Custom agents

The library for testing bots on aiogram3

An Android ChatBot powered by IBM Watson Services (Assistant V1, Text-to-Speech, and Speech-to-Text with Speaker Recognition) on IBM Cloud.

All-in-One: Text Embedding, Retrieval, Reranking and RAG in Transformers

⚡ ZhiYing — 终极开源 AI Agents 生态协同系统 | Agents Browser · Agents Workflow · Agents Studio World

74 production-ready Claude Code skills and 7 specialized agents for engineering, DevOps, product workflows, UI, deployment, and AI-agent automation.

Build a WebUI of ChatGPT with multiple authentication methods using Gradio and revChatGPT

Code together, right now! GPT powered code assistant to build project in minutes

NIPS Conversational Intelligence Challenge 2017 Winner System: Skill-based Conversational Agent with Supervised Dialog Manager

A Simple ChatBot Widget

BotMan Facebook Messenger Driver

AI Agent for Chinese Chess - CS 221 Project

AI Agent Memory System inspired by Neuroscience

KIT (Knowledge Inference Tool) — A lightweight AI agent for coding

A production-grade framework for building AI agents.

The platform for AI developer agents. Describe what you want to build and watch it become a reality.

Monte Carlo Tree Search (MCTS) is a method for finding optimal decisions in a given domain by taking random samples in the decision space and building a search tree accordingly. It has already had a profound impact on Artificial Intelligence (AI) approaches for domains that can be represented as trees of sequential decisions, particularly games and planning problems. In this project I used a board game called "HEX" as a platform to test different simulation strategies in MCTS field.

Practical tutorial on RLlib for deep hierarchical multi-agent reinforcement learning

:flying_saucer: An implementation of multi-agent flocking formation control with specific formations that can follow a target without collision and can avoid obstacles.

ClawSync, OpenClaw for the cloud. Deploy an open source personal AI agent with chat UI, skills system, MCP support, and multi-model routing. Built on Convex.

🚀 分分钟构建 AI 应用

LoFS 面向本地知识库的桌面级文件管理与信息检索和对话应用

The missing human checkpoint for AI coding agents. Give your AI agent a "pause & ask" button — review, correct, or enrich every step before it runs.

MCP tool for exposing a structured task queue to guide AI agent workflows. Great for taming an over-enthusiastic Claude.

A multi-entity Transformer for multi-agent spatiotemporal modeling.

Design and implement agents, bot and chatbots in Python

GoalChain for goal-orientated LLM conversation flows

Specs, tracking, and coordinated development for AI coding. Works with Cursor, Claude Code, Replit Agent, and any AI coding assistant.

Developed an AI-powered supermarket analytics system using LSTM, K-Means, and Apriori to predict sales, segment customers, recommend products, and optimize inventory through an agent-based architecture with a Streamlit dashboard.

CodeNav is an LLM agent that navigates and leverages previously unseen code repositories to solve user queries.

A self-contained multimodal AI agents lab built using MongoDB, Gemini and LangGraph.

A seed for growing a personal AI that improves through use and continues through failures.

Memory management MCP server for AI agents using Neo4j knowledge graphs

A repository of useful guides and frameworks for effective AI-Human interaction

[ACL 2025] Multi-Agent System for Science of Science

Official code for the publication "Large Language Models as Zero-shot Dialogue State Tracker through Function Calling" https//arxiv.org/abs/2402.10466

A voice assistant application built with the LiveKit Agents framework, capable of using Model Context Protocol (MCP) tools to interact with external services

A unified web extraction and stateful automation engine for AI. Replaces heavy testing frameworks with token-optimized browser control, deep research, and HITL.

An AI chatbot plugin for Obsidian using the Gemini API for note summarization, content generation, and more. Enhance your workflow with AI assistance like the Notion AI bot.

Open source agentic build system - transforms specifications into verified source code with blind adversarial review

Run your own persistent, self-cloning, collaborative 'agents' called Abes to manage your own homelab -- Local first.

Research automation skills for Claude Code. Idea to submittable paper in one session.

An environment simulation for networks security tasks for development and testing AI based agents. Part of AI Dojo project

OpenClaw with Ollama is a lightweight, high-performance integration designed to run sophisticated AI agents locally on Android devices. By leveraging the power of Termux and the flexibility of Ollama, this project enables a completely private, free, and offline-capable AI workstation in your pocket.

Implementation of my AI agent system for ERC 3: https://erc.timetoact-group.at

Multi-user AI assistant and agent

Inspired by Project Hail Mary, a macOS desktop companion app that puts an animated pixel-art character on your screen — powered by Claude Code. Rocky walks back and forth along the top of your Dock. Click him to open a retro terminal-style chat window and talk to Claude directly from your desktop.

AI-powered content pipeline: trend discovery → research → social publishing. Built with Claude Agent SDK + MCP.

Advanced AI tagging and prompt generation studio.

Introduces a comprehensive agent-based framework for guided software development (GSD)

基于 claude-agent-sdk 的智能渗透测试 Agent，用于参与第二届 TCH 智能渗透挑战赛。

AgEnFK - Agentic Engineering Framework

[NeurIPS 2026] GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators

An open source ai platform being built for everyone ❤️

Single-file agent goal ledger for Claude Code and Codex CLI - pairs with /goal mode

A lightweight ALM toolkit for Copilot Studio agents – GitHub Actions workflows, best practices, and deployment guidance

Rust runtime with TS/Python bindings for Claude Skills with progressive disclosure of skill metadata, full content and scripts/resources. Any agent can now own skills. Currently support Seatbelt and experimentally, WASM, sandboxing

VV knowledge layer for AI agents — MCP server exposing Visualize Value frameworks, voice, and content

Agentic RAG Harness for long documents, Tree and Graph based reasoning. Cited answers down to the pixel

LLM evaluation framework for Ruby, powered by RubyLLM. Tribunal provides tools for evaluating and testing LLM outputs, detecting hallucinations, measuring response quality, and ensuring safety. Perfect for RAG systems, chatbots, and any LLM-powered application.

