Custom agents

Open Dynamic Workflows: TypeScript CLI runtime for Claude Code-style dynamic workflows across Codex, Claude Code, Gemini, Qwen, Kimi, and custom coding-agent CLIs.

A Claude Code plugin that fills your job applications from your profile, drafts the cover letter, and leaves Submit to you. Locally.

🦀 Decoder-only LLM built from scratch in pure Rust using Candle — no Python, no PyTorch. Gated DeltaNet + sparse attention, fine-grained MoE, native video/document understanding, long-horizon tool agents, quantization-aware training. Scales: Tiny (25M) to Large (1.3B).

Python terminal AI agent CLI with ReAct tools, MCP, Runtime API, memory, snapshots, web search, and image input

MCP server for Z-Library: search, download, and process books into RAG-ready text for AI assistants (Claude Code, Claude Desktop, Cline, RooCode)

The UI SDK and agent-ready developer toolkit for AI factories, robotics, and autonomous vehicles.

Enterprise AI customer-service Agent platform featuring hybrid intent recognition, multi-agent orchestration, MCP-powered RAG, dynamic Skills, memory, human handoff, observability and evaluation. 小祥智能客服系统，支持可追溯、可观测与云端部署。

跨平台的 draw.io (diagrams.net) 图表生成技能，适用于 Claude Code、codex、zcode、workbuddy、OpenClaw 等各类 AI 编程 Agent。Agent 直接生成 drawio XML，校验后通过 CLI 导出图片；没有桌面版时自动降级为 draw.io 官网打开链接。

Cross-border e-commerce AI knowledge base, read by people and installed by agents: 69 trilingual guides, 878 prompts, a 100-entity / 322-constraint ontology, and 9 skills as a Claude Code plugin or over MCP. Factual claims are dated and CI-verified. CC0.

Multi-agent code review, supervised and auditable

thinkingbox is a framework for defining tool as MCP servers, running LLM agents against them, and evaluating agent behavior — for offline training-data generation, reinforcement-learning training loops, and model evaluation.

Unified adapter framework for evaluating agent harnesses (claws) on SWE-bench

The Applied AI Field Guide: fieldwork, value, engineering, and operations for AI that works beyond the demo.

An open-source research system for autonomous investigation, recursive self-improvement, and human–AI collaboration. Run experiments, refine methods through evidence and feedback, and turn traceable research into paper drafts.

Autonomous AI Lead Generation, Social Discovery & Smart Conversational Growth Agent for Threads & Instagram. Multi-platform with native browser CDP.

Experience-driven automated environment configuration with LLM agents, speculative execution, and adversarial verification.

Qwen-Planner-Agent: A Closed-Loop AI-for-AI Framework for Real-World Mobile Planner Agents

Local screen recording and agent-assisted video editing for Claude Code, Codex and other AI agents on macOS.

Open-source YouTube AI video editing system: Eyeline teleprompter, editing agents, JSON, Claude Design, animation and motion graphics.

AI Agent Lockout Backup Kit A vendor-independent continuity kit for backing up, rotating, and recovering information used by AI agents—without storing secrets in the agent or in GitHub. Check out Muse, your personal AI agent. Code: 5F2V31 https://muse.ai/join

TaskFlowAI is a lightweight and flexible framework designed for creating AI-driven task pipelines and multi-agent workflows. It provides developers with a streamlined approach to building agentic systems

A simple experiment on letting two local LLM have a conversation about anything!

🚀 Open-source AI IDE plugin for intelligent code completion, codebase indexing & multi-model chat. Learning-oriented AI engineering platform for IntelliJ IDEA & VS Code.

Hierarchical Cooperative Multi-Agent Reinforcement Learning with Skill Discovery

Radhika is a multi-model AI assistant built for your mood and friendship 💞

All the code and materials

Limopola is an AI platform that allows you to communicate with a wide range of AI models. It features autonomous agents, model-agnostic reasoning, and more.

Conflict-based search for multi-agent path finding

Generative Engine Optimization skills for AI agents. Optimize content for ChatGPT, Perplexity, Claude, and Gemini.

CAMEL framework-based multi-agent system for task-driven and dynamic environments

All-in-one Python framework for building production-ready LLM agents and workflows. Developed by Miquido.

