Custom agents

DSH 插件：自建微信/QQ「鲸鱼娘」机器人的控制面 —— 启停 Python 侧车、逐个开关功能、改人设、调回复频率，并可用 whalegirl_* 工具在对话里指挥她

Keep an eye on your AI coding agents: a live browser view of your agents, and CLI-based mail for them to collaborate on Tasks.

CARD: Towards Conditional Design of Multi-agent Topological Structures. Published at ICLR 2026.

Open-source MCP server for your docs. Zero LLM at query time. docker compose up and go.

Knowledge graph and context manager for AI coding agents: Claude Code, Codex, Gemini CLI, Cursor, Copilot and local models. Code map with PageRank, temporal knowledge graph, hybrid search, early compaction with handoffs.

A local agent workstation: one Go loop, three doors: Wails desktop, browser, and CLI. It writes code, reviews hunks, opens an isolated browser, runs skill packs, and keeps Create, Shorts, Drama, and Canvas in their own folder. Files stay in a folder you pick. A new harness has to pass Harbor before you trust it.

FableForgeAI-StoryEngine integrates cutting-edge AI technologies including Gemini-Pro, Hugging Face models, and Gradio interfaces to provide an immersive platform for generating stories, engaging with chatbots, and creating comic videos, showcasing the synergy of AI in creative storytelling and interactive content creation.

The Universal Open Knowledge Format (OKF) Ingestion Compiler. Convert PDF, DOCX, Markdown, and HTML into structured, cross-linked RAG context graphs using Google Gemini.

My agent that won HackerRank Orchestrate (May 2026), #1 of 12,885: a support triage agent with one hybrid search tool and injection guardrails

An MCP server built on top of Huawei Training Camp (HTC) APIs, enabling AI agents to access and analyze Huawei Health training data.

Mobile remote control for AI coding agents on your own computer. Works with Claude Code, Codex, OpenCode, Gemini CLI, Cursor Agent CLI, GitHub Copilot CLI, Kimi Code, Qwen Code, Kiro CLI, Google Antigravity, CodeBuddy Code, Cline CLI, Trae Agent, CodeFuse Agent, DeepSeek Harness, Pi, OpenClaw and Hermes Agent.

Polya Agent Skills for developing and programming apps with AI Agent, coding agent tools, and AI harness

Unofficial Android client for Alma Desktop — pair over Alma's end-to-end encrypted relay

SharedNet CLI and Agent Skill: join persistent SharedNet Rooms where Claude Code, Codex and other coding agents talk over one ordered log. Published to npm as sharednet.

Awesome Grok Bot: beginner guide and curated resources for the Grok Bot AI teammate app (Bots, routines, skills, cloud computer, Connect apps, Pages).

Free interactive tools for data scientists to learn MLOps, ML system design and agentic analytics: a production ML system map, ML project structure, data drift simulator, agentic analytics system map and AI evals.

An open-source AI chat assistant for your website, running on your own Cloudflare account.** One command sets up the chat widget, a knowledge base learned from your site, and a dashboard for conversations and leads. The default setup runs on the **Workers Free plan**

Extensible AI agent framework in Go — multi-channel (Feishu/Slack/CLI), sandboxed tool execution, MCP integration, multi-tenant sessions

Model Context Protocol server for Sapo.vn POS & e-commerce — 105 tools across 4 modes, stdio + Streamable HTTP, single-tenant Private App.

⚒️ The open-source framework for LLM experiments and agent orchestration.

Async AI coding orchestrator: turns Yandex Tracker tasks into Claude Agent SDK workflows and GitHub PRs, with code review, deployment checks, and supervised auto-merge.

Multi-agent governance layer for self-maintaining LLM wikis

Python and MATLAB codes for Density-Driven Optimal Control (D2OC) using Optimal Transport and Wasserstein distance, enabling decentralized multi-agent / multi-robot non-uniform area coverage.

MCP for Scorable Evaluation Platform

AI assistant in your command line

Merge Ayurvedic wisdom with AI chatbots for personalized health recommendations

Repo for Implementing Research Papers & Projects related to Machine Learning

给你的agent找个家

RoundTable Framework For Claude Code — A structured multi-team AI governance framework

Create AI Agents equipped with tools and extensions

AI-first Go development framework. Ship production CLIs that AI agents build correctly.

Hermes Agent + webui in Linux GUI Desktop

AI-powered idea & task manager for developers. Brainstorm → structured tasks → AI agent execution via MCP. CodeMirror editor, Claude/Gemini/Codex, local-first SQLite.

Dissi is a high-performance, real-time communication agent powered by Groq and built with Agno, designed to interact with Discord servers using natural language.

🧶 Open-source GenUI Agent framework — AI autonomously decides which UI components to render. Powered by LangGraph + AG-UI protocol. Plug in any LLM via LiteLLM, any API via YAML config.

Command-line interface for performing software engineering tasks using large language models. It is based on Cline, but is simpler, uses fewer input tokens, has fewer capabilities, and does not depend on VSCode.

AI got hands. This is the leash. Policy, audit, kill switch for any AI agent with access to your accounts.

Auto connect wallets, referrals, do tasks, spinning, checkin.

🍀 An AI's crypto trading journal. Learning in public, one trade at a time.

Persistent, self-maintaining memory for AI agents. 1,451 tests. 5ms recall. $0/month forever.

