Custom agents

2026 Multi-Agent AI Town Simulation | Polis Darwin LangGraph

Claude Mythos Engine 2026: AI Sub-Agent Framework for Epic Interactive Storytelling

Java AI Assistant GUI 2026: Event-Driven Modular Interface Design

Secure AI Engineering Framework 2026: Data-Boundary Security for Frontier Models

🦡 codebadger is a containerized Model Context Protocol (MCP) server that gives AI agents and LLMs deep, queryable access to a codebase's structure and data flow through Joern Code Property Graphs (CPGs).

AI pixel art agent that paints like a real artist. Not diffusion — actual tool-based painting with shapes, noise, and per-pixel control.

Agentic text-to-SQL SDK: hand the LLM one execute_sql tool and let it explore the schema, test queries, and self-correct — no RAG, no semantic layer. 20/20 on an 80-table Spider run. Built-in tracing and scenario support.

OpenCode AI Coding Agent 学习与实践教程：从 Agents、Skills、MCP、Context Engineering 到 AI Coding Workflow。

Your AI coding agent is only as reliable as the harness around it. Measure that harness in seconds with harness-score.

WhiteLightning distills massive, state-of-the-art language models into lightweight, hyper-efficient text classifiers. It's a command-line tool that lets you create specialized models that run anywhere—from the cloud to the edge—using the universal ONNX format for maximum compatibility.

Multi-Agent Conversation Framework in TypeScript

OpenClaw aka (Clawdbot, MoltBot) is an open agent platform that runs on your machine and works from the chat apps you already use. WhatsApp, Telegram, Discord, Slack, Teams—wherever you are, your AI assistant follows.

Model Context Protocol server to allow for reading and writing from Pinecone. Rudimentary RAG

Comprehensive sets of standards and practices designed to elevate the capabilities of AI coding agents.

A framework for fine-tuning retrieval-augmented generation (RAG) systems.

We present the first systematic study on the scaling property of raw agents instantiated by LLMs. We find that performance scales with the increase in the number of agents, using the simple(st) way of sampling and voting. Our method is called Agent Forest, as a tribute to the classic Random Forest.

Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".

Dr. MAS is an end-to-end RL training framework for multi-agent LLM systems, supporting the co-training of multiple (heterogeneous) LLMs.

A dashboard for running and coordinating multiple AI CLI agents at once.

An OpenCode plugin that integrates OpenSpec, adding a dedicated 'openspec-plan' mode for creating and editing spec files.

SearchAgent-Zero: A Scalable Multi-Turn Search Agent RL Framework

Silent Wolf WhatsApp automation bot.

Source-backed feature comparison of memory systems for AI coding agents. No affiliation, no marketing — just facts from public docs.

不死鸟 Phoenix — Hermes Agent 插件：路由分档/风险防线/自愈/存档点提醒/审批策略自适应，官方钩子接入，不改 Hermes 核心代码

Async Python client for the Model Context Protocol with interactive CLI and reactive Web UI, connecting AI models to MCP servers via stdio and SSE

XMPP/Jabber echo bot (written in sed)

Pebblo enables developers to safely load data and promote their Gen AI app to deployment

Code for Paper: Autonomous Evaluation and Refinement of Digital Agents [COLM 2024]

Yang's PhD work

Prompt focused MCP Server for .json and .csv agentic data analytics for Claude Code

Your AI mate into your favourite terminal

Evidence-first coding agent for GitHub Copilot CLI

👷‍♂️High performance agent framework that can do everything. Minion is designed to execute any type of queries, offering a variety of features that demonstrate its flexibility and intelligence.

一个强大的 VS Code AI 编程助手

Local-first, auditable Python code agent. Ships its own 30-task hidden-test benchmark plus SWE-bench Verified scored by the official harness -- every number reproducible, negative results included.

System for managing collections of agent skills. Switch between skillsets seamlessly!