Implementation of the board game Codenames, re-imagined as a collaborative game between LLM agents

🌈RainbowGPT AI Agent & Dalle3 free & Stock Analysis & GPT-4 Free API & Private LLM Application & SQL Agent for Everyone

AI Sub-Agents Collection for Claude Code - AI智能代理集合

Framework integration with PyTest

An AI Agent tool to automate Android devices reliably

Sad's HKTRPG is a TRPG dice rolling bot for Telegram, Line, Whatsapp, web site and Discord. 現支援TRPG暗骰, TPRG擲骰, 頻道經驗值, 占卜, 先攻表, TRPG角色卡, 搜圖, 翻譯, Discord 聊天紀錄匯出, 數學計算, 做筆記, 隨機抽選, 自定抽選

Autopus-ADK is of the agents, by the agents. for the agents. Multi-model orchestration (consensus/pipeline/debate/fastest). Architecture-as-Code, Lore decision tracking, SPEC/EARS engine.

iloom: a developer workflow system delivered as a CLI and a VS Code extension for structured AI-assisted development. The CLI is the system of record, running tasks in isolated workflows and persisting analysis, plans, and decisions to your issue tracker, while the VS Code extension exposes insights, assumptions, risks, and decisions in real time.

Deeptoai 系列 RAG 教程

Official Code for "EigenTrajectory: Low-Rank Descriptors for Multi-Modal Trajectory Forecasting (ICCV 2023)"

macOS accessibility inspector for AI-agent workflows. Hover, annotate, copy structured output.

Code Repository for: AIRTBench: Measuring Autonomous AI Red Teaming Capabilities in Language Models

The issue tracker your AI agents are missing. Think Linear or Jira, but for your Claude Code..

WinDbg Copilot - Agentic Debugging extension

Multi-agent AI platform with voice and text control. Visual workflows, web interface, and chat integrations (Telegram, Discord, Slack). Long-term memory, any LLM backend, extensible via MCP tools.

The source code of [Sec'25] Make Agent Defeat Agent: Automatic Detection of Taint-Style Vulnerabilities in LLM-based Agents

Production-ready multi-agent academic illustration system with Chinese GUI, background generation, plot workbench, and portable result bundles. Extended from PaperBanana.

这是一个为 Claude Code / AI Agent 设计的诊断技能（Skill）。它通过自省式分析和多项特定的压力测试，帮助用户检测当前使用的 API 是否为官方原版的 Claude 4.6 模型，或者是否存在第三方中转、提示词注入与封装。

OpenClaw Desktop – One-click .exe Windows installer & native desktop app for the OpenClaw AI agent framework. Run, update, and manage OpenClaw locally with ease. | 龙虾智能体官方中文桌面版一键安装部署EXE程序

Experimental agent swarm extension for Pi. Inspired by Claude agent teams.

SRA-Bench and SR-Agents: a benchmark and toolkit for skill-retrieval-augmented LLM agents.

Enterprise RAG ecosystem managing 32000+ semantic chunks. Features hybrid parsing (LlamaParse/PyMuPDF) and 256-dim MRL embeddings for 512MB RAM environments

网约车场景的 Spring Boot 全栈实战：Redis 高并发考点全覆盖（抢单秒杀 / GEO 派单 / 延迟队列 / 缓存一致性）+ 手搓 ReAct 多 Agent 框架

Apple Watch notifications for Claude Code and AI agent workflows.

Local-first AI decision workspace with four competing perspectives, human approval, evidence tracking, and native macOS and Windows apps.

Native Word (.docx) generator tool for Open WebUI — Markdown/JSON in, cover pages, styled tables, callouts, TOC out. MIT.

Production agent skills for Claude Code, Cursor, and any SKILL.md harness — Codex fleets, video pipeline, monorepo review bundles, multi-chain explorer.

Awesome Multimodal Agent

Local-first coordination hub for Codex x Claude: shared identity, tasks, messages, write intents, immutable review bundles and a replayable event stream. The Hub never calls a model itself.

The open source agentic dental software. Built for AI.

Self-evolution for any agent harness. Plug in. Evolve. Measure.

Open-source canvas for orchestrating Claude Code, Codex, and other CLI agents. Run agents in parallel, delegate tasks, and let AI build reusable workflows.

Trusted e-commerce AI after-sales platform — RAG, controlled tools, human confirmation, Java-authoritative writes, and observable workflows.

