Custom agents

AI agent skills for Nutrient APIs and SDKs — works with Claude Code, Codex, Gemini CLI, Cursor, and 35+ more agents

Official Alibaba Cloud MCP servers, skills, and plugins to help AI agents build on Alibaba Cloud

Personal knowledge vault plugin for Claude Code — session recording, memory distillation, and hybrid semantic + BM25 retrieval.

A curated paper list on On-Policy Distillation (OPD) & On-Policy Self-Distillation (OPSD) for LLMs — student rollouts + teacher feedback, covering white-box/black-box methods, OPD-RL hybrids, agentic & multimodal applications, and industrial multi-teacher recipes.

OpenCurro AI Agent is a fast, lightweight, and autonomous general-purpose AI agent.

RepoDoc is a lightweight, zero-dependency utility that scans any project directory and generates a complete Markdown document containing the full directory structure and source code of all text-based files.

TRACE Bench: Task-driven Roleplay Agentic Checklist Evaluation

Open-source Polymarket AI trading bot — multi-agent news swarm for fair-odds edge detection, Kelly sizing & CLOB paper/live execution.

EvolveX is a research framework for principled agent self-improvement. It evolves prompts, skills, and agent code under frozen evaluators and declared mutation boundaries, recording verifiable lineage — scores, artifacts, and Git-tagged generations, so every improvement is reproducible and auditable.

An LLM Benchmark evaluation platform for automated model testing and analysis. 面向大语言模型的 Benchmark 自动化评测平台，支持模型测试与结果分析

Local-first AI coding agent runtime — your models, fail-closed safety, evidence-gated self-improvement

A harness-engineered AI agent runtime. Build agents with tool isolation, self-correction, and permission scoping out of the box.

通用 AI agent skill / 脚本包：Search / Fetch / Map 三类网络访问能力，调用 Grok / OpenRouter 兼容接口，并行返回 Tavily / Firecrawl 独立信源。A lightweight web-access toolkit for AI agents: Search / Fetch / Map powered by Grok-compatible APIs with Tavily / Firecrawl sources.

A personal substrate for agent packages that ship their own screens. One manifest declares the agent, its verbs, and its UI.

Agentic terminal forked from the holy Alacritty.

🦞 Headless real-time Python voice assistant powered by ElevenLabs, Gemini, Mem0, MCP tools, and local wake-word detection.

dsh-lark-bot：把 DeepSeek Harness (dsh) 桥接进飞书/Lark 的 bot：流式卡片、项目工作区、并行任务、多角色 Agent、跨会话通知、对话内模型/密钥管理与安全网守护（dsh 崩溃后飞书仍可自救）。A bridge bot connecting DeepSeek Harness (dsh) into Feishu/Lark: streaming cards, workspaces, parallel tasks, multi-role agents, cross-session notify, in-chat model/key management, and a safety-net guardian.

⚡️ The "1-Minute RAG Audit" — Generate QA datasets & evaluate RAG systems in Colab, Jupyter, or CLI. Privacy-first, async, visual reports.

Domain-specializált, RAG-alapú multi-ágens pre-audit rendszer transzferár-dokumentációk (TP) elemzésére. 🏆 7. helyezés a PwC Hungary AI Hackathon 2026-on.

基于 Yui 的机器人框架. 无electron依赖

Bot moderator for your telegram chat

macOS GUI 安裝精靈 — 讓 OpenClaw 設定從 30 分鐘 CLI 變成 3 分鐘圖形化體驗 | Swift 6.0 | 繁體中文

Coordinate AI agents in a workflow

Learn TypeScript chatting effortlessly with AI

a newsstand skill that gives agents API access to the current main headlines of many newspapers across 20 countries.

🤖 A lightweight chatbot that knows nothing and has to learn from scratch. Using sqlite and python. Also comes with a Discord intergration 🗣

A Web Chat bot to determine the prakriti of an individual.

