Custom agents

电脑、手机、浏览器、终端共用同一个 AI Agent 会话。开源可自托管,会话内可无缝切换PI、Claude Code、Codex、OpenCode 等 Agent。| One AI agent session across desktop, phone, browser and terminal. Self-hosted, switch between PI, Claude Code, Codex and OpenCode mid-chat.

面向 Android ARM64 的 Linux 桌面与本地 Agent 运行环境

Save, list, and resume AI coding-agent sessions by project title — one ledger per harness: Pi, Claude Code, Codex, Antigravity, OpenCode.

Multi-Agent Reinforcement Learning for Connected and Automated Vehicles Control: Recent Advancements and Future Prospects

Multiple Chatbots at one place. ChatGPT, BARD, Claude, Bing, Poe, Insys, Xunfei, Purplexity, Cohere and more

The Chatbot (HealthBot) will try to solve or provide an answer to health-related issues or queries that the user is asking for. We are implementing NLP and ML to improve the efficiency of the chatbot. Tkinter is used as a frontend, and we are creating a desktop application with the help of Tkinter.

[IROS 2024] EPH: Ensembling Prioritized Hybrid Policies for Multi-agent Pathfinding

Algorithm that combines QMIX with SAC for Multi-Agent Reinforcement Learning.

An AI-powered agent based framework designed to assist with complex software engineering tasks

A comprehensive Model Context Protocol (MCP) server for Nigerian banking operations using the Mono Open Banking API.

[ACL 2024] The project of Symbol-LLM

The system consists of multiple AI agents that collaborate to strategize, generate commands, and execute scans based on the client's description, without the need for human intervention.

这是一个AI使用工具，可以使用AI进行文字创作或模拟聊天，支持简单地配置复杂的设定，支持在任何时候修改、停用、启用设定，实现更便捷有效的控制AI生成内容。可以配合API中转服务使用ChatGPT、Claude、ChatGLM、通义千问等大模型

AWS Lex based chatbot that calculates calories based on different fast food restaurants. This was an entry for a coding challenge on DevPost, and is actively used on Facebook Messenger. The issues list is actively managed as what defects or improvements are found by real world usage.

QQ频道机器人

Repository of Telegram's BotListBot

Make WhatsApp ChatBot and use WhatsApp API to send the WhatsApp messages in php .

S3 vector database for LLM Agents and RAG.

Multi-Agents using Workflows

Minimal implementation of multi-agent reinforcement learning algorithms

Stealthy x64 thread manipulation library for calling functions inside target processes without creating remote threads or installing hooks.

Outsource your understanding. Capture every human-AI decision as a step in a trajectory; grade trajectories retroactively when outcomes land (deal closed, sprint shipped). Hooks + MCP server for Claude Code, Qdrant + FastEmbed local-first.

Natural language understanding library for chatbots with intent recognition and entity extraction.

A Virtual Assistant for Windows PC with wicked Qt Graphics.

AgentOS2-Live by OrionStar — an end-to-end real-time voice interaction solution based on the Realtime API. No more ASR/LLM/TTS pipeline: direct “voice in → voice out + function call.” Works seamlessly with DeepV Code for speech-driven robot applications.

OpenBrowse is a macOS browser agent that gets things done on the web through autonomous task execution, chat-based clarification, and resumable local workflows.

ICLR'2024: Learning Multi-Agent Communication from Graph Modeling Perspective

Use Claude Code & other AI agents from inside DuckDB via extension

A LLama agent that builds startup ideas from your intutions (generates react codebases)

Mental health chatbot developed in RASA Framework, to analyze person's chances of mental illness on the basis of a survey questionnaire. Have a fun conversation with the bot and uplift your mood!

Easily convert agents and orchestrators from existing agent frameworks to A2A servers

Real-time translation copilot for your browser

Multi-agent codebase review for PRs, CI, and downstream fork syncs.

Create a Chatbot app on your own data with GCP tools

A Rust SDK for building AI agents with multi-provider LLM support.

