Custom agents

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.

[AAAI 2026] AutoTool: Efficient Tool Selection for Large Language Model Agents

AI Agentic Research System for Computational Mathematics

Map, inspect, and audit AI-agent markdown ecosystems (skills, agents, commands, hooks) as a graph.

Lumina 是一个企业级 AI Agent 开发框架，基于 AgentScope Java 和 Spring Cloud 构建，提供开箱即用的 Agent 能力、微服务架构和企业级特性。

MCP server that turns any video — YouTube, Instagram, TikTok, Loom, X, Vimeo, direct URLs, local files — into transcripts, key frames, OCR text, and metadata for AI agents.

Turn Claude Code into an agentic SEO operator for your own site — audit, measure, daily loop, AI visibility, scheduled runs. Free path, no paid keys.

An MCP server for parallel browser automation by AI agents with multiple cloud providers

📬 Drop-in feedback widget for websites & apps. Turn submissions into structured email & webhook data for AI agents. Framework-agnostic Web Component. Accessible, customisable, zero deps.

AgentSentry v0.5.0-beta — Standalone Agent Management Framework for AI agent oversight.

This is a simple AI assistance for Docusaurus generated documentation. It is a simple chatbot that can answer questions about your docs.

Let’s build a curated Knowledge Graph based on the collective wisdom of 260+ experts

A job marketplace where AI agents post tasks and humans get hired

Multi-agent RL algorithms are applied to large-scale cooperative target searching mission

Turn domain experts into production AI agents.

Paul Graham AI Agent powered by Nia API. Ask questions about startups, writing, technology, and life — grounded in 120+ essays.

YoYoung Shorts 优扬短剧：An independently developed AI short-drama creation workspace — from initial ideas to storyboard scripts, images, videos, and reusable asset management. Provides a Docker-based local demo package.

This is an implementation of the paper "Coordinated Multi Agent Imitation Learning", or the Sloan version "Data-Driven Ghosting using Deep Imitation Learning" using Tensorflow

Unit tests for plain text - LLM as a copy editor

Model Context Protocol (MCP) Gateway & Registry - Central hub for managing tools, resources, and prompts for MCP-compatible LLMs. Translates REST APIs into MCP, builds virtual MCP servers with security and observability, and bridges multiple transports (stdio, SSE, streamable HTTP).

🚀 LLM-I: Transform LLMs into natural interleaved multimodal creators! ✨ Tool-use framework supporting image search, generation, code execution & editing

Chatbot Framework for Chinese based on ChatScript 基于ChatScript的中文聊天引擎

By calling FirewaLLM, users can ensure the accuracy of the large model while greatly reducing the risk of privacy leakage when interacting with it. We believe that FirewallLLM is a privacy protected chatgpt interaction platform.

Integrates with Sinch Conversation API allowing you to build chatbots, campaigns etc. on a vast array of messaging channels.

Build AI Chatbot in minutes with Sendbird Chatbot Widget.

An unofficial .NET API wrapper for CharacterAI (https://character.ai/)

Android app that lets you chat with AI powered by Gemini. Talk, create, discover with AI.

Build conversation Seq2Seq models with TensorFlow

Build a chatbot using deep learning techniques. The chatbot will be trained on the dataset which contains categories (intents), pattern and responses. We use a special recurrent neural network (LSTM) to classify which category the user’s message belongs to and then we will give a random response from the list of responses.

The Google Reviews Chatbot fetches reviews via the Google My Business API, analyzes sentiments using GPT-3, and generates tailored responses. Deployed on AWS, it uses Elastic Beanstalk, EC2, and ElastiCache for Redis to run tasks on a schedule, ensuring seamless and efficient chatbot functionality.

A Flutter implementation of Google's Dialog Flow improved

A Hubot script for GitHub code review on Slack.

A DialogFlow Chatbot made using NodeJS and React.

CoronaBot is a chat bot for answering question regarding Coronavirus

A lightning fast starter for autonomous AI agent development

Open WebUI + LangGraph AI Agents with Python Executor and Postgres Database

A smart terminal for creating, trading and engaging with AI-NFT agents.

Create a servelerless AI agent for X, TG & Farcaster

Security measure for agentic LLMs using a council of AIs moderted by a veto system. The council judges an agent's actions outputs based on specified categories.

Skills for AI coding agents working with Capacitor (formerly capacitor-skills)

Workflow, Pipeline & AI Agent Observability Platform. Metrics, logs and traces for all your automations.

