Custom agents

Gate for AI is an AI-native crypto infrastructure that enables AI agents to trade, analyze markets, manage wallets, and query on-chain data through MCP (Model Context Protocol) and modular AI Skills. Integrate ChatGPT, Claude, and OpenClaw with CEX + DEX capabilities.

Voice dictation menu-bar app for macOS. Press a hotkey, speak, transcript appears at the cursor. Whisper runs locally via WhisperKit on Apple Silicon — no audio, text, or telemetry leaves your Mac. MIT, Swift.

Model Context Protocol (MCP) server that connects AI agents (Claude, Cursor, etc.) to Wolfram Mathematica for symbolic computation, visualization, and notebook manipulation.

Awesome list of AI Code Review agents, copilots, and research papers.

Self-orchestrating multi-agent system for Claude Code — you say WHAT, the AI decides HOW. v7.1: 15 AI agents, Smart Routing, parallel quality gates, skills architecture, plugin & one-command installer. Optimized for Claude Fable 5.

HumanizerAI Agent Skills for Claude Code and Codex - AI detection and text humanization

Rust CLI to extract relevant codebase context to clipboard with XML tagging for web AI

Kubernetes-native sandbox platform to run AI agents, coding assistants and harnesses.

🚀 DeepSeek-V4-Pro Agentic AI Automation Toolkit for Enterprise Apps 2026

Agents, Commands and Pipelines for Claude code & other harnesses

Public Claude agent skills that turn JoomPulse data into Mercado Livre seller workflows: market research, competitor tracking, product discovery. Requires JoomPulse MCP.

🎭 Battle-tested plugins for Hermes Agent — zero core patches. Native vision bypass, multi-agent context injection, and more.

GAIA Code - Most powerful Perplexity Assistant for any software development. Agentic coding capabilities like Claude Code.

🤖 Agent skills for interacting with Capawesome, Capacitor and the Ionic Framework.

Capka AI — An open-source, self-hosted sandbox for AI agents. A community-driven alternative to Claude's Cowork

The Ultimate AI Compute Gateway ( Router ) | A high-performance, stateless-to-stateful LLM compute gateway in Go. Features multi-model pooling, zero-dependency local RAG with muti-users support, session memory stack injection, and cascading optimal routing for Morden Agent compatible endpoints.

Run DeepSeek as a real sub-agent inside Claude Code / Codex CLI — with its own 7-tool agent loop, workspace-scoped file access, and bounded Bash.

An enterprise-grade implementation of multi-agent systems using OllamaJS, featuring advanced orchestration, dynamic agent allocation, and seamless integration capabilities.

An agent that edits your Word and Excel files — then looks at them, through real Microsoft Office, to check its own work

An autonomous AI agent written in Go, designed to run entirely on the 32MB RAM of an obsolete OpenWrt router. It acts as an always-on smart home orchestrator with Wake-on-LAN, Telegram, and Google Workspace integration.

Independent policy kernel for AI agents: judge before execute. F1–F13 floors, VAULT999 receipts. Not a model. Not a chatbot.

Sample skills and prompt patterns demonstrating how to use the Azure DevOps MCP Server with GitHub Copilot and agent-based workflows

Claude Code plugin for autonomous AI research — multi-agent loops take a bare topic all the way to running experiments, with no human-written experimental code.

Local-first, evidence-controlled academic writing workflows for AI agents, with bounded revision, clean-room review, and release governance.

The bridge for remote MCP — seamless OAuth, resilient auth recovery, production-grade reliability

MCP server for Cosense (Scrapbox) — read, search, create, and edit wiki pages from Claude and other AI agents. Also works as a CLI and Claude Code plugin.

Private local AI Photographer Agent on AMD Radeon and ROCm

A free, open-source coding agent inside VS Code.

Curated list of open-source AI-assisted penetration testing tools, frameworks, CTF agents, and benchmarks

Procedural writing-style skills for AI agents: official frameworks (plain language, business writing, GOV.UK, AP style, STE-100, developer docs) + character voices. Agent Plugins 1.0.0, works in opencode, Claude Code, Codex.

