Custom agents

Computer use for the Pi coding agent — Windows apps, browsers and desktops through native UI trees, screenshots and real input.

Self-evolving AI workspace — it rewrites its own UI, tools, skills and plugins while it runs, live on screen. Local-first, one Go binary, no API key needed to try.

Build an LLM agent from scratch and continuously evolve it.

A transit map of parallel AI agent work: threads and records on a canvas, a git-style branch graph and a timeline. Claude Code hooks, MCP server and skill; no dependencies.

JARVIS — assistente de IA estilo Homem de Ferro. Frontend 3D (Three.js), backend FastAPI, memória persistente, TTS, tool calling.

An ML-powered framework for detecting and counteracting sycophantic spiraling in AI chatbots.

Swarm Intelligence Prediction Engine - Multi-agent AI debate for calibrated forecasting

Claude Code agent that routes to external LLMs (Grok, Gemini, GPT-5, etc.) via OpenRouter - just mention the model name

An AI Assistant on your terminal

💻 The website and an online client for Olivia

simple web-based chatbot application powered by POE (WIP)

Turn your home router into a universal device control hub. Auto-discover, identify, and control everything on your LAN.

Turn Any Browser Action & Data Extraction into an AI Tool in 60 Seconds

最简单的 OpenClaw 入门手册：从零到接飞书/Telegram/WhatsApp、改人设、多 Agent 实践，零基础可读。

Swaps/Mutes active audio input device in OBS upon a specified channel point redemption in Twitch chat.

Messenger webhook implementation in java with jetty, contracts of facebook messenger webhook

A convenient framework for developing LLM- and LMM-based web agents. (ACL'24 Demo)

Provides LLM with the ability to interact with an Android applications and perform high-level tasks

Generate story with LLM, Generative Agents (Arxiv. 2304.03442) and other technologies. A full stack monorepo.

Multi-agent Pose-Graph Sensor Fusion - from "Multi-robot Coordination with Agent-Server Architecture for Autonomous Navigation in Partially Unknown Environments", IROS 2020

CMake functions for adding NuGet package dependencies with CMake exports or native .targets files, generating and merging .nuspec files, calling nuget pack, and more. WIP.

one more tool to change the timer resolution in the context of the calling process

Short fine tuning demo with custom dataset for training gemma2-2b-it to perform function calling

A light framework for building agentic tools.

Production-ready personal AI agent runtime in Go with WebUI, multi-agent orchestration, memory, audit, and distributed node support.

Experimental OpenCode-first orchestration plugin inspired by the Tang Dynasty's Three Departments and Six Ministries: draft, review, dispatch, execute, and audit.

Build and deploy AI Agents, fast.

The building blocks of an enterprise adoption framework for agentic coding — technical training, adoption playbooks, governance policies, industry analysis, proposal templates, and practical workflows. From understanding how AI agents work to rolling them out across teams. Built for leaders driving adoption.

Deterministic & Blazing-Fast Skills Manager for AI Agents (Claude Code, Cursor, Codex & More).

A lightweight, type-safe workflow engine for TypeScript that helps you create flexible, graph-based execution flows

Python framework for building agents using claude-code-sdk with programmable tools

Customer support AI Agent

A calm reliability layer for AI agents: thoughtful execution, clear safety boundaries, reusable memory, and one-click installation.

Task Manager and Kanban Board for OpenClaw Agents

Dria SDK is for building and executing synthetic data generation pipelines on Dria Knowledge Network.

Multi-Agent Distributed Adaptive Resource Allocation

SourceWizard - Setup Wizard for devtools and libraries.

Dify DSL collection收集Dify工作流文件DSL，这里很多文件并不是本人原创，而是收集而来，感谢原作者。目前我是初学github，后面会加入大量原创内容

Production blueprint for building SaaS with Claude: prompts, theme system templates, and the workflow that prevents looping. Distilled from a 3-month real-world build.

FBbot - Facebook Messenger bot framework for Humans, for Go

A scalable, customisable yet simple chatbot built entirely from scratch in C++. The chatbot's domain of expertise can be completely chosen by you. Now, with plugins!

A voice-to-voice conversation with ChatGPT. Support for talking through a NAO robot

Generative chatbot using seq2seq

Minette is a minimal and extensible chatbot framework.

Football chat bot build with NestJS framework

CollabChatbot is a cutting-edge, open-source project designed to revolutionize how organizations access employee information and foster team collaboration. This beta version introduces a suite of powerful features, including instant personal details, real-time occupancy updates, skill identification, and smart team-building recommendations

基于语义理解、知识图谱的聊天机器人

Sample chatbot with rasa stack

Threema messaging from Go

🤖 An artificial intelligence chatbot able to learn. Made with html, css, javascript and firebase. 🤖

RAG-Buddy: Decrease cost and lower latency for LLM apps

Natural Language Querying using RAG LLMs with Excel Sheets as the context

A python module library that simplifies RAG through abstraction

Using KAG and RAG Approaches to Enhance an AI-Powered Cryptocurrency Trading Agent

Let's RAG it RAW without fancy frameworks

An app that shows you how to build a conversation search experience, using Typesense's built-in RAG pipeline

Demo implementation for 《Large Language Model Enhanced Multi-Agent Systems for 6G Communications》

LLM Agent framework with Stateful Tools.

Code for our paper: "Exploring Design of Multi-Agent LLM Dialogues for Research Ideation", SIGDIAL2025

LLM retrieval augmented generation agent for the Monarch Knowledge graph.