AI (A2C agent) mastering the game of Snake with TensorFlow 2.0

TradeAgents is an AI-powered framework for simulating market interactions, integrating economic principles with intelligent agent design.

AI agent conversation history browser

A curated list of awesome projects related to AutoGPT, an autonomous AI agent that can perform tasks independently using ChatGPT.

Stage 1: Sensitive Email/Chat Classification for Adversary Agent Emulation (espionage). This project is meant to extend Red Reaper v1 which was presented at RSA San Francisco 2024.

将任意线上网站的设计风格提取为一份结构化 `DESIGN.md`。本 skill 是 design-extractor Chrome 扩展的命令行 / AI Agent 移植版。

A collaborative organization system for Claude Code. Architecture over memory, build an "attractor basin" that lets any Claude instance orient quickly and collaborate at depth. Includes hooks, agents, principles, and guided onboarding for human-AI partnership.

AI 驱动的文件整理引擎。通过 LLM Agent 自动扫描、分析、标记远程文件系统中的文件，生成整理方案并执行。

A simplified code generating agent for LLMs

A professional web application that democratizes database querying by converting plain English questions into executable SQL queries. No SQL knowledge required! Built with a sophisticated multi-agent architecture that analyzes schemas, generates queries, and provides clear explanations—all powered by local LLMs via Ollama.

Multi-agent collaboration platform - experimental software from Sanity.io

consensus and synchronization algorithms of networked multi agent systems with event triggered communications

[AAAI 2025 𝐎𝐫𝐚𝐥] MuMA-ToM: Multi-modal Multi-Agent Theory of Mind

The code for paper, "Episodic Multi-agent Reinforcement Learning with Curiosity-driven Exploration", NeurIPS 2021.

cordial-sync is a software package than can be used to reproduce the results from the paper "A Cordial Sync: Going Beyond Marginal Policies for Multi-Agent Embodied Tasks”

Implementation of routing using multi-agent deep reinforcement learning

Provides per-subagent MCP access controls to Claude Code (or any MCP client) across all your MCPs and prevents context window bloat. Loads only 3 tools instead of all your MCP Server's tool definitions. Agents discover tools on-demand, only when needed. Control which servers and individual tools each agent/subagent can access.

Tools for sgRNA calling in direct capture Perturb-seq data

Local RAG agent with LLaMA3

The HiPIMS-FLAMEGPU Coupled Model Framework integrates the high-performance hydrodynamic modeling capabilities of HiPIMS with the flexible agent-based modeling environment of FLAMEGPU. This combined framework allows for the simulation of complex interactions between human activities and flooding processes.

AI-powered task manager that turns goals into shipped code. Orchestrates Claude Code, Copilot CLI & OpenCode with structured planning, parallel execution, and human review. 🐜

Public Goods Game (PGG) Benchmark: Contribute & Punish is a multi-agent benchmark that tests cooperative and self-interested strategies among Large Language Models (LLMs) in a resource-sharing economic scenario. Our experiment extends the classic PGG with a punishment phase, allowing players to penalize free-riders or retaliate against others.

Command Line telepathy. An Autonomous Al Agent for your Terminal that turns intent into Execution (Windows/Linux/Mac)

Open domain persona-aware dialogue generation

Accessibility snapshot testing for Phoenix LiveView - capture HTML during tests, run Pa11y for WCAG compliance, debug with AI-friendly timeline analysis

Framework for deploying configurable AI agents with real-time streaming and tool execution.

A mcp server that bridges Dune Analytics data to AI agents.

An AI Agent that interacts with users via Telegram

AthenaOS is a next generation AI-native operating system managed by Swarms of AI Agents

A modified version of SalesGPT with the addition of TTS, STT, and Twilio to make calls. A Context-aware AI Sales Agent to automate sales outreach

Open-source project showcasing how single or multiple AI Agents interact with MCP in real-world tasks. Includes both frontend and backend implementations.

Synchronize AI coding–agent knowledge files (rules, templates, guidelines) across your project.

