Custom agents

iOS application for Lumo

🛡️ Portable credential management for AI agents — Age encryption, session leases, killswitch

An open taxonomy and scoring framework for evaluating AI agent sandboxes: 7 defense layers, 7 threat categories, 3 evaluation dimensions, 27 "sandboxes" scored.

🔬 A Researcher&Agent-Friendly Framework for Time Series Analysis. Train Any Model on Any Dataset!

A personal AI agent that can work safely on your machine, remember useful context, and keep its data under your control.

A collection of skills, agents, commands, and workflows for security researchers. Compatible with Claude Code, Claude Desktop, OpenCode, and other AI coding tools.

Annotate/Draw any web UI for AI agents and export structured context, no app code changes required.

A ready-to-use self-growing desktop AI assistant for long-running tasks, memory, agents, tool reviews, MCP, and high-concurrency workspace automation. / 开箱即用的自我成长型桌面 AI 助理，面向长期任务、记忆、部门协作、工具审查、MCP 与高并发工作区自动化。

Complete Kaggle integration plugin/skill for AI coding agents — competition reports, dataset/model downloads, notebook execution, and badge collection. Works with Claude Code, Gemini CLI, Cursor, Codex, OpenClaw, and 35+ agents via skills.sh.

[ARCHIVED] Superseded by XenolithGraph — modern TypeScript/WebGL successor with React/Vue adapters and MCP for AI agents. See: github.com/XenolithEngine/xenolith-graph

Official samples and developer tools for building on SharePoint Embedded, the document storage API on Microsoft 365. Includes React, TypeScript, and ASP.NET Core boilerplates, an MCP server for AI coding agents, Copilot and Power Platform assets, Postman and Bruno collections, and admin scripts.

Open-Source Intelligent Command Layer

Your local-first command center for working with AI agents like a real team.

Agent Skills de conformidade LGPD (Lei 13.709/2018), resoluções ANPD e ECA Digital (Lei 15.211/2025) — instaláveis em Claude Code, Codex, Gemini CLI, Cursor e OpenCode. 1 maestro (lgpd-audit) + 18 sub-skills.

AI-powered video production pipeline for Claude Code, Github Copilot, Codex, Cursor, OpenCode and PI — 6 automated phases from design thinking to final render

🎙 Local zero-cost audio→markdown/docx pipeline. Whisper + AI cleanup. Replaces Otter.ai/飞书妙计. Agent-ready (Claude Code/Codex/Copilot/Cursor). macOS/Windows/Linux.

Bootstrap projects from Figma, Linear, Notion & GitHub specs. The only AI ralph with source integrations.

The open, machine-readable standard for the Somali language — orthography, grammar, terminology, translation, and AI/benchmark resources, as a versioned, citable RFC-style catalog.

Autonomous multi-agent harness for Claude Code (A.L.B.E.R.T. orchestrator) plus a zero-dependency live HUD console.

豆包搜索 MCP server — 给换了国产模型的 Claude Code 补上联网能力。字节系信源、千字正文、每月500次免费 | Agent-first web search MCP

LLM agents: curated papers on planning, memory, tool use, multi-agent systems, evaluation, and safety.

Swiss-army toolkit for .docx — faithful DOCX→HTML rendering, an in-browser block editor, Word-grade redlines with native tracked changes, and anchor-addressed markdown for LLM agents. .NET, WASM/TypeScript, Python, CLI.

Metrik 可以集中查看本机多个 Agent 的配额余量和 Token 消耗，目前支持 ChatGPT、Claude、GLM、Kimi 等主流 AI 服务。

An open-source MCP server that turns LLMs into condition monitoring assistants for reliability engineers. It gives your AI assistant evidence-based vibration diagnostics: machine fault detection, severity assessment and diagnostic reports, for faster predictive maintenance decisions. Also available as a Claude Code plugin.

Verified AI dependency migrations. Finds which of your lines a version bump actually breaks, fixes them, and proves the result still compiles and passes your tests.

Local multi-agent harness for running persistent agent teams, long-run, society-simulation

Evidence-first AI workflow for economic and financial research: literature → identification → data → econometrics → verifiable LaTeX. 43 data sources, 58 method modules, 18 AI skills, 30 journal templates.

一个面向A股的多agent股票辅助分析系统

The agent harness you can fork. A working agent loop with compaction, sessions, approvals, a terminal REPL, a local dashboard and ACP, where every tool, skill, hook and policy is a file you can change. Build your own internal or coding agent on any model.