A desktop workspace (inspired by Grok Bot & Muse) for AI agents that collaborate, write code, and use tools. Run locally or on your own server, with shared conversations, persistent memory, and MCP plugins.

🔐 密钥管理 / 秘钥管理 / 令牌管理 / Token 管理 / API Key 管理 CLI — Local-first 的 Secret Manager 与 Secret Management：API Key Manager、Token Manager、Credentials 凭证库，dotenv / .env 替代 (dotenv alternative)。AES-256-GCM 加密存储，ky run 把凭证注入子进程、避免明文进入模型上下文。

蒸留蔵 — distilled long-term memory for agents: recall by meaning, writing gated by evidence, one kura per agent mode. Ships as a DeepSeek Harness plugin and an MCP server.

0.6.0 comming soon! Context-efficient, correctness-first ripgrep search and bounded code inspection for Pi, with adaptive context budgets, stable cursor snapshots, safe grep interoperability, and localized controls.

Grok Bot 0.18.0 runtime code archive — unminified bundles, mechanical per-module split, byte-for-byte reproducible

MemXT is a Local long-term memory for Claude Code & coding agents. 100% local

Local-first workbench for Claude Code, Codex, OpenCode, Pi Agent, Grok Build and Antigravity on Windows, macOS and Linux. Control terminals through MCP, resume native sessions, preview files and reconnect from your phone.

AI 执行与监察体系（Agent Oversight Framework）：分层治理规范 + L2 运行时监察参照实现——证据分级、自校正、边界诚实。A layered governance spec for AI agents, plus a runnable reference implementation of the L2 runtime-oversight layer. Docs CC BY-SA 4.0 / code Apache-2.0.

The DeepSeek and OpenRouter Harness built on Elixir

Dextra targets **DeFi, NFT, and general Solana workflows** by pairing large language models with **function calling** and **Solana Agent Kit**–style tooling. Authentication and embedded wallets are handled via **Privy**; chain reads and enhanced RPC flows use **Helius** where configured.

Open-source autonomous AI browser agent Chrome extension running locally in your authenticated browser. Researches web data, fills forms, automates workflows, and streams live results using active logins.

Cubicle: a live pixel-art office for your AI agents (Paperclip, Claude Code, Codex, Gemini CLI). See who works, who needs you, who failed; KPI board, Telegram alerts, HD themes. Zero dependencies, read-only.

Agentic Development Lifecycle

NOW you can let AI agents make code changes without losing engineering control.

Agent 应用学习与实战仓库：ReAct 运行时、工具调用与审批预算、RAG 分块检索入库、MCP 主机与示例；pnpm 多包（core / providers / tools / runtime / cli）可独立安装使用。

Xylocopa is a visual orchestrator that runs your Claude Code agents in a more organized way.

Desktop app built on Claude Code harness for proactive engineers.

A database-agnostic Agentic GraphRAG framework using swappable System One models (local Laya / cloud Jev). A plug-and-play intelligence layer featuring a complete 4-phase pipeline, continuous evaluation and custom A* traversal for any graph database.

Talk to your computer: dictation into any app, a voice assistant that answers out loud and gets things done, meeting notes, and a phone app to control your PC. Local-first, open source.

AI 自主渗透测试 · 红队作战平台 | 多 Agent 自主推进 · 漏洞情报运营 · 后渗透与 C2 | LLM 三通道轮询 | 全程证据留痕 | 原百度攻防赛冠军项目独立演进版

Minimize AI and Agent failures into minimal reproducible traces.

Discord clever chatbot powered by brainshop.ai

Submit trading order to CEX & DEX with multi messaging platform and plugin support | EST. 2022

Minimalist AutoGPT capable of updating it's own source

Fibo is a cutting-edge framework designed to build and deploy AI agents that seamlessly integrate automated task execution with interactive chat capabilities.

A fast, agnostic, and powerful Go AI framework for one-shot workflows, building autonomous agents, and working with LLM providers.