A Minecraft anarchy server chatbot

Langflow chat proxy and frontend using FastAPI and HTMX

An advanced AI-powered conversational agent leveraging the Llama 3.2 model and Phidata framework. Features include reasoning, natural language interaction, and tool integration for web searches and calculations. Designed for interactivity with enhanced logging, support for custom tools, and structured outputs.

This repository introduces a Gemini CLI extension that integrates File Search feature. This tool provides a fully managed Retrieval-Augmented Generation (RAG) system directly in your command line, enabling content generation grounded in your private documents and data.

🧑‍⚕️ Ai智能医生聊天助手-这是一个前端基于Vue3、TS、后端基于Nest.js、MongoDB、Redis、Milvus并结合大模型、RAG等技术实现的医疗库智能问答系统，能结合大模型的生成能力和上传的专业医疗领域知识库针对提问给出专业回答。同时具备工具调用能力，可使用MCP集成网页爬取能力让大模型根据网址对应的医疗领域文章进行分析和输出。

AI-powered tool to run old Windows games on macOS via Wine — automatic configuration, no manual setup. Supports Apple Silicon and Intel.

Give AI agents eyes and hands inside your live React app — no browser extension required

Local-first desktop workspace for creating, versioning, comparing, and shipping AI Agent Skill assets.

Discord server management CLI for AI agents and humans. Channels, roles, permissions, messages, embeds, files, emojis, invites, audit logs. One command = one API call. No bot server needed.

OKR lifecycle management skill for AI agents. Create, track, and report on Objectives and Key Results.

TaxEase.AI is a user-friendly AI assistant designed to demystify and simplify US tax filing, a system that has become needlessly convoluted and stressful for millions of Americans.

Agentic IQ - $AGENT

Pure CLI + HTTP messaging gateway for routing channel messages to external agents.

personal-cfo , Reference implementation — 展示非專業投資人如何用確定性運算做退休軌道監控。銀行帳單進，財務報表出，資料留在本地。Fork 後依照你的情況改 config.yaml 就能用。

A Baseline for an Omnipotent AI Data Catalog

Connecting AI to biomedical data

Minimal tmux popup radar for Codex, Amp, Claude Code, OpenCode, Pi, Gemini and Auggie.

Connect agents to agents. MCP server for querying any LLM through your existing subscriptions: compare, vote, and synthesize across GPT, Gemini, Claude, and local models from one terminal.

SAM - Autonomous TDD agent system for Claude Code, Cursor, Gemini CLI, GitHub Copilot, and Antigravity. PRD in, working tested app out.

OneSDK: A unified AI access SDK for edge devices, providing LLM capabilities (text/voice chat, image generation) and IoT device management with MQTT support, compatible with ESP32, Linux, macOS, and Windows platforms.

A fully client-side chat application with AI capabilities running entirely in your browser. No servers, complete privacy, and persistent storage.

Generate reliable data visualizations from LLM output using validated specs.

Autonomous AI Agent built on tinyloom

CLI Ralph Loops with Good UX

Principal Agent Protocol — a principal-first, zero-trust agent negotiation protocol for the open web

Execution-control runtime for AI agents: budgets, cancellation, circuit breakers, and observability—delegating heavy work to external worker CLIs.

Deploy parallel AI agent swarms for planning, implementation, and code review — a Claude Code plugin.

Reduce your OpenClaw agent costs. Free real-time LLM cost tracking + dashboard. Installs in 60 seconds.

Lightweight TUI dashboard for Claude Code token usage, agent sessions, and system resources. Go.

Virtual MasterCards for AI agents - pay with USDC via x402 on Stellar

AI Swarm Agent Launcher - A powerful CLI tool for launching and coordinating AI agents with specialized personas using git worktrees

claude-devkit - an agentic coding framework

Analysis that sees what you don't. 7 cognitive lenses + solution engineering for Claude Code.