适合所有人的 AI 编程、AI 应用开发的实战教程——从 Vibe Coding 到 Agent、RAG，循序渐进，边学边做。

Agent skills for Claude Code and other AI agents

Yuan (元) — a unified destiny-reading skill for Codex, Claude Code, and Agent Skills runtimes. One input surface, six methods (BaZi / Cheng Gu / Numerology / Western / Vedic / Zi Wei), production-grade output.

Open-source cognitive coprocessor with active memory for AI agents — persistent recall, semantic search, overnight dreaming, verified facts, encrypted USB sync. MCP server; works with Claude, ChatGPT, and any local LLM. Built by one maker and his agents.

Clear path from where you are to what you want to learn. AI agent turns goals and topic dumps into graph with visible dependencies (generative roadmap.sh)

Production-ready code examples for Telnyx AI Communications Infrastructure — Voice AI, SMS, SIP, and IoT APIs

LLM | Agentic | Security | Operations in one github repo with good links and pictures.

为小红书 AI 工具实操内容生成稳定、干净、精致封面的 Claude / Codex Skill（脚本模式 + Agent 自主执行）

Academic Agents Studio 是一款面向学术研究人员、教育工作者和学生的新一代开源学术研究全流程智能体应用服务平台，基于多模型（GPT、Claude、Deepseek、Qwen等）与智能体协议，提供论文专利写作、文献综述、代码解析、多语言翻译、可视化图表和在线检索等一体化学术功能；基于 Gradio的界面，支持科技感输入区、插件扩展、自定义模型与外部 API，提供模块化、可扩展的系统，致力于帮助全球的研究者、教育者和机构专注于创新和探索，提高学术生产力，促进协作，推动知识创造和突破。

Akari 是一个面向开发者团队的 AI Agent 并行开发管理平台。它基于 Git worktree 为每个会话创建完全隔离的工作区，让你能够同时启动多个 Agent（Claude Code、Kimi、Aider、Shell 等），通过统一界面查看状态、终端输出、代码 Diff，并在任务完成后统一 Review、合并回主干。

Web builder AI-Agent

Toolkit for rapid AI and agent prototyping

A React-based virtual avatar component for real-time gameplay analysis and emotional support. Integrate with screen capture to provide insights and companionship through advanced LLM integration.

A mcp server that bridges the Model Context Protocol (MCP) with the Agent-to-Agent (A2A) protocol, enabling MCP-compatible AI assistants (like Claude) to seamlessly interact with A2A agents.

Create an AI that chats like you

All your AI Agents like Claude Code, Codex CLI in a single TUI to keep things organized.

All-in-one local low-code AI agent development platform. Installs and runs n8n, Flowise, Browser-Use, Qdrant, Ollama, and more. Proxies LLM requests through LiteLLM with Langfuse for observability.

[NeurIPS 2024 D&B] GTA: A Benchmark for General Tool Agents & [arXiv 2026] GTA-2

✨一款面向内容创作者的人工智能助手，整合视频下载、字幕处理、资料检索与桌面执行能力 · An AI assistant for content creators with video download, subtitle workflows, research, and desktop execution

A knowledge source about TTPs used to target GenAI-based systems, copilots and agents

A third-party component library based on Gradio. Integrates Ant Design, Ant Design X, Monaco Editor and more advanced components to help you build applications efficiently.

🌈 这是一个专注于大语言模型人格定制的预设包集合库：DAN机器人、猫娘、丁真、律师、诗人、辩论家、小说家等等，为用户提供了丰富多样的AI角色设定，让聊天体验更加个性化和有趣。

STELLA: Self-Evolving LLM Agent for Biomedical Research

LLM <-> Python agentic runtime prototype

Agent-native TypeScript framework for building MCP servers. Declarative definitions with auth, multi-backend storage, OpenTelemetry, and first-class support for Bun/Node/Cloudflare Workers.

Penetration Testing AI Assistant based on open source LLMs.

Claude Code style AI agent from scratch using Python

CLI tool for agents to quickly access browser telemetry (DOM, network, console) via Chrome DevTools Protocol.