An ecologically inspired multi-agent system. Agents are designed with neural network based decision making, and complex resource requirements.

Copilot for the terminal. Generate commands and preview them before running

로컬 또는 클라우드 LLM을 사용해 문서 폴더 기반으로 검색·답변하는 RAG 어시스턴트

基于llama-index框架的 RAG 最佳实践，通过业界领先的PDF结构化文档解析能力、混合检索、small2big、Contextual rag等策略实现了高精度的传统rag模式问答效果，同时支持基于plan and solve agent执行pipline的Deep RAG模式，提供多格式文档支持与数据安全的存储架构。

This repository is the official implementation of ZSC-Eval: An Evaluation Toolkit and Benchmark for Multi-agent Zero-shot Coordination. Pre-trained Agent Zoo: https://huggingface.co/Leoxxxxh/ZSC-Eval-policy_pool.

Claude Code skills for China quant trading

MCP server for Xcode that wraps its AppleScript interface & uses XCLogParser to return clear build results

This repository contains a collection of the most influential papers, and benchmarks related to Large Language Models (LLMs) based Agent Planning.

Deploy your autonomous agents to production grade environments with 99% Uptime Guarantee, Infinite Scalability, and self-healing.

Is your CLI ready for AI agents? Automated checks to ensure optimum agentic CLI use: don't block agents, don't waste tokens, ensure safe use.

Portable skill for building reliable LLM prompts. Drop-in for agentic-stack.

T2I-Copilot: A Training-Free Multi-Agent Text-to-Image System for Enhanced Prompt Interpretation and Interactive Generation (ICCV'25)

MCP Android agent - This project provides an *MCP (Model Context Protocol)* server for automating Android devices using uiautomator2. It's designed to be easily plugged into AI agents like GitHub Copilot Chat, Claude, or Open Interpreter to control Android devices through natural language.

GitHub Issues-backed agent orchestration for Claude Code – a single Claude wears persona hats (Orchestrator, CEO, workers) routed by issue labels, driven by a heartbeat loop

aiXplain enables python programmers to add AI functions to their software.

Research, monitor, and action your brand's visibility in LLM search.

All about llm-agents security,attack,vulnerabilities and how to do them for cybersecurity.

The repository for "MedChain: Bridging the Gap Between LLM Agents and Real-World Clinical Decision Making"

A portable framework that reduces the cognitive load of working with AI coding agents — plan, build, verify, milestone by milestone.

GitHub Copilot Agent Skill for Nightscout CGM blood glucose analysis

TokToken is a fast, single-binary C codebase indexer for AI coding agents. Powered by universal-ctags and SQLite FTS5, it provides precise symbol search, dependency tracking, and an MCP server. TokToken reduces LLM context token usage by 88-99% by retrieving exact code symbols instead of reading entire files. Zero runtime dependencies.

AI PM 실전 가이드 — Claude Code로 PM 워크플로우를 재설계하는 8파트 커리큘럼

A multi-room chat application in C++ using Winsock. Supports real-time messaging, private chats, undo/redo, history, and search. Built with threads, mutexes, and socket programming for concurrent multi-client communication.

🤖 Local AI agent for your laptop. Voice activation, multi-step tool use, 7-layer memory, human-in-the-loop approvals. Zero cloud. Zero API keys. Zero telemetry.

The Mastercard Developers Agent Toolkit allows popular agent frameworks to integrate with Mastercard Developers Platform for service discovery and integration guides.

VT Chat - A modern, privacy-first AI chat application with security

🚀 100% local RAG system with one-command setup. Your data never leaves your server.

General RAG framework specialized for scientific and academic applications.

Implementation for the paper "CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards".

[npj Digital Medicine 2026] HealthFlow: Automating electronic health record analysis via a strategically self-evolving multi-agent framework

📚 Lama Loca — локальный ИИ-ассистент для учёбы. Учится по вашим книгам, создаёт отчёты, презентации, конспекты. Полностью офлайн.