Copy and paste prompts for cursor agent. Free for anyone to use or add to. This repository provides a curated collection of advanced .mdc rules for Cursor IDE to optimize AI agent behavior, memory management, and development workflows.

A lightweight, extensible cybersecurity toolkit that connects AI assistants to security tools through the Model Context Protocol (MCP), enabling AI-assisted security research, scanning, and analysis.

Agentic AI Software Engineer that can convert natural language to executable code

The Eternego codebase

a QA bot on contents of given docs 用所给文档进行问答的聊天机器人

[IROS'25] COCMT

It shows an intelligent agent based on LangGraph for long form writing.

Hive is a Multi Agent Orchestrator modelled after Agile Teams

We use policy gradient to help agents learn optimal policies in a competitive multi-agent contextual bandit setting

Decentralized multi-agent collision avoidance

Mandali (मंडली) — Autonomous multi-agent adversarial collaborative system using GitHub Copilot SDK

Deterministic agent runtime with explicit plans, typed tools, permissions, and replay. Implements Google DeepMind's Intelligent AI Delegation framework. Named after ELP's Karn Evil 9.

event-sourced adk for go

SmartAgentic is a project-centric, multi-agent memory OS for software engineering. It turns conversations and code decisions into an evolving knowledge graph so teams keep context across sessions, reduce contradictions, and ship.

The simplest way to deploy, manage, and scale AI agents in your Kubernetes cluster with declarative YAML configurations

plan-bound authorization architecture for governing privileged effects in untrusted computational agents.

Your site's built-in, self-hosted AI web dev. Chat to build, update, and manage your entire website. The CMS, reimagined.

TrustifAI: A Comprehensive Framework for AI Trustworthiness

An agentic solution designed to create a llms.txt file for any given repo or folder.

AI-powered developer onboarding platform using natural language to deploy applications via GitOps. Golden path workflows with ArgoCD and OpenRouter integration.

Validation and permission system for Claude Code

A simple task management system for managing AI dev in Cursor

Universal Agent Protocol (UAP) - Making AI agents work together seamlessly. The standard way for agents to find, talk to, and coordinate with each other in multi agent systems (MAS).

Framework for RAG over Excalidraw canvas data

Maps Claude Computer Use to Playwright

Agentic Workflow & Patterns implemented using Spring AI

Ask questions about your business data in plain English, Get automatic SQL queries and visualizations, Receive AI-powered insights and recommendations, No SQL knowledge required

Containerized A2A-native agents with simple setup

A plugin for Obsidian that replaces embed syntax with actual content for easier context sharing with AI language models.

:sunglasses: Simple ChatBot, which replies to anything you ask ! Now with voice recgnition ! Say "Hey" to wake the bot ! :D

Food recommendation chatbot with LLM fine tuning. 2023 graduation project from Pusan Nat'l Univ.

Very simple example of Seq2Seq model

A chat-bot powered by Amazon Lex and built on top of Serverless Architecture

JanSevak is a AI powered HealthCare Management System. The system allows users to register as patients, book appointments, and predict diseases based on symptoms. Doctors can view and manage appointments. Additionally, the system provides information on various health-related topics through blog posts.

Intentional is an open-source framework to build reliable LLM chatbots that actually talk and behave as you expect.

For facebook comment and messenger fan page.

Chatbot Designed to Help Tenants Facing Eviction and Other Landlord-Tenant Law Issues

Rasa Chatbot using Django backend and Sockets for communication

TGPT - Lightweight GPT Telegram Bot built in Go

Some unofficial extensions to Kernel Memory to do some advanced RAG

WMB-100K — The first 100,000-turn benchmark for AI memory systems

Knowtate is a sophisticated platform designed to elevate your academic research experience. Seamlessly blend reading, note-taking with markdown, and knowledge management into one intuitive interface, allowing you to effortlessly track your insights and ideas as you delve into scholarly literature.

js client for R2R: production-ready RAG engine with a sh*t ton of features.

Retrieval-Augmented Generation (RAG) toolkit for Laravel: async docs, chat, outlines, multi-provider.

In-memory vector database with pluggable indexing algorithms, metadata filtering, and a FastAPI-based REST API.

Official implementation of "RAViG-Bench: A Benchmark for Retrieval-Augmented Visually-rich Generation with Multi-modal Automated Evaluation"

RAG-Mathstar 智数星

RagCheck is a proactive corpus quality assessment tool that analyses RAG application document collections before deployment, identifying content gaps and providing specific recommendations to improve query performance. The platform transforms reactive corpus fixes into proactive quality assurance, helping organisations achieve as high as 85% score.

技术周刊，每周一发布。前沿技术、社区资讯，一网打尽。

Exploring the use case of LLMs in healthcare, in particular assisting in document retrieval and summarization.

🚀 this project aims to develop an app using an existing open-source LLM with data collected for domain-specific Jenkins knowledge that can be fine-tuned locally and set up with a proper UI for the user to interact with.

Optimize Subtitles for RAG Ingestion

🔒 100% Private RAG Stack with EmbeddingGemma, SQLite-vec & Ollama - Zero Cost, Offline Capable

AI Search Engine in 70 lines

PDF AI Assistant Powered By Genimi

Convert any image into a Region Adjacency Graph (RAG)

This project is an automated research and summarization tool that allows users to conduct research on a specific question and summarize the information found and present it as a blog post.

Open-Source Java AI Assistant

An AI-powered search engine to interact with documentation using RAG and local LLMs. Privately deployable with vector search and a modern frontend.