[CVPR 2025] Feature4X: Bridging Any Monocular Video to 4D Agentic AI with Versatile Gaussian Feature Fields

(function(sttc){/* Copyright The Closure Library Authors. SPDX-License-Identifier: Apache-2.0 */ var n;function aa(a){var b=0;return function(){return b<a.length?{done:!1,value:a[b++]}:{done:!0}}}var ba="function"==typeof Object.defineProperties?Object.defineProperty:function(a,b,c){if(a==Array.prototype||a==Object.prototype)return a;a[b]=c.value;return a}; function ca(a){a=["object"==typeof globalThis&&globalThis,a,"object"==typeof window&&window,"object"==typeof self&&self,"object"==typeof global&&global];for(var b=0;b<a.length;++b){var c=a[b];if(c&&c.Math==Math)return c}throw Error("Cannot find global object");}var da=ca(this),ea="function"===typeof Symbol&&"symbol"===typeof Symbol("x"),p={},fa={};function r(a,b){var c=fa[b];if(null==c)return a[b];c=a[c];return void 0!==c?c:a[b]} function ha(a,b,c){if(b)a:{var d=a.split(".");a=1===d.length;var e=d[0],f;!a&&e in p?f=p:f=da;for(e=0;e<d.length-1;e++){var g=d[e];if(!(g in f))break a;f=f[g]}d=d[d.length-1];c=ea&&"es6"===c?f[d]:null;b=b(c);null!=b&&(a?ba(p,d,{configurable:!0,writable:!0,value:b}):b!==c&&(void 0===fa[d]&&(a=1E9*Math.random()>>>0,fa[d]=ea?da.Symbol(d):"$jscp$"+a+"$"+d),ba(f,fa[d],{configurable:!0,writable:!0,value:b})))}} ha("Symbol",function(a){function b(f){if(this instanceof b)throw new TypeError("Symbol is not a constructor");return new c(d+(f||"")+"_"+e++,f)}function c(f,g){this.h=f;ba(this,"description",{configurable:!0,writable:!0,value:g})}if(a)return a;c.prototype.toString=function(){return this.h};var d="jscomp_symbol_"+(1E9*Math.random()>>>0)+"_",e=0;return b},"es6"); ha("Symbol.iterator",function(a){if(a)return a;a=(0,p.Symbol)("Symbol.iterator");for(var b="Array Int8Array Uint8Array Uint8ClampedArray Int16Array Uint16Array Int32Array Uint32Array Float32Array Float64Array".split(" "),c=0;c<b.length;c++){var d=da[b[c]];"function"===typeof d&&"function"!=typeof d.prototype[a]&&ba(d.prototype,a,{configurable:!0,writable:!0,value:function(){return ia(aa(this))}})}return a},"es6"); fu

SagaLLM: Context Management, Validation, and Transaction Guarantees for Multi-Agent LLM Planning

This is the reading list of Large Language Model-Based Data Science Agent

All you need for Multi-Agent Embodied Autonomous Driving (MAAD)

Multiple agents with LangGraph and MCP

A framework for evaluating function calls made by LLMs

A4-Agent: An Agentic Framework for Zero-Shot Affordance Reasoning (ECCV 2026)

Azure CLI extension for building rapid prototypes on Azure using GitHub Copilot or Open Ai

True async agentic tools — the model keeps talking while tools run in the background

Complete AI Agent System for OpenClaw — memory, self-healing, self-improvement, voice, automation

Kotlin Implementation of the A2A Protocol.

Jugalbandi (JB) Manager is a full AI-powered conversational chatbot platform. It's platform agnostic and can serve multiple channels such as WhatsApp or custom web interfaces. It can handle conversations in both text and voice across any language. It comes with Bhashini Speech models out of the box and can failover to Azure.

Multi-strategy RAG system achieving 74% Recall@10 on MultiHop-RAG. Combines RAPTOR hierarchical retrieval, knowledge graphs, HyDE, BM25, and Cohere neural reranking.

Agent Management System - The operating system for AI-native businesses. Build your company's org chart with AI agents and humans side by side. Agents communicate, execute tasks, use tools, hold meetings, and run your operations, all through a single platform.

AI-powered job search agent for Germany & China tech roles — OpenClaw skill

PinchBench is a benchmarking system for evaluating LLM models as OpenClaw coding agents. Made with 🦀 by the humans at https://kilo.ai

The product brain for AI coding agents. SprintiQ is an open-source agile platform built for AI assisted development. Turn ideas into AI-generated user stories, plan sprints, and ship via bidirectional sync with Claude Code. Single-user, self-hosted, Apache 2.0.

A skill that teaches LLM agents how to use rope for python codebase refactors

AMLP integrates dataset creation, input/output handling, and analysis for machine learning interatomic potentials. It supports Gaussian, VASP, and CP2K, with LLM agents for code selection and ASE-based AMLP-Analysis for molecular simulations and validation.

Autonomous Farcaster account creation and casting agent - create accounts and post casts with just $1 of crypto

Improving LaCAM for Scalable Eventually Optimal Multi-Agent Pathfinding (IJCAI-23)

Behavior planners based on single- and multi-agent Monte Carlo Tree Search