LLM powered AI multi agent platform that coordinate global to individual health through scaling each layer of healthcare

Deep SRE Agent is a cutting-edge intelligent SRE (Site Reliability Engineering) experimental platform designed to explore the application of LLMs (Large Language Models) in the field of SRE.

This repository serves as an example showcasing a structured approach for collaborating with AI agents (like GitHub Copilot Chat or similar LLM-based assistants) during software development.

LLM-powered macOS automation agent. Control Mail, Calendar, Reminders via natural language using AppleScript. Telegram voice commands, browser automation, and 100+ LLM providers.

一个面向企业场景的 AIOps 智能体系统，基于大模型（LLM）构建，融合 RAG（Milvus）与 MCP 工具调用，实现知识问答、信息检索与智能运维能力

Modular framework for autonomous AI agents that interact with blockchain protocols, execute transactions, and coordinate multi-agent workflows. Supports EVM (Base, Ethereum L2s) and Solana.

Multi-Agent Deep Reinforcement Learning for Cooperative and Competitive Autonomous Vehicles

[Science Advances 2026] Bridging Electron Microscopy and Materials Analysis with an Autonomous Agentic Platform

🤖 An autonomous AI agent system that collaboratively designs, implements, and manages Apache Airflow DAGs through natural language interaction.

Heuristic Search vs. Learning. "Distributed Heuristic Multi-Agent Path Finding with Communication" reproduced, trained & benchmarked with M*

[IROS2021] Human-Inspired Multi-Agent Navigation using Knowledge Distillation

Multi Agent Ecology Modelling

example of a multi-agent-a2a

Multi-agent AI Teaching Assistant Learns from Limited Data

CityLearn Challenge Multi-Agent Reinforcement Learning for Intelligent Energy Management, 2020, PikaPika team

Multi-agent deep research for Claude Code — 7-phase pipeline with source triangulation and quality ratings

Production-ready TypeScript SDK for MCP servers: auth, multi-tenant, observability. Build enterprise AI agents fast.

This repository represents an implementation of suggested distributed control algorithm for formation control of multi-agent system with distrubance compensation.

MATEval is the first multi-agent framework simulating human collaborative discussion for open-ended text evaluation.

[AAAI 2025] CoPEFT: Fast Adaptation Framework for Multi-Agent Collaborative Perception with Parameter-Efficient Fine-Tuning

The sourcemap of claude code, the best coding agent of the world

Agent SKILL for Claude Code and Opencode and others.

A beautiful native macOS app to manage skills for 25+ AI coding agents including Cursor, Claude Code, and Windsurf.

Run `npm i -g socrate` to install a discussion room for using GPT personalities with internal monologues to debate problems. Provide a problem to start, or customize the settings of the debate room. Custom agents incoming!

Opossum is a tool to pre-process RNA-seq reads prior to variant calling.

Ollama function calling demo

Calling Go functions from Erlang

A chatbot (also known as a talkbot, chatterbot, Bot, IM bot, interactive agent, or Artificial Conversational Entity)The classic historic early chatbots are ELIZA (1966) and PARRY (1972).More recent notable programs include A.L.I.C.E., Jabberwacky and D.U.D.E (Agence Nationale de la Recherche and CNRS 2006). While ELIZA and PARRY were used exclusively to simulate typed conversation, many chatbots now include functional features such as games and web searching abilities. In 1984, a book called The Policeman's Beard is Half Constructed was published, allegedly written by the chatbot Racter (though the program as released would not have been capable of doing so). One pertinent field of AI research is natural language processing. Usually, weak AI fields employ specialized software or programming languages created specifically for the narrow function required. For example, A.L.I.C.E. uses a markup language called AIML, which is specific to its function as a conversational agent, and has since been adopted by various other developers of, so called, Alicebots. Nevertheless, A.L.I.C.E. is still purely based on pattern matching techniques without any reasoning capabilities, the same technique ELIZA was using back in 1966. This is not strong AI, which would require sapience and logical reasoning abilities. Jabberwacky learns new responses and context based on real-time user interactions, rather than being driven from a static database. Some more recent chatbots also combine real-time learning with evolutionary algorithms that optimise their ability to communicate based on each conversation held. Still, there is currently no general purpose conversational artificial intelligence, and some software developers focus on the practical aspect, information retrieval. Chatbot competitions focus on the Turing test or more specific goals. Two such annual contests are the Loebner Prize and The Chatterbox Challenge (offline since 2015, materials can still be found from web archives).

Lightweight library demonstrating how to create agenting application without using any specific framework.

PULSE Framework: CLI (pulse) + MCP Server (pulse_*) for controlled agentic development. Features 30-min rule, 5 safeguards, loop detection, Git checkpoints, and escalation workflows.

A collection of particularly difficult test scenarios for evaluating browser-use.

AI agent skills for workflow automation — Feishu integration, content generation, data processing, and media tools by UniqueClub

🦞 Web UI for browsing OpenClaw session tool call history. Zero dependencies, just Node.js.

Python MCP Server for Kestra — you can use it as a tool in Kestra's AI Agents

A unified open format for agent-ready projects across tools, teams, and platforms.

A structure-first agent skill for readable, composable code.

MPhil DiS and MPhil Economics and Data Science - Research Computing and Software Development

Vision-first AI agent for desktop automation. Fully offline. Powered by YOLO, OCR & ResNet — building towards local intelligence.

Building an Intelligent AWS Cloud Engineer Agent with Strands Agents SDK