破甲next · macOS 版 | WorkBuddy + Codex 人格注入装载台（WorkBuddy 六层靶点 / Codex 双锚点 + 封条完整性保护 + 反去标识化声明）。纯 Python 标准库 + Bash，零第三方依赖、零网络请求、改前自动备份、随时一键还原。

Self-hostable RAG backend for document knowledge: hybrid search, cited answers, and agentic deep reading. Java · Spring Boot · Spring AI · Elasticsearch.

Keeps AI coding agents such as Claude Code, Codex, GitHub Copilot, Gemini CLI and Cursor to the least code that does the job and still works.

校园知识服务 Agent 智能体平台：基于 FastAPI、Qwen3 与 RAG，贯通公开资料解析、时间范围检索、证据溯源及人工审核。

麦当劳 MCP 技能：待评价清单、好评兑礼进度、发票报销门槛凑单、单次抽奖确认。99 项测试，非官方产品。

A toolkit of agent primitives

Claude Code integration for OpenPets: automatic desktop pet status updates with one-command setup.

Core abstractions for your agentic workflow

Learning multi-agent robotic mobile manipulation with deep reinforcement learning

An agent-based epidemiology simulation framework built in Rust

A true Artificial Intelligent Assistant with ALICE as backend and offline speech recognition with vosk engine and pyttsx3 as text to speech engine

GibRAM is an in-memory knowledge graph server designed for retrieval augmented generation (RAG / GraphRAG) workflows.

[TMLR'25] "Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents"

A mobile first, self-hosted multi-model AI chat powered by the GitHub Copilot SDK. A modern alternative to ChatGPT, Claude, and Gemini.

[ACL 2026] OxyGent: Making Multi-Agent Systems Modular, Observable, and Evolvable via Oxy Abstraction https://arxiv.org/abs/2604.25602

The self-evolving AI factory: an open-source framework that builds, evaluates and evolves AI agents for your task. An Inria spin-off.

Pydantic AI agent that implements the idea of Claude Skills (progressive disclosure) with no reliance on Claude itself.

基于LLM的股票投资助手

A Web Crawler based on LLMs implemented with Ray and Huggingface. The embeddings are saved into a vector database for fast clustering and retrieval. Use it for your RAG.

agent-from-scratch is a Python-based repository designed for developers and researchers interested in understanding the inner workings of single and multi-agent systems

Supercharge Claude Code with Expert Knowledge A comprehensive framework for AI-assisted development. Install standardized rules, agents, and commands for your projects across multiple technology stacks.

A modern AI chatbot with chat, image generation, and text-to-speech features, designed for a smooth and friendly user experience.

基于多智能体协作的中国基金市场智能分析系统与智能管家--A smart analysis system and smart manager for the Chinese fund market based on multi-agent collaboration.

量化投資研究 AI Agent — 透過 CLI 互動介面，自動搜尋財經新聞、分析市場情緒、產生風險評估報告。可接OpenClaw。

Bridge local AI coding sessions between Pi, Claude Code, and Codex.

OR-LLM-Agent: Automating Modeling and Solving of Operations Research Optimization Problems with Reasoning LLM

[ICML 2026] BuildArena, where LLM agents design, build, and test rockets, cars, and bridges in a physics simulator given a goal-directed sentence.

A type-safe, declarative AI agent framework for Swift. Build composable AI pipelines with Steps, Agents, structured outputs, and tool integration. Features FIFO session management, MCP support, and distributed actor communication.

A lightweight, extensible Python framework for building and orchestrating single or multi-agent AI systems. | 一个轻量、可扩展的 Python 框架，用于构建和编排单智能体或多智能体 AI 系统。

🤖 Autonomous development orchestrator for the BMad Method. Runs fully autonomous, parallel, multi-agent pipelines through the full story lifecycle (create → dev → review → PR) driven by your sprint backlog and dependency graph.

5 Claude Code skills for product managers. Drop them in your .claude/skills/ folder and go.

Python port of the Flue: The Agent Harness Framework

Chat, specs, tasks, and code. An autonomous engineering platform. Full autonomy when you trust it. Full control when you don't.

Daofy for Delphi — MCP Server that compiles Delphi projects and queries knowledge base for AI assistants.

A modular, fully configurable DataviewJS dashboard for Obsidian — monitor Claude Code sessions in real-time, manage AI agent fleets, track 30-day analytics, and boost productivity with focus timer, quick capture, and more.

hermes-agent源码解析

One app for both cloud LLMs and on-device LLMs.

