Custom agents

API documentation via MCP for AI coding agents

My collection of Claude Code Agents & Skills for web and iOS Development

AI-powered group finance assistant using MCP architecture, Gemini LLM and Streamlit.

A curated collection of Claude Code skills for SpoonOS development and Web3 integrations. 57 Python scripts across 19 skills: SpoonOS Skills for Vibe Coding (build agents) + Web3 Skills for Skill Agent Integrations (DeFi, NFT, DAO, Security).

Official content archive for Animoca Minds — AI agent platform by Animoca Brands

AI dev framework: 22 agents, 100 core skills + 142 addon skill packs, 149 commands. Runs on 21 AI tools: Cursor, Claude Code, Copilot, Windsurf, Cline, Aider, Roo, Kiro, OpenHands, Gemini, Codex, Goose, Warp & more. File-based memory persists across sessions.

Replayable Browser Agent

Tool-calling AI agents that run locally.

Claude Code skills for Convex backend development. Drop-in knowledge for queries, mutations, AI agents, components, and auth patterns. Community contributions welcome!

A self-hosted, secure code execution sandbox for LLM agents deployed on your cloud infrastructure using SkyPilot. Built on llm-sandbox for multi-language code execution.

Cactus AI framework plugin for UE5 to run local LLMs at runtime. https://github.com/cactus-compute/cactus

SeedX turns any idea/question into a structured, agent-evaluated mastery path with plans, exercises, checkpoints, and real-world transfer.🪴

[ICCV'21] Official implementation of the "Social NCE: Contrastive Learning of Socially-aware Motion Representations" in PyTorch, for Social-STGCNN on trajectory forecasting.

Pluto is a high-performance coordination server built on Erlang/OTP that enables safe, real-time collaboration between multiple AI agents.

Fetch.ai Carpark agent - A Raspberry Pi CCTV camera project to broadcast numbers of available car parking spaces on the Fetch.ai network

Demo with multiple AI agents using A2A (agent-to-agent) with the Strands Agents SDK.

A clean and easy implementation of MuZero, AlphaZero and Self-Play reinforcement learning algorithms for any game.

AutoGroqAgent is a Streamlit-based demo application designed to showcase the powerful new AutonomousAgent class introduced in PocketGroq v0.5.x. This demo provides a hands-on experience with the advanced capabilities of the AutonomousAgent, demonstrating its potential for creating intelligent, autonomous AI assistants.

Cloud serverless implementations of AWS Strands Agents.

Neural Adversarial Agent Mutation-based Security Evaluator

Give life to an AI agent with a single command.

Official implementation of Paperify. for running the Bilibili account "具身人机", focusing on embodied intelligence, human-computer interaction, and robotics.

IntelliSearch V3.1: Unifying Search, Empowering Action

Command-Line Agentic Refactoring of Java Code

Live context engine for AI assistants — resolve-before-context, session waypoints, and tool-selection intelligence for Hermes Agent

Solve AI context window limits for API docs | Convert any Swagger/OpenAPI to searchable MCP server | AI-powered endpoint discovery & code generation | Works with Cursor, Claude, VS Code

Self-evolving AI daemon in Go with fully generative UI. LLM generates unique HTML/ANSI interfaces from scratch for every response — not templates, not component catalogs. 10-stage pipeline, 4-level reflection, fractal agents, auto-generated code skills, 6 input channels.

A Discord Bot based off of Discord.JS and heroine from DiTF (not to be confused with ZeroTwo-Bot from https://zerotwo.bot)

Telegram bot with options to receive text and response with ChatGPT and also parse voice and response in the same language.

Flow.ai JavaScript SDK

Docker container for running hubot in a container.

a plug-n-play Discord chat bot

Local Llama project, L³ is an electron app that runs llama 3 models locally

Gemini AI is an innovative web application that brings an interactive chat experience with Google Gemini AI.

Learn to build a facebook chatbot using Python and Flask

Lawyer Bot is a suite of applications, containing an AI Chatbot designed to keep website visitors engaged in an automated conversation. The goal of the AI Chatbot is to increase the probability of conversion from inquiry to lead generation.

In this project, I extend the implementation of a Tweet/Sentence Sentiment Classification to a "Depression Assistant Chatbot". This software asks the users how they are feeling and if what they write expresses sadness of anger then they are greeted with jokes until they feel better.

Open source voice bot for Humanoid Robots and virtual digital humans

It is Deep Learning based chatbot model used for medical assistance.

🏆 基于transformer的单轮对话中文聊天机器人

👋 Simple greeting bot for Telegram groups

Chatbot in spanish using differents model: Seq2Seq model with Luong attention and transformer

🐱‍🏍 Your personal assistant, reimagined

Bot para whatsApp simples criado para uma clinica.

An NLP based Chatbot trained over a simple fully connected neural network using Tensorflow. Custom dataset.

The project's aim is to develop a chatbot that can help people create spec documents without knowing the specification.To get started with, the bot will consume the spec, JSON schema and serves the user as an expert. So based on a set of questions and answers it will generate an AsyncApi spec document according to the use cases.

