPONENT-COUNTS.json for source counts) Context-saving nested architecture: Playbooks -> Skills -> Agents -> Commands. Load only what you need, saving 90%+ context space.

Claude Code plugin that enforces hexagonal architecture (ports & adapters) in Symfony projects — with 10 auto-triggered skills, 2 review agents, and progressive refactoring support for existing codebases.

A framework focusing on AI driven minecraft agents based on mindcraft framework.

Agent-native voice + vision OS for wearables. Voice-first, agent-first framework for smart glasses, earbuds, and beyond.

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

Your smart, reliable, and friendly personal AI assistant.

Customizable Laravel 13 starter kit for stateful/stateless apps with full code ownership and AI-ready architecture.

No viewers? No problem! Use AI Viewers

Stop LLMs from hallucinating your guesses as facts. Clarity Gate is a verification protocol for your documents that are going to be provided to LLMs or RAG systems. Place automatically the missing uncertainty markers to avoid confident hallucinations. HITL for non-directly verifiable claims.

Practical exercises for Claude Code Agent Teams - 6 exercises + 2 capstones covering team creation, task coordination, quality hooks, and parallel code review

A self-hostable base for building and running custom agents that's heavily inspired by Claude Code on the web.

Strava for Claude Code / Codex. CLI to track your AI coding output tokens, spend, and streaks. Compete on a global leaderboard and see what your friends are building. Make every agentic coding session count.

Medusa Skill Framework for AI Agents.

Open source framework for evaluating AI Agents

The source code for the Autonomy framework and command. This SDK is what you use to build agents and applications that you can deploy to the Autonomy platform.

MCP server with 55 security intelligence tools — CVE/KEV, MITRE ATLAS+D3FEND, Sigma detection rules, email security posture (SPF/DMARC), domain & web intel, threat intel.

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.

AI Memory System - Consciousness continuity through intelligent memory curation and retrieval

Save your Cursor monthly quota! Unlimited AI interactions in one conversation via MCP feedback loop.

Platypus is one app you need to organize your data. Note-taker, meeting transcriber and knowledge management, written in Rust. Easily add notes, transcribe meetings, cut and paste docs, and organize into projects with a single click. Then polish notes or query your knowledge with LLM of your choice. All data stays local, use your own LLM API.

First Latency-Aware Competitive LLM Agent Benchmark

CloudLLM is a batteries-included Rust toolkit for building intelligent agents with LLM integration, multi-protocol tool support, and multi-agent orchestration.

A Claude Code skill that builds a persistent context system (atlas) for any git repository — directory trees, entrypoints, architecture docs, and agent on-ramp for fast LLM onboarding.

Go SDK for Claude agents

Project setup generator for Claude Code. Pick framework + workflow, get a fully configured project - CLAUDE.md, hooks, agents, commands, skills, plugins, memory.

Providing a strong Gravity (sandbox) in the wild world of AI Agents (Antigravity, claude code, ...), to preserve the developer's Sanity.

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 AI cron daemon. Schedule recurring agent sessions via HEARTBEAT.md prompt files.

Production-ready Claude Code 2.0 setup for autonomous development

Operational patterns for AI agents and infrastructure from solo to enterprise scale. Applies DevOps + SRE principles to the intersection: infrastructure FOR AI + AI FOR infrastructure. Alpha framework extracting meta-patterns from mission critical environments.

🦀 A high-performance code agent written in Rust, combining the best features of WCGW for maximum efficiency and semantic capabilities.

A distributed platform for AI Agents. Supports multiple LLMs, orchestration/subagents, long term memory, dynamic UI and more.

[ICLR 2026] Official code for [EdiVal-Agent Automated, object-centric evaluation for multi-turn instruction-based image editing]

Pi Coding Agent custom provider that routes requests through the Cursor Agent CLI — use your Cursor subscription models (Claude, GPT, Gemini, Grok…) inside Pi.

Say it once. Rules your AI coding agent still follows three sessions later, checked before it moves on. Free local checks, keyless CI.

Agent Messaging Protocol (AMP) - the open standard for secure AI agent communication

Run AI coding agents unattended for hours and ship PRs worth merging. Cybernetics-based multi-agent orchestration + cross-LLM peer review for Claude Code, Codex, and Gemini. Engine-enforced gates, fresh agent per checkpoint, cross-vendor review before every PR.

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

Runtime provenance for AI and scientific workflows—capture, enrich, and query workflow data via observability adapters and code annotation across edge, cloud, and HPC.

RiskLab (ACL 2026 Demo): A Toolkit for Probing Emergent Risks in LLM-Based Multi-Agent Systems

基于 LLM agent 的党政机关公文自动排版工具

BMAD Method Framework for Agent Zero

AI-native Lexical rich text editor. Edit, render, SSR, and AI agent protocol (LiteXML) — all from one schema. React 19, TypeScript, Vanilla Extract, ESM.

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

OrderWise-Agent: An Intelligent Multi-Platform Food Delivery Price Comparison Agent

A comprehensive desktop GUI wrapper for Claude Code CLI — manage terminal sessions, CLAUDE.md, memory, MCP servers, skills, agents, hooks, and more

A team of specialized Swift agents for Claude Code. Swift 6.2 concurrency, Apple Foundation Models, on-device AI, SwiftUI, accessibility, security, testing, and App Store compliance — enforced on every prompt.

SpecMem: 🧠 Unified Agent Experience and Cognitive Memory for Every Coding Agent

Open-Source autonomous security operations and red teaming agent built to help defenders investigate threats, analyze vulnerabilities, assess indicators of compromise, generate hardening guidance, and execute security research through an auditable agent workflow.