600 KB WASM runtime for Cactus Compute's Needle AI tool-calling models, Needle 3, 2 and 1 from one build. Browser, Cloudflare Workers, Node.js, Python, C FFI and no_std. Token-exact with the JAX reference. No backend, no API key.

Standalone MCP server for cross-pane AI agent communication via tmux. Lets Claude Code, Gemini CLI, Codex, and Kimi CLI talk to each other through tmux panes.

maw — CLI for running multiple AI agents across machines via tmux. Wake agents, talk across nodes, watch screens, track cost. Engine-agnostic (Claude Code, Codex, Aider, OpenCode), built on Bun.

🪞 An AI existential-psychology counselor asks you 3 meaningful questions every night for 21 days — and remembers, reflecting your own words back to you. Bilingual zh/en. A Hermes Agent skill. 每晚三个问题，一面慢慢显影的镜子。

The AI Agent designed for work with security in mind.

An opinionated list of awesome Pydantic-AI frameworks, libraries, software and resources.

A Model Context Protocol (MCP) server that exposes PyMOL as a typed tool surface to your agent (Claude Code/Desktop, Codex, or any MCP-compatible client)

Open-source AI browser agent — type plain-language commands and Bah operates the web for you. Works with cloud AI (DeepSeek, Mistral, NVIDIA) or local Ollama models.

Lightweight Codex/Claude loop harness with strict evidence gates.

Self-hosted AI agent memory — MCP memory server with durable recall for agents

💼 One MCP server to search job boards and company career sites

55 MCP tools to drive the Unity Editor from any MCP-compatible AI agent — scenes, GameObjects, prefabs, assets, tests, and builds. OpenClaw gateway included for remote and chat access.

Adds support for selecting a custom model provider to use for a thread/chat, without logging out of your ChatGPT account.

Benchmark framework that measures cost, quality, and duration of coding agents across any AI Coding Assistant CLI, any model, and any use case — with pluggable verification and real-repo support.

给 HR 和猎头的 AI 招聘工作流：岗位梳理、BOSS 直聘与猎聘双通道寻源初筛、人才盘点、简历评估、面试安排、候选台账与日报。支持 Claude Code、Codex、WorkBuddy 等工具及 DeepSeek Harness 插件，配有招聘进展看板；标准、台账与档案保存在自己的工作区。

Prompt-native interactive HTML docs — bdocs. Generate, comment on, and publish docs from inside codex, Claude Code, and any agent

WebView automation for Kotlin Multiplatform. Run page workflows in an embedded WebView on Android, iOS and desktop, from your app, a test, or an LLM agent over MCP or Koog.

Pentest anything you want

具备自主经验涌现与上下文治理能力的 Agent 长期记忆系统

Open source Android AI agent. Control your device with voice & AI. Lightweight, any LLM, no root.

Auditable AI-assisted scientific research: evidence-gated hypothesis routing, isolated computation, independent replication, and anomaly-sensitive representation repair.

Agent orchestration service for the Agent Landing Zone, built on Microsoft Foundry Agent Service and Microsoft Agent Framework. Coordinates specialized agents for conversational experiences with grounded knowledge, NL2SQL and MCP tools.

Your Apple-Native AI Agent

使用Drl来解决多智能体卸载问题

Ballerina ReAct type Agent module using Large language models (LLMs)

A PHP Framework For Creating Autonomous Slack Bots

Chat with PDF lets you ask questions to PDF documents. Built and deployed with NuxtHub, and powered by Cloudflare Workers AI and Vectorize.

Building a Q&A LLM Agent to Answer Questions about Your Dataset

This is a simple implementation for crypto research agent inspired by Claude Skills repo

AURA (Agent-Usable Resource Assertion) is an open protocol designed to make the web machine-readable. It replaces fragile screen scraping with a declarative aura.json manifest, allowing websites to expose their capabilities as a secure, efficient, and standardized API for AI agents.

This is the source code of "Efficient training techniques for multi-agent reinforcement learning in combatant tasks".

[NeurIPS2021] Federated Reinforcement Learning with Theoretical Guarantees. The repo contains code and experiments for our Federated Policy Gradient with Byzantine Resilience framework for improving sample efficiency of RL agents.

A caching solution for asyncio

3-tier agentic ChatOps (n8n + GPT-4o + Claude Code) implementing all 21 patterns from "Agentic Design Patterns" — solo operator managing 137 devices