🔮 A smol coding agent in Elixir

CTX is the standard Cognitive Version Control System for AI. Structured working memory for AI agents. CTX preserves goals, tasks, evidence, decisions, conclusions, runbooks, and origins so agents can continue work instead of restarting from scratch.

Tài liệu Agent Guide đã chuyển về phiên bản web với trải nghiệm sử dụng tối ưu hơn. Click link dưới đây

Deep code indexing MCP server for AI agents. 25 tools: hybrid FTS5 + embedding search, call graphs, git blame/hotspots, build system analysis. Multi-repo workspaces, GPU-accelerated semantic search, 10 languages via tree-sitter. Fully local, zero cloud dependencies.

LatentMem: Customizing Latent Memory for Multi-Agent Systems

Let Claude Code reach you on Telegram when it finishes work or needs decisions

面向 Claude Code、Codex、Open Code等Ai Agent 的确定性公文排版 Skill，可直接渲染为规范公文格式的 .docx（字体、字号、行距、页码等）。

Run your entire company with Claude Code. 15 AI Agents + 5 Skills + Approval Pipeline. Battle-tested in production for 1+ year.

A fully featured, enterprise grade multi-agent harness with full observability, natural language agent creation, and intelligent context management.

The open-source marketing agent workspace for Claude Code. 42 commands, 12 hooks, 4 industry starters.

SYNINT: Agentic OSINT & Intelligence Framework – Modular, Stealthy, API-Free, Multi-Agent System for Automated Intelligence Collection & Analysis.

Repo-local continuity runtime for AI coding agents. Helps them continue from the same inspectable work state instead of starting cold. Stop onboarding your coding agents like rookies every session.

【ICML2026 Spotlight】 T2PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning

Agent Skill for Git workflow best practices - branching, commits, PR workflows | Claude Code compatible

MuseUI is a browser-only AI interface and image design generator. It helps you create UI mockups, social images, covers, infographics, stickers, logos, and other visual drafts from prompts and reference images.

A curated corpus of incidents, attack vectors, failure modes, and defensive tools for autonomous AI agents.

Composable data security plane for Model Context Protocol. Pluggable layers — collect, analyze, guard — across 50+ enterprise providers. Open architecture.

An enterprise-grade implementation of multi-agent systems using OllamaJS, featuring advanced orchestration, dynamic agent allocation, and seamless integration capabilities.

DeepBlue Brain：一个面向 RAG 全链路教学与理解的白盒化交互平台，支持各类文档上传、混合检索、实时检索日志流、提示词原文溯源与流式问答。

Event-driven multi-platform bot framework with Dashboard, Docker, hot-reload & module marketplace | 事件驱动的多平台机器人框架 — 支持 QQ/Telegram/Kook/云湖/Matrix/邮件等 15+ 平台

Ship agentic. Stay coherent. Self-checking code integrity for AI coding agents, via MCP.

AI-powered QA testing framework that uses LLMs (Claude or GPT) to test web apps, CLI tools, and TUI programs from markdown story cards, returning structured pass/fail verdicts with evidence.

Curated, verified Agent Skills powered by ModelStudio.

Code for "Skill-MAS: Evolving Meta-Skill for Automatic Multi-Agent Systems"

[ICLR 2026] Code for the paper "Graph-of-Agents: A Graph-based Framework for Multi-Agent LLM Collaboration"

🔁 Build reliable recurring AI-agent systems: 1022 resources, 22 operational patterns, 22 loop contracts, 8 runtime starters, an interactive atlas, and a structured dataset.

Open-source, self-hosted control plane for OpenClaw and Hermes AI-agent fleets on Docker/Kubernetes — REST, CLI, and MCP.

The address book for AI agents: Nondual gives all your agents one shared record for every person they talk to: who they are, what was said, what happens next.

Open-source context infrastructure for agents. Sync changes, inspect paths and read current source content through Python, CLI or MCP.

List ports and their processes on Linux, macOS, and Windows.

Local web workspace for coding agents — Claude, Codex, Gemini, and more in one inspectable, LAN-ready hub.

LemonClaw, an open-source, universal AI digital employee agent