An [Agent Skill](https://agentskills.io) that enables AI coding agents to tackle complex, long-running implementation tasks autonomously.

ParaView-MCP integrates multimodal LLMs with ParaView via Model Context Protocol, enabling natural language control of scientific visualizations. The agent observes the viewport for visual feedback, making complex visualization tool accessible to all users while providing intelligent automation for experts.

Game Codebase Analysis AI Agentic Tool

A local-first Chrome extension that passively captures ChatGPT, Gemini, Claude, Grok, Perplexity conversations into a private memory graph. Features in-browser Hybrid RAG (Vector + BM25), semantic search, and 100% privacy via WebAssembly and IndexedDB. No servers, no API keys.

One-Stop Personal Health AI Agent "Say Hi to Healthy Me"

The first intelligent AI agent running natively on a smartwatch. NullClaw + Vosk offline STT + Claude on Galaxy Watch

Turn your markdown vault into a compounding knowledge wiki (Karpathy inspired). Six agent skills - knowledge grows with every conversation. Works with Obsidian, Logseq, etc. or just folders on your local drive. Compiled memory for your LLM sessions. Crossplatform. GUI install on Claude Desktop, no terminal, no code.

Most AI agents forget you the moment the tab closes. Constellation Engine gives them a hippocampus — a living star map with spreading activation, Hebbian writeback, episodic recall, and post-turn consolidation. Local-first, model-agnostic, AGPL.

A curated list of voice AI agent frameworks, tools, resources, and best practices

An open-source Android AI voice assistant built with Kotlin, Jetpack Compose, and on-device ML (BERT + TFLite, MediaPipe, ML Kit).

Harness-enforced AI business research skill for Claude Code and Codex Desktop

PTY-backed Claude Code wrapper that provides claude -p compatible output

An auditable enterprise sales insight agent with LangGraph, evidence grounding, deterministic guardrails, evaluation, and human review.

Say what you want in plain words. Atris plans it, builds it, checks it, and shows proof. CLI plus MCP server for AI agents.

Your desktop AI agent, always ready

本地优先的 macOS AI Agent 信号灯：状态栏 + 桌面悬浮信号灯，自动监控 Codex / Claude Code。Local menu bar and floating desktop status lights for AI agents.

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

PostHog context and skill assembly for AI agents and LLM tasks

A curated list of AI Agent Swarm frameworks, multi-agent orchestration, swarm intelligence, and collaborative agent systems.

Long-term, cross-project memory for AI coding agents. Your own Obsidian vault as the source of truth. Daemonless and without opaque databases, your memory belongs to you.

Free multi-agent coding workbench: Grok/Codex/Claude/Cursor panes + TrueMemory (per-repo + global)

Finance data and heatmap images for AI Agents Hermes OpenClaw

My personal library of reusable skills for AI coding agents.

MiraFrame 是一个面向 AI 漫剧创作的全栈 Agent 项目。它不是简单调用一次大模型，而是把“故事大纲 → 角色设定 → 分镜脚本 → 角色图 → 镜头素材 → 导出”拆成可观察、可重试、可人工反馈的创作流水线。这个项目特别适合正在从前端转向 AI Agent / AI 应用工程的同学

Take the 100 Days of AI challenge - learn one AI concept a day, from machine learning basics to AI agents in production, in 100 days.

Multigent is an AI-native collaboration platform that brings humans and autonomous agents together. Manage teams, projects, workflows, tools, and shared context through a unified control plane designed for the future of intelligent work.

🧪💥 Evaluation framework based on Vitest, the testing framework you familiar with, for agents, models, and more.

Local session-mining loop for staging AI agent improvements and public-safe content ideas

TCP-enhanced fork of Cheat Engine MCP Bridge. Connect Cursor, Copilot and Claude AI directly to local or remote Cheat Engine via TCP. Automate reverse engineering, pointer scanning, and memory analysis using natural language.

AI agent skills for Catalyst by Zoho — enables Claude, Gemini, Cursor, Copilot, and Windsurf to write deployment-ready Catalyst code, recommend architecture, and manage infrastructure via Zoho MCP.

AI powered SSH, SFTP, telnet and Windows RDP in a single window, with integrations for Claude Code, Codex and OpenCode agent that reads and execute commands in the session in front of you. Free and open source.

EDITH Agent, a multi‑user agent platform

Use large-scale AI agent teams to rapidly discover code improvements and "autoresearch" your hardware systems.

Let your AI agent use your passwords and API keys - without ever letting it see them

Upload spreadsheets, ask questions via chat, and auto-generate chart reports. No coding required, gain instant insights and unlock data value effortlessly. ｜上传表格，像聊天一样提问，系统自动分析生成图表报告。无需编程，即时洞察，数据价值触手可及。

AI agent skills for generating high-quality unit tests — Given-When-Then test cases, JUnit 5, Mockito, AssertJ. Works with Claude Code, Cursor, and any AGENTS.md-compatible agent.

Open-source quantum Agent workspace with a desktop client, Web UI, messaging, Qiskit/MCP tools, and scientific validation