Custom agents

Video-production toolkit for AI agents: Deno + WebGPU + three.js/TSL render engine with VRM character locomotion, simulations, effects, and a full audio pipeline — real-time GPU rendering with minimal CPU

A collection of AI agent skills and plugins for Hermes Agent — research, creative, productivity, devops, and more. Each skill is self-contained and tested.

Watch, approve and steer your coding agents from your phone.

自媒体视频发布前违规风险审核。检查画面/声音/文字/封面/评论/带货信息/资质/引流，输出 Pass→Blocker 五级风险报告。覆盖抖音/小红书/视频号/B站/快手+千川低质素材。Claude Code、codex、workbuddy、hermes skill

Aksara is a modern, developer-friendly framework and CMS built on CodeIgniter 4, featuring rapid CRUD development, modular architecture, smart routing, flexible access control, API integration, and an AI assistant to make content management faster and smarter.

一个本地优先的私人财务云(CFO Agent)：iPhone快捷指令一键记账，Web 财务大脑 + LLM 对话分析你的现金流，支持本地/云端部署。

可审计、可复现、可恢复的多 Agent 研究工作台，可产出论文初稿 + 可独立运行的研究代码仓库 + 完整实验记录（配置、种子、指标、失败日志、SHA-256 清单）。含通用版（零基础/本科毕设）和专业版（CV 多卡实验/电网控制仿真）两条独立发行线。

Self-hosted AI workspace with agents, skills, and tools (Gmail, Calendar) that runs entirely on your own provider API keys (BYOK). Bring your own keys — Groq, OpenRouter, NVIDIA, Hugging Face, Google AI.

Anyone can predict the future. Almost nobody keeps the receipt. A hash-chained prediction ledger for LLMs — sealed before the answer exists, graded with proper scoring rules.

DocWire SDK: local-first C++20 data-processing infrastructure for deterministic, auditable, on-premise workflows. Supports 100+ formats, OCR, local AI, and opt-in cloud AI pipelines

Accessibility scanner for humans and AI agents.

Develop and deploy smart contracts using natural language.

麦麦省的券谁都能领，但领了不等于楼下那家店认。一键领全后逐家门店校验哪张券真的能核销，并算出券后实付，直接回答「去哪家店、用哪张券、省多少钱」。基于麦当劳 MCP。

Engineering discipline for AI coding agents: question the request, verify against current docs, plan, build test-first on the cheapest capable model, review with a second model family, prove it before saying done. One repo for Claude Code, Codex, Antigravity, Cursor, Gemini CLI and OpenCode.

An agent orchestration framework for economic agents

Claude Sub Agent Test Generator Command

JOYA(Joy Agents) is a governance framework for teams of AI agents. It provides the rules, structure, and accountability mechanisms that let multiple agents collaborate safely under human oversight.

BotSIM - a data-efficient end-to-end Bot SIMulation toolkit for evaluation, diagnosis, and improvement of commercial chatbots

Multi-agent project (commnet, bicnet, maddpg) in pytorch for Multi-Agent Particle Environment

Groq Cloud runs LLM models fast and cheap. This is a convenience client library for Ruby.

ChatGirl is an AI ChatBot based on TensorFlow Seq2Seq Model. ChatGirl 一个基于 TensorFlow Seq2Seq 模型的聊天机器人。（包含预处理过的 twitter 英文数据集，训练，运行，工具代码，来波 Star 。）QQ群：167122861

Document AI. Extract structured data like JSON, Markdown and HTML from documents using LLMs and AI agents.

InterfaceAgent: a versatile framework designed to create system and interface agents capable of managing mobile and desktop applications and features.

Internal Q&A and knowledge base for Backstage. Empower teams to share knowledge, ask questions, and integrate AI-powered answers directly into their developer portal.

AdaSociety is a customizable multi-agent environment featuring expanding state and action spaces, alongside explicit and alterable social structures. AdaSociety is friendly to tensor-based and LLM-based methods.

ChatGPT for Bhagavad Gita i.e. GitaGPT. Now, we can talk to Krishna in our everyday lives.

A Comprehensive Library for Memory of LLM-based Agents.

Modern desktop application (Rust + Tauri v2 + Svelte 5 + Candle (HF)) for communicating with AI models that runs completely locally on your computer. No subscriptions, no data sent to the internet — just you and your personal AI assistant

Training Proactive and Personalized LLM Agents

An multi-agent design-to-code tool that generates production-ready React code with high visual fidelity and iterative validation.

