Custom agents

A native PC port of GoldenEye 007 (N64) and a testbed for multi-agent AI porting a large decompiled C codebase.

A curated collection of papers, research blogs, open-source tools, benchmarks, and community demos for robot-use agents, including demos powered by GPT-6 Astra. —— Explore our searchable website.

Deterministic code-graph context engine for AI coding agents - PostgreSQL + Apache AGE + pgvector, MCP & REST, no LLM in the loop.

🐋 Полный гайд на русском: как установить и запустить DeepSeek локально (V4, R1) на ПК, Mac и сервере — Ollama, llama.cpp, LM Studio, vLLM, Open WebUI, API, RAG, агенты, fine-tuning, лучшие фишки

An open-source engineering governance standard defining trust boundaries for conversational AI agents in high-stakes domains. MIT Licensed.

Code for the paper: "Large Language Models as Corporate Lobbyists" (2023).

probabilistic multi-agent trip simulation with physically realistic GPS modeling

Codes accompanying the paper "ROMA: Multi-Agent Reinforcement Learning with Emergent Roles" (ICML 2020 https://arxiv.org/abs/2003.08039)

One folder. Every session knows where you left off. — An open-source methodology for AI-assisted projects.

Code release for our NeurIPS 2024 Spotlight paper "GenArtist: Multimodal LLM as an Agent for Unified Image Generation and Editing"

Resources for our paper: "EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms"

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.

An AI companion that lives on your desktop - OpenGuider watches your screen, listens to your voice, and guides every step with clear actions.

Job search Agent (AI) searches and applies to jobs on your behalf, creating tailored applications for positions that match your skills, making your entire job search hassle-free.

⚡ TubeCLI — The Ultimate Open Source AI Agents Ecosystem | Agents Browser · Agents Workflow · Agents Studio World

Local knowledge graph for AI agents. Hybrid search + MCP server for Obsidian vaults.

Drop-in scientific plotting skill for Claude Code, Codex, Cursor, and other coding agents.

A curated list of awesome things related to the WebMCP W3C standard

Skills, prompts, and instructions for building AI agents on top of Dynatrace production context

OpenSRE — the memory-first AI SRE. Self-hosted incident investigation with episodic memory, knowledge graph, web console, Slack & Teams. opensre.in

Make AI output sound human. Strips AI-isms (sycophancy, stock vocab, hedging stacks, em-dash pileups), preserves code/URLs/headings. Plugin for Claude Code, Cursor, Windsurf, Codex, Cline, Copilot, Gemini.

Turn your local Claude Code / Codex CLI history into a shareable, anonymized AI-Native developer profile + viral SVG poster. A skill, not a script — 100% local & read-only.

Durable, file-based long-term memory for AI agents. Five-package plugin family: SDK, CLI, MCP server, Hermes adapter, and a LangGraph BaseStore. No vector database, no embeddings.

Handling 10M+ docs using RAG with zero hallucinatons

Lighting the path for every math modeling student. An end-to-end multi-agent LangGraph pipeline that turns competition problems into complete papers.

🪼 Lagune AI is your security copilot as you build, your Blue Team when you audit, whether you're a developer or not (no API key needed).

A repository that ships its own code. AI workflows triage issues, implement them, review, and auto-merge with no human reading the diff. Runs on Archon. The app it maintains is a cited RAG chat over YouTube transcripts, live at chat.dynamous.ai.

Arrest is a small utility to easily structure and validate your REST api calls using pydantic and httpx

Build automated workflows, apps, and AI agents with WOML

JobAppAgent: open-source AI job application agent (Agent Skill + CLI). Searches wide, matches one verified résumé, applies within your rules on Greenhouse, Ashby and Lever, tracks confirmed submissions.

A local-first workspace for documents, tasks and meetings on macOS — nested spaces, typed properties, relations and saved views, with transcription, Smart Minutes and an agent running entirely on-device via MLX on Apple Silicon

多智能体深度研究系统，融合私有知识图谱(GraphRAG)与联网搜索，含 Harness 编排、持久化 Memory 与受控自进化 Skills，FastAPI + React 全栈。

Full-lifecycle wiring between Claude Code and the Clawd on Desk pet — all 15 hook events, with permission prompts answered straight from the desktop

Pass the baton from Claude Code or Codex to a local DeepSeek Harness. An MCP server that hands off tasks and brings the result back.