This repository is a collection of resources, code-books and illustrations on MediBo project - a medical chatbot capstone project by a group of Columbia University students

Maxbot is an open source library and framework for creating conversational apps

Java Application for local area network Voice Chat

Sage is a versatile AI assistant designed to enhance your data interaction experience within a container environment. It provides a user-friendly conversational interface for accessing and manipulating data from various sources, all through a simple configuration file.

插件概念原型机 /// Agents System/自决策 |类 ChatGpt 插件系统| Gpt-3.5/Gpt-4 |Assistant | 📱 Cross-Platform | 🦾 Async | 🔌 Plugin System

使用LnagChain+FastAPI+Vue，搭建一個可以上傳並讀取PDF回答問題的LineBot。

A chatbot application using SwiftUI that uses the raw power of Chat GPT

A local-first LLM development studio. Build, test, and customize inference workflows with your own models — no cloud, totally local.

Chatbot that learns and provides map, video, and Web searches.

Robots developed in Python

a basic bot to evaluate using neo4j graph database as chatbot memory.

Telegram Bot that will remind you about important things

Grade: 82%. My COMP3000 final year university project that allows you to manage nearly every facet of your finances with an open-source web, mobile, and desktop application, along with a self-hosted GraphQL API.

A flexible and pragmatic chatbot intent classifier for chatbots

A chat app with which you can talk about different topics

Monetize.ai is a web-based chatbot that provides personalized investment advice using GPT-3.5 and Yahoo Finance API. It's built using Flask, SQLite, HTML, CSS, JavaScript, Bootstrap, and jQuery. The project is open-source and welcomes contributions.

Tock bot example using Kotlin and Integrated mode, implementing stories over an open data API.

Python ChatBot Implementation using chatterbot library

🤖About A fully customizable bot built with discord.js

A Twitch Bot for maximum user interaction and chat spam induction.

AI chatbot with GUI using Python Tkinter. This chat bot uses NLP(Natural language Prossesing) and takes Article as input and responds to user commands based on that Article.

An external Chat Bot for Minecraft made in Java

WhatsApp Api Java - Esta documentação tem como objetivo exemplificar o uso do Moorse Whatsapp API na linguagem Java.

GPT-3 Chatbot with long-term memory and external sources. Original work & inspiration by @daveshap

This is Windows based based chatBot in Python using tkinter

A simple chatbot built with XState.

Online search from your terminal using Perplexity AI

Everything you desire in the revolution of cryptocurrency.

Chat bot able to speak natural language and markup, prompt to complete commands, and offer localized help. Configured with schema-validated YAML, features JWT authentication with granular RBAC, and SQL persistence.

Simple YouTube LiveStream Chatbot (not maintained)

CBR (Case based reasoning) chat bot with C#.

Chatbot using Seq2Seq model and Attention

Helps with administration of chats

GPT Table Semantic Parsing with complex & non-intuitive structure.

A Question Generation Application leveraging RAG and Weaviate vector store to be able to retrieve relative contexts and generate a more useful answer-aware questions

RAGthoven, a Retrieval Augmented Generation Toolkit that helps you easily set up and execute your RAG experiments

VySol is an accessible local-first graph RAG app built to be easy to set up and use in one place.

Vortex is a self-hosted RAG (Retrieval-Augmented Generation) application that lets you chat with your documents using any LLM provider. Upload PDFs, ingest URLs, and get accurate answers grounded in your own knowledge bases — all with a clean, modern interface.

a local RAG LLM with persistent database to query your PDFs

Obrew Server: A self-hostable machine learning engine. Build agents and schedule workflows private to you.

A powerful RAG system for querying code repositories using tree-sitter parsing, LanceDB vector storage, and Qwen models

Production-ready RAG system using PostgreSQL + pgvector for semantic search

Converting unstructured text to knowledge graph using spacy LLM and ne04j.

CLI tool for creating single-file snapshots of multiple (code) files.

Agent tooling scripts and examples powered by Bun and Stacks.js

Exploring the Intersection of Large Language Models and Agent-Based Modeling via Prompt Engineering

📊 AI-powered strategic session facilitator based on EOS, OKR, 4DX, Scaling Up. Solo & team modes.

A privacy-first, self-hosted AI assistant that plugs directly into your Home Assistant stack, this project turns local LLMs into a practical automation brain—capable of understanding natural language, calling tools, and orchestrating real-world actions across your devices without relying on the cloud. Designed for hackers and builders.

No more guessing. No more panic after a bad patch. No encoding surprises. A protocol for safer, smarter updates — the bigger your codebase, the more it pays off.

Relational memory substrate for AI agents with MCP tools, identity continuity, and self-hosted persistence.

Open-source infrastructure for production AI agents

Exploring agent "thinking" animation.

Production-ready Claude Code framework with 13 agents, 9 skills, and auto-generated documentation for JavaScript, TypeScript, PHP, Laravel, React, and Python projects

Open-source security scanner for AI agent hosts. Audits macOS and Linux machines for misconfigurations, credential exposure, and network hardening — 42 checks across 5 phases with auto-fix.