Battle-tested skills for AI agents that do real work

Self hosted secure gateway for AI agents. One token. Full control. Complete audit trail.

基于 Expo + React Native 构建的现代化、纯净、无广告的跨平台传统文化工具。应用致力于将传统国学与现代化的移动前端技术和人工智能分析系统相结合。

Maven Lightning Lesson on Product Thinking for Agentic Development - Specflow framework, patterns, and live tnyOffice demo

Generate AI context for your dev stack — works with Claude Code, Cursor, Windsurf, GitHub Copilot, Gemini CLI, or any LLM.

⚙️ Enable AI agents to conduct autonomous penetration testing on any Linux distribution with a persistent and robust Model Context Protocol server.

A curated list of awesome Pinecone resources, libraries, tools and applications

Orchestrate a full feature lifecycle with human-in-the-loop gates across all SpecKit phases

AI Council is a self-hosted web app that runs a structured multi-model deliberation process

Real-time guardrail runtime for AI agents.

Declarative firewall for OpenClaw tool calls.

SANCTIS is a cognitive architecture that gives LLMs structured tools to organize their own reasoning, maintain long-horizon coherence, and reduce drift. It installs stable thinking patterns that emerge more powerfully the longer the model runs.

Architecture Deep Research: deep research for strategic system design decisions.

Launch, watch, and command your Cursor agents from one terminal

Mainnet-first Tempo MPP automation starter with workflow orchestration, spend caps, and provider safety controls.

AgentOrchestrator - Multi-agent development coordination platform. Transform AI assistants into sophisticated project planners that orchestrate teams of specialized agents for complex development workflows.

This is a fork from Ryan Carson's AI Dev Tasks repository, with some code cleanup and refactoring to enable support for PostgreSQL databases.

Save your tokens!

The high quality agentic ai Solana harness ✨ like openclaw 🦞 but specialized for Solana 👽 make trading bots, launch bots, build strategies, trade prediction markets and do research. Made with bun, solana/kit 6, Svelte, Helius, and more. Very gud tek 🤌🏼

Searchable Markdown KB built for AI workflows. Hybrid search, typed relations, wiki links, graph views. Token-efficient CLI for agents, static publishing for humans.

Validate your remarkable idea with Claude Skill. 用 AI Skill 验证你的好想法

end-to-end fullstack and real-time discord clone, all with servers, channels, video calls, audio calls, editing and deleting messages as well as member roles.

Traditional operating systems are reactive - they wait for user input or system events before taking action. SwarmOS breaks this paradigm by implementing distributed artificial intelligence that constantly learns, predicts, and optimizes system behavior.

Structures and algorithms for Multi-Agent PathFinding in Julia

Community Regularization of Visually Grounded Dialog https://arxiv.org/abs/1808.04359

The kernel layer for production AI agents

Xaibo is a modular agent framework designed for building flexible AI systems with clean protocol-based interfaces.

Make Agent CLI is a powerful command-line tool designed to streamline the management and deployment of AI agents across multiple chains. This tool simplifies the process of making your AI agents discoverable and registering them as plugins.

This repository demonstrates a variety of **MCP Poisoning Attacks** affecting real-world AI agent workflows.

MCP server that execute applescript giving you full control of your Mac

An autonomous AI agent orchestrator that coordinates an entire software company within OpenCode

The Digital Workers OS

Branch-Thinking MCP Tool A TypeScript-powered MCP server for managing parallel branches of thought, semantic cross-references, and persistent tasks. Features dynamic scoring, AI-generated insights, batch operations, and visual graph navigation for advanced agentic workflows.

Safety proxy for your AI Agents

Using AI Agents for Audit SBOMs for OSS Compliance

semantic grep

Convert LinkedIn data exports to clean Markdown for LLM analysis & PDF resume generation. Zero-dependency Python CLI tool for AI career intelligence.

One CLI. Every debugger. Give your AI agent eyes into runtime state instead of guessing from source code.