Fewer Tokens, Better Action: GPT-6 Astra Robot Agents with 14% Higher Success but 65% Fewer Tokens

Set up your web app first. Then build it with AI.

DeepTrans Studio is a multi-agent intelligent translation platform for professional localization teams. It unifies a translation IDE, terminology and translation memory, AI‑assisted quality evaluation, and workflow automation, delivering end‑to‑end project management from document parsing and segment editing to collaboration and final delivery.

Shared Memory That Never Forgets — persistent memory for AI agents with Space-based sharing across agents and teams. Plugins for OpenCode, Claude Code, OpenClaw, MCP Server.

Conversational AI tooling & personas built on Cohere's LLMs

pgSCV is a multi-purpose monitoring agent and metrics exporter

Lookerbot lets you access all your Looker data from Slack! Super fun!

Collection of useful Claude AI skills and commands

switch2ai - A JetBrains IDE plugin enabling seamless collaboration between JetBrains IDEs and various AI agents (Cursor, Qoder, Claude code etc.). Key features include instant switching between different AI editors, rapid AI prompt input with AI selection, and fully custom commands with variable support for enhanced AI collaboration workflow.

基于ReAct手搓一个Agent Demo

Most complete C# .Net SDK for Google Generative AI and Vertex AI (Google Gemini), featuring function calling, easiest JSON Mode, multi-modal live streaming, chat sessions, and more!

A banchmark list for evaluation of large language models.

[ICML-25] AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML

CLI tool for Zalo automation — multi-account, proxy support, bank transfers, QR payments

Cover your Mac's screen with a hotkey while AI agents keep running, even with the lid closed. The covered screen glows when Claude Code, Codex or Gemini needs you. Touch ID unlock.

AI Agent Skill for automated vlog editing. Feed raw footage, get a finished video. Powered by ffmpeg + Whisper + Vision API.

Local MCP server for stateful, fail-closed Logic Pro control and live project readback.

Agentic Voice Notes for iPhone and macOS - Rust, Dioxus, LanceDB + RIG + SQLite

Harness engineering applied to knowledge production: a self-evolving multi-agent newsroom that turns your documents into a cross-linked markdown wiki. A "reground" loop pulls published pages back in before they go stale — writer ≠ reviewer, local-first, a structured alternative to RAG.

Universal, model-agnostic operating harness for AI agents (Claude, Codex, Gemini, …) — a lean core + work-type profiles assembled by one setup script.

免费接入 GPT4 , DALL-E3 API , 还提供 Google&Bing 搜索 , BiliBili搜索 等众多插件

An Enterprise-Grade Full-Stack RBAC Permission Management System Built with Go + React

Markdown Editor Pro — A powerful, feature-rich markdown editor with live preview, LaTeX math support, GitHub-inspired styling, and seamless integration into React apps. Built with React, TypeScript, and Tailwind CSS.

OpenFlow — a visual builder for multi-agent AI workflows, built on the opencode engine

A local, Git-native review + feedback layer for existing LaTeX projects.

A fast browser agent: Jev picks each action from what is on the page, an LLM reads and plans, and every claim in an answer cites a quote from the page.

Where you direct your coding agents: start a job with a chat, watch them work in sandboxes, and approve what matters with the evidence.

First-class Linux packaging for DeepSeek Harness desktop — AppImage, .deb, .tar.gz for x64/arm64, built by native CI.

Agent Skill: realistic handwriting with the Inko API — solve & hand-write homework, write on your own notebook paper, phone-photo looks, PDF. For Claude Code, Codex, Cursor, Copilot, Gemini CLI, OpenCode.

把上課教材變成 iPad 上好讀、可手寫的深色講義｜Agent Skill for Claude & Codex

AI Experiments A public repository of AI/ML projects exploring generative models, NLP, computer vision, and autonomous agents. Includes code, documentation, and demos for educational purposes.

Evaluation tools for Retrieval-augmented Generation (RAG) methods.

Cute voice assistant built on ESP32 to help users with reminders, productivity, and daily conversations.

企业级AI助手规则体系 - 基于agent-rules优化扩展，专为中国开发者打造，支持Augment、Cursor、Claude Code、Trae AI等主流AI工具的一键安装和配置

Tools and templates for building generative UI applications. Mobile-first, optimized for Expo.