Guides, courses & reading lists for learning to build autonomous LLM agents

AAHL's Agent Skills. 汇集了多种实用的智能体技能，涵盖Home Assistant智能家居控制、微软Edge TTS和智谱GLM-TTS文本转语音、DuckDuckGo搜索、DeepWiki文档检索、加密货币行情、天气预报、Lark/飞书、影视搜索、商品比价等功能

Claude Code subagent for pastry recipe lookup and Baker's Percentage calculation

A curated list of tools, papers, and datasets for applying AI to cybersecurity tasks. This list primarily focuses on modern AI technologies like Large Language Models (LLMs), Agents, and Multi-Modal systems and their applications in security operations.

Lightweight CLI to build self-managing AI agent teams. Define roles, skills & projects in Markdown+YAML — agents run autonomously on a heartbeat schedule, talk to each other via inbox, and delegate tasks. Works with Claude Code, Codex, Gemini, Cursor & more.

For Claude.

SkillLens: a framework for studying model-generated agent skills across the full raw experience generation → skill extraction → skill consumption lifecycle.

Clean-room, model-agnostic harness for Claude Code-class coding agents

Webextension tool for Odoo

UniHarness (formerly HexAgent) – An agent harness that gives any LLM a computer to complete tasks the way humans do

JD-driven Chinese resume optimization skill for China job seekers. 解析岗位 JD、诊断简历缺口、生成真实可信的中文定制简历、ATS 纯文本版和面试追问。

Local-first 🧠 memory for Hermes Agent that lives in your Obsidian vault and remembers project context. Nightly 😴 dream passes turn repeat corrections into confirmed preferences with measurable confidence. Adapters ship for Claude Code, Codex, and OpenClaw, with an MCP server for anything else.

Overleaf CLI - pull, push, sync, compile LaTeX projects from your terminal. Git remote helper, MCP server for AI agents, and TypeScript library.

Native cross-platform SSH ops: persistent tmux sessions × always-on monitoring × built-in AI assistant. Windows/Android, free forever, open-source soon. 原生跨平台 SSH 运维 · tmux 持久化 · 常驻监控 · 内置 AI 助手

An open-source alternative to Cursor, Windsurf (Local RAG, Bring your own LLM, Agents). Written in golang

Total Surveillance Automatic Ban Machine for Twitch and Discord

The multi-agent version of TORCS for developing control algorithms for fully autonomous driving in the cluttered, multi-agent settings of everyday life.

Tutorial to create WhatsApp Bot using Twilio and Python

[EMNLP 2024] OneGen: Efficient One-Pass Unified Generation and Retrieval for LLMs.

Implementation of PALI3 from the paper PALI-3 VISION LANGUAGE MODELS: SMALLER, FASTER, STRONGER"

[EMNLP2025]Official implementation: Agent-style vision question answer in Autonomous Driving!

多AGV路径规划演示模型（CBS算法）

Minimal by design, explicitly multi-lang, production-ready and battle-tested collection of configs and plugins for your Claude Code agentic development workflows: mcp, configs, skills, agents and more.

Multi-agent orchestration system using Claude Code with Git worktree isolation and specialized AI agents for collaborative development

Ultra-Lightweight, Pure Python Multimodal Agent.

A curated list of awesome top best AI Agents

Collection of Claude Code commands and memories for agentic coding.

Payload Skills to assist AI agents

让 AI 主动记错题、自我迭代的协作机制 · A framework that makes your AI reflect on its own mistakes and stop repeating them

Resumable, traceable AI coding — decisions and history stay with the project

Evoplex is a fast, robust and extensible platform for developing agent-based models and multi-agent systems on networks. It's available for Windows, Linux and macOS.

Machine Learning and having it Deep and Structured (MLDS) in 2018 spring

基于seq2seq模型的简单对话系统的tf实现，具有embedding、attention、beam_search等功能，数据集是Cornell Movie Dialogs