墨参 MoShen · 个人写作 Agent — 自整理资料、自核对设定、自追踪伏笔，但不代你动笔

AIBuildAI LLM-Post-Train Agent: a recursive self-improving (RSI) agent for autonomous LLM post-training

中国软著登记材料生成器：源码进去，页数一页不差的 PDF 出来

Claude Code / Codex / AI configs for the expert Solana builder. CLAUDE.md, agents, commands, hooks, rules, skills and settings across Web, Anchor, Pinnochio, Unity, Mobile, security and more.

Team Avatar: a universal agent orchestrator for Claude Code, Codex, and Cursor. Nine Avatar characters, 58 engineering skills. pstack with Avatar characters on top.

Claude Council Khalifa ⚖️ مجلس من 4 Agents (المؤيد، المشكك، المستثمر، الحَكَم) بيحكم على فكرة البيزنس بتاعتك: ابنيها، عدّلها الأول، ولا انساها

Native GUI Terminal Agent & Mobile Vibe Coding Hub for Claude Code, Codex & CLI Agents. Seamless Phone ↔ PC task collaboration over Tailscale & FRP.

Kumoss turns natural-language requests into compliant, plan-validated Terraform/OpenTofu pull requests - with drift correction, policy gates, and human review. Multicloud, bring-your-own LLM.

Lightweight multi-platform AI agent chat framework. Connect multiple LLMs to Feishu/WeCom/QQ with composable tools, long-term memory, scheduling & browser automation. | 轻量级多平台 AI Agent 聊天框架，连接多个 LLM 到飞书/企业微信/QQ，支持可组合工具、长期记忆、定时任务和浏览器自动化。

wxpath - declarative web crawling with XPath; a Web Query Language (WQL)

Silent Wolf WhatsApp automation bot.

🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, distributed swarm intelligence, RAG integration, and native Claude Code support via MCP protocol. Ranked #1 in agent-based frameworks.

UAV Logistics Environment for Multi-Agent Reinforcement Learning / Unity ML-Agents / Unity 3D

🚀 One-command requirement development flow for Claude Code - Complete workflow system with sub-agents, quality gates, and intelligent automation

A tool to interact with Windows drivers to perform a raw disk read and parse out target files without calling standard Windows file APIs

The source code of the paper "Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning".

Remote MCP server (SEE + Streamable HTTP) implementing the MCP spec's authorization extension. Use directly from your agents, or from Cursor / Claude with mcp-remote

An F/OSS solution combining AI with Wikipedia knowledge via a RAG pipeline

Multi-Agent Reinforcement Learning for Mobile Manipulation with NVIDIA Isaac Sim

AI desktop pet with social agent(live in telegram, QQ, whatsapp) with map and local memory. Unified access to frontier LLMs

Scala code intelligence for coding agents. Zero Build Server. Zero Compilation. Just answers.

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

Open source, local first AI medical agent for desktop and web.

A framework for self-improving prediction market trading agents.

Shareable Claude Code infrastructure for PhD researchers — skills, agents, hooks, and rules for academic workflows

Skardi is a self-improving context framework for ai agents

AI Instructions Diagnostics | Supported agents: Claude | Codex | Copilot | Cursor | Gemini

Marketing skills for AI agents — paid ads, social media, SEO, competitor research, creative generation, email, analytics, and more. Powered by Hyper MCP.

The open automotive contract for MCP, A2A and Personal Agent Protocol: dealer discovery, inventory, evidence, pricing and consented inquiries.

Agents for Role Play. Agents for Game. Agents as a Game. An orchestrator-agents engine for living worlds — file-backed, event-sourced.

Free open-source Screenpipe GUI + macOS automation agent. Search your screen history, view analytics, automate workflows — all local, no cloud. Works with the free Screenpipe CLI.

给智能体安装了思维导图，让 Codex/Claude code/Agent 在复杂问题上用“可见思维树 + 轻量 MCTS”来探索，而不是线性瞎试。

AI protocol scanner — discover exposed MCP servers, A2A Agent Cards, and open LLM APIs in one command. 一条命令盘点 MCP、A2A Agent Card 和 LLM 开放接口暴露面。

Turn your own PDF textbooks into an AI-searchable knowledge base and structured, fully-cited notes — figures included. Local-first, token-frugal.