Shared memory MCP server — persistent, searchable, cross-client Claude, Opencode

Claude Code多智能体编排Skill：自适应决策 + 6阶段工作流 + 5大场景 | Multi-agent orchestration skill for Claude Code

R-Judge: Benchmarking Safety Risk Awareness for LLM Agents (EMNLP Findings 2024)

Muse Studio is an Agentic AI workspace for planning, visualizing, and iterating on stories and video creation.

🪐 面向 AI 的多音乐平台的 API 代理 • 网易云 • QQ音乐 • 酷狗 • 酷我 🎻 Multi-platform music API agent for AI • NetEase • QQ Music • KuGou • Kuwo

Generate agents by simply describing your task in natural language

An "LLM wiki" upgraded to a real database — typed entities, graph relations, HTTP API, and a built-in natural-language agent.

Unified realtime agent trace database & search MCP

PhantomCrowd AI Marketing Simulator 2026: Content Spread Forecasting with Local LLM

Ultimate AI Fitness Coach PWA 2026: Iron Mike Workout & Smart Recipe Agent

ai algo trading engine of AI-driven multi strategy, multi timeframe cryptocurrency trading monitor with ai auto trading ai auto trading ai auto trading

An ongoing, collaborative meta-analysis about Human-AI-Interactions. We aggregate data and knowledge to build a non-abrasive, user-friendly prompting framework tailored to LLM mechanics, ensuring reasoning stability and a friction-free prompting environment that is safe for the human psyche and wellbeing.

Gridgeist turns product intent into a rigorous visual system—without the generic AI SaaS aftertaste.

Open-source mission control for coding agents. Run cross-vendor workers in isolated worktrees, audit every submission, and revert an entire mission.

Open-source Agentic Development Environment (ADE) for Codex, Claude Code and other agents. Run on your own Windows, macOS or Linux machines; steer sessions, review changes and test apps from any browser.

AI 编程智能体统一桌面工作台 | Desktop hub for managing Claude Code, Codex CLI, Gemini CLI & OpenCode. Tauri 2 · Rust · React · SQLite.

A recipe-driven WaaS platform for ComfyUI that turns complex workflows (Image, Audio, Video, 3D) into intuitive Gradio UIs, high-level semantic APIs, and MCP tools for LLMs & AI Agents.

A lightweight, self-hosted AI subscription pool for teams.

Official Code for the paper "Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents "

Agentic IDE for Claude Code, Codex CLI, Antigravity CLI, and Pi.dev

Send email and SMS, run flows and campaigns, and call Nitrosend MCP tools from the terminal.

Solevia · 足下：能聊清需求、规划路线、陪你执行的智能规划助手。节奏型、探索型、期限型规划，覆盖学习、生活与技术成长。

Open-source platform for AI chat agents that answer from your own knowledge base. Hybrid RAG search in PostgreSQL, MCP and custom tools, guardrails and human handoff. Put agents on a hosted chat page, a website widget, Slack, Teams, WhatsApp, Telegram or a REST API. Self-host with Docker and open-weight models.

Chatto is a minimal chatbot framework in Go.

🏰 Real-time dashboard for monitoring and managing Clawdbot AI agents

LocalChat is a ChatGPT-like chat that runs on your computer

Natural Language Data Augmentation Tool for Conversational Systems

🦞 Pre-hardened, multi-agent OpenClaw setup. One script from zero to a fully secured AI assistant on Discord, Telegram, or both.

A python library for creating AI assistants with Vectara, using Agentic RAG

An LLM-powered Slack bot for your internal knowledge, powered by tiger-agents-for-work libraries.

Hubcap is an autonomous AI agent in 25 lines of code: a small Autobot that you can't trust

🔥[CVPR2025] EventGPT: Event Stream Understanding with Multimodal Large Language Models

Zero-magic Express + React starter. Readable, hackable, and built for rapid prototyping in the era of agentic coding.

Official repo of "MMBench-GUI: Hierarchical Multi-Platform Evaluation Framework for GUI Agents". It can be used to evaluate a GUI agent with a hierarchical manner across multiple platforms, including Windows, Linux, macOS, iOS, Android and Web.