A strongly typed Python DSL for developing message passing multi agent systems

Python package that provides an agent framework that can be used to build agents that serve Sentient Chat events.

Claude Code skill that forces AI to understand before executing. Three disciplines: cognition check, requirement understanding, method search.

Long-term Research Assistants with Self-Scheduling

🤖 AI 工程师的成长手册：从基础知识到 RAG、Agent 实战，涵盖学习路径与高频面试题。

Simple and elegant component for building conversational interfaces on React.

CarikBot - Carik Chatbot Engine

Crucible turns YouTube videos into blogs, Twitter threads, and even lets you chat with the video itself.

Simple keras chat bot using seq2seq model with Flask serving web

通用大模型 × 文风大模型 = 多样化风格的聊天机器人

Download music and play on Telegram for free

Demo repo for connecting an LLM Agent to a Whatsapp webhook

Checkmate is a Spec Oracle Engine built for AI-driven development. It verifies that code changes made by autonomous agents actually deliver what your spec promised using real evidence.

Task-oriented Dialog Policy Learning with Multi-Agent Reinforcement Learning

Multi agent scalable reinforcement learning for formation control with collision avoidance

Formation control for a multi-agent system in a bidimensional space. Various types of formations available. Implementation in ROS2 Foxy.

基于 claude code sdk 的 agent api，兼容Skills + Sub Agents

Thread Dispatcher is an open source tool to pass the execution of a Delegate, Coroutine or Task from a background thread to the main thread, and await its completion or result on the calling thread as needed.

Swift implementation of BabyAGI

MCP server connecting AI assistants with Jira & Confluence for smart project management.

LINE Flex 開發人員工具

Flexible Agent Framework for building Chat Bots, AI agents, and LLM microservices on the JVM.

Autoresearch with PhD-level workflows and modular agent skills. Built for the autonomous AI Scientist.

AI multi-agent system for comprehensive Bitcoin (BTC) analysis, combining financial news, market performance, and AI-driven price predictions for investment recommendations.

A Multi-Agent Path Finding visualization website.

Privacy-first Apple Health analyzer — cross-metric insights, behavioral patterns, and health reports. Agent skill for Claude Code, Codex & Cursor.

CLI tool to encoding/decoding data to/from MessagePack format and calling RPC via msgpack-rpc / msgpack.org[Shell]

Gym environment for cooperative multi-agent reinforcement learning in heterogeneous robot teams

Dremio MCP server

A complete Retrieval-Augmented Generation (RAG) application that demonstrates modern AI capabilities for answering questions about Ultimate Frisbee rules and strategies. This project showcases how to build a production-ready RAG system using cutting-edge technologies.

Self-evolving Agents. MOLTRON upgrades agents to learn and evolve skills autonomously. Welcome to the Singularity.

Production-grade agent orchestration for Claude Code - 11 agents, 46 MCP tools, SQLite+FTS5, drift detection, consensus checkpoints

An Agent-Based Modelling (ABM) Framework for Unity3D

Official Code for "A Set of Control Points Conditioned Pedestrian Trajectory Prediction (AAAI 2023)"

LeiAI Agent 是一个基于 Spring Boot 3 和 Spring AI 构建的智能旅游助手系统，采用了 RAG 、Tool Calling 和 MCP 等先进技术，为用户提供个性化的旅游规划、信息查询和智能对话服务。

A reusable framework of agent skills that bring structure and repeatability to AI-assisted software delivery.

AI agent skill for building modern, composable, and accessible React UI components following the components.build specification

An agent fine tuned on the injective trading framework and docs

HTTPS C&C Framework with encrypted beacons, web dashboard, and Windows agent.

Reduce errors with test-driven development using Browserbase, Stagehand and Claude Code using these sub-agents and output styles

Keep your agents, skills, commands, and configurations in sync across Claude Code, Codex, Copilot, Cursor, Gemini, and OpenCode on every machine.

KGARevion: AI Agent for Knowledge-Intensive Biomedical QA

Amazon Bedrock AgentCore – Multi Framework Examples