Custom agents

BIM LLM Code Agent with Vector and Graph RAG

Agent-driven Android ANR evidence extraction and AI-assisted root cause analysis pipeline.

local-first MCP discovery runtime for agents — search before invoke, reduce prompt bloat, and route to local MCP tools

A modern, user-friendly terminal emulator designed to enhance your AI pair‑coding experience.

Security scores for 800+ MCP servers. 9 analyzers scan for prompt injection, toxic flows, and attack surface risks. Updated daily. 🛡️

CLI/TUI app to easily detect, manage, install, and update AI Agent CLI tools

Multimodal-LLM Based AI Agent for Schematic Generation of Analog Circuit

Zero-config local LLM optimization for Ollama, LM Studio, and Apple Silicon MLX. Reduces TTFT by 40%, wall time for local agents by 46%, and RAM usage by 3x.

Robinhood portfolio advisor skill for Hermes Agent, OpenClaw, Claude Code, Codex, and other MCP-compatible AI agents

The goal of this project is to create a modular Agentic Python framework for robotics that can be used to develop specific robotic applications for various types of robots, IoT, and physical devices. The initial focus will be on the hospitality sector, with a longer-term focus on transitioning to consumer usage such as household tasks.

A team of specialized Swift agents for Claude Code. Swift 6.2 concurrency, Apple Foundation Models, on-device AI, SwiftUI, accessibility, security, testing, and App Store compliance — enforced on every prompt.

A forkable Next.js template featuring a design canvas UI with AI integration. Build your own Canva, Figma, or tldraw alternative.

Simple Social Agents powered by Claude Agent SDK

Cancel-aware Rust framework for building Model Context Protocol (MCP) servers and clients: tool, resource, and prompt abstractions over stdio, HTTP, and SSE transports, with asupersync capability contexts for cooperative cancellation.

Open-source health AI agent platform for self-hosted health questions, personal health data, personalized Nutrition for Metabolic Health, AI meal planning, Telegram chat, and Apple Health sync.

Browser engine for agents. HTML in, structured Semantic Object Model out. Native MCP and AWP with a supported CDP subset. Apache-2.0.

Agent-readable skill files for Internet Computer (ICP) development. Prevents AI hallucinations.

orcv is an infinite canvas of virtual desktops for visually orchestrating many tasks at once

🐙 Admin console for the OCTO platform — manage tenants, users, spaces, channels, and Lobster agents. Built with React, TypeScript, Vite & Ant Design.

MCP server for Outlook email, calendar, and contacts — let your AI assistant manage your inbox directly from the conversation.

基于本地 RAG 与大模型人格蒸馏的多平台聊天记