An agentic terminal UI for Claude, built for Flutter developers

[ACM MM2025] Official code of " HM-RAG: Hierarchical Multi-Agent Multimodal Retrieval Augmented Generation"

n8n-playbook: cheastsheet, examples

Code and Data for "MIRAI: Evaluating LLM Agents for Event Forecasting"

A virtual clinical environment for self‑evolving LLM diagnostic agents.

The Trading Research Framework inspired by Deerflow Multi-Agent!

Run OpenClaw AI agent with zero API cost, local LLM via AirLLM

A curated list of reinforcement learning (RL) for agents.

🤖 A Model Context Protocol (MCP) library for use with Agentic chat bots

Open-source voice agent OS. Rust runtime, AI-driven builder, sub second latency. Self-host everything.

Agents and tools for using Quint with LLMs

Data-Agent：从 0 到 1 构建 Text2SQL 智能体实战教程，覆盖 StateGraph 编排、双重 RAG、关系图谱、HITL 人工确认、SQL 自动纠错、Python Docker 沙盒执行与 A2A + SSE 流式交互。

Autonomous AI trading agent with web dashboard, MCP tools, and Go trading backend

Tu equipo de desarrolladores en un plugin. 10 agentes, 11 skills planas, 18 comandos /alfred-dev:*. Memoria persistente, quality gates con evidencia y MCP local.

GBase — Recursive Self-Improvement Agent Framework. Memory, evolution, quality gates, identity system, and 40+ auto-registered tools.

Automated Proof-of-Carrying Change Management for AIOps 2026

Autonomous AI BD Agent for SolCex Exchange: 24/7 Cross-Chain Token Scoring & Payments 2026

QozeCode 是轻量级的 命令行 AI agent，基于 LangGraph 架构构建的专业级命令行智能体（AI Agent）。它旨在将大语言模型的推理能力与终端操作环境深度融合，通过 ReAct（Reasoning and Acting）范式，实现复杂开发任务的自动化执行。

Bounded, typed, ablatable memory contract for long-horizon LLM agents — Slay the Spire 2 testbed

The harness orchestrator — a local-first kanban for running Claude Code, Codex, and other CLI coding agents in parallel, each in its own git worktree.

Extends the Hooks API, Directed Acyclic Graph Agent Execution Engine. This project is self-maintained by GPT-6.

Open-source framework for superagents.

Collection of skills giving agents guidance on design/eng concepts LLMs aren't trained on.

The document framework built for agents — write reports as React, get real A4 pages, an outline, page numbers, and a PDF.

Agent-native executable language for AI-native development: Agents build programs; humans govern verifiable semantic graphs.

🏛️ The patent plugin for AI coding agents — turn technical ideas into patent disclosures with Claude Code, Codex, and OpenCode.

ACL 2026 Code and Skills for “AMA: Adaptive Memory via Multi-Agent Collaboration”.

看看哪些麦当劳权益快到期，哪些值得用，哪些不用为了到期硬消费。基于麦当劳官方 MCP 的 WorkBuddy Skill：只读查询优惠券与积分，按预算给出最多两套经官方接口试算的用餐方案。McDonald's coupon & points expiry assistant — a WorkBuddy Skill on the official McDonald's MCP. Read-only queries, official price calculation, max 2 budget-friendly plans.

Pi.NET 是 Pi 的 .NET 10 移植版。Pi 是一个极简、可扩展的 Agent harness（TypeScript monorepo，约 17.1 万行），本项目把它的核心库逐一移植到 net10.0，让 .NET 生态用上同一套能力。

AL development toolkit for Business Central with specialist agents, skills and review workflows for Copilot, Claude Code and Codex.

(THIS IS THE PUBLIC VERSION) Muse-by-Meta usage audit companion designed for those who want to understand Muse’s actions during a multi-step task without pretending to have telemetry they can’t actually access.Check out Muse, your personal AI agent. Code: 5F2V31 https://muse.ai/join

2019语言与智能技术竞赛-基于知识图谱的主动聊天

This is an open source implementation of the Github Copilot AI Model based on reverse engineering of the VSCode and IDEA plugins.

Agentic-first Cursor Rules powered by MiniMax M2 — clarify-first prompting, interleaved thinking, and full tool orchestration for production-ready AI coding

Accurate and flexible loops calling tool for 3D genomic data.

Kieker is an observability framework, that consists of an monitoring and tracing agent, and compatible analysis tools