This repository contains an implementation of a UAV-based task offloading model using the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) reinforcement learning algorithm.

A secure, local RAG journal that understands you better the more you write.

Pre-configured agent skills for Vibe Coded projects. These skills provide AI coding assistants (Claude Code, Cursor, etc.) with specific guidelines for code quality and design standards.

Multi-agent investment team powered by Agno and Gemini — 7 AI analysts collaborate across 5 architectures to deploy a $10M equity portfolio

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

Payload Skills to assist AI agents

SaaS boilerplate/starter-kit in Go+React with Stripe integration, multi-tenant support, comprehensive features and AI-agent ready

The open source runtime that turns your APIs AI-Native, without rebuilding them

Rust port of the pi agent harness — coding agent + LLM runtime stack

AI-powered MCP penetration testing framework combining HexStrike's 150+ security tools with BOAZ's advanced payload evasion (77+ loaders, 12 encoders). Features 12+ autonomous AI agents for bug bounty, CTF, CVE intelligence, exploit generation, and red team operations.

High-performance Google Drive CLI and Model Context Protocol (MCP) Server for LLM/AI agents. Natively execute Google Apps Script (GAS) under a secure whitelisted runtime sandbox, automate transfers, and manage Drive infrastructure.

Claude Code skill: turn a Zillow listing into a cinematic room-by-room walkthrough video (Apify → Higgsfield → ffmpeg). Built to sell to real estate agents.

AI assistant in Telegram that remembers everything and helps you run your life. Self-hosted in one command.

Continual agent skill evolution through persistent decision history. Whole-skill optimisation (SKILL.md + scripts + references) with every decision landing as a local Git issue / PR / wiki. Runs on any agentskills.io runtime — Claude Code, Codex, OpenClaw, Hermes.

This is a fork of the https://dockbox.dev project I made

Python toolkit for PowerPoint ↔ HTML, built for AI. Round-trip fidelity preserves formatting across every edit loop — ideal for RAG ingestion, LLM agents, and AI-assisted slide editing.

MerchantBench is a 365-day, order-level benchmark for evaluating the long-term coherence of LLM agents in seller-side e-commerce operations.

A swarm of autonomous AI minds, unified and steered by a single consciousness - the Veil. Runs on any language model.

Autonomous AI Driven OSINT & security-research desktop agent (macOS/Windows) that builds a live knowledge graph. Authorized use only

An autonomous AI agentic harness built to code anything, automate terminals, perform cybersecurity tasks, and execute complex real-world workflows with minimal human intervention. From writing and debugging code to analyzing systems, managing files, running commands, and orchestrating tools, Agent-2 turns simple prompts into autonomous execution.

面向 Codex、Claude Code 等 AI Agent 的医学绘图 Skill，基于可信证据制作医学插画、科普漫画与科研示意图，提供可编辑成果与审核记录。 · Evidence-backed medical illustration, comics and research figures for Codex, Claude Code and other AI agents, with editable output and review records.

Claude Code agent skills for game dev in Blender. Turn concept art into rigged, game-ready 3D assets, measured against your references.

从 Vibe Coding 到 Vibe World：AI原生的可编程三维世界，面向元宇宙、Science、世界模型的开源底座

Local-first AI agent for Chrome: browser automation, web research, and data extraction with your own model.

Agent Speed — A lightweight, real-time token speed monitor for Codex and Claude Code. Track tokens per second (TPS), detect slowdowns, and monitor AI agent performance at a glance.

Official Code for "Can Language Beat Numerical Regression? Language-Based Multimodal Trajectory Prediction (CVPR 2024)" and "Social Reasoning-Aware Trajectory Prediction via Multimodal Language Model (TPAMI)"

Multi-agent Combat Arena (UAV swarm vs UAV swarm)

Code for our paper: Scalable Multi-Agent Reinforcement Learning through Intelligent Information Aggregation

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

🤖 Taskade MCP · Official MCP server and OpenAPI to MCP codegen. Build AI agent tools from any OpenAPI API and connect to Claude, Cursor, and more.

Rails MCP server: stop AI coding agents from guessing your app. A Ruby gem with 35 read-only tools that give Claude Code, Cursor, GitHub Copilot, OpenCode and Codex CLI your real schema, models, routes, controllers and views. MCP or CLI, Gemfile or standalone, and it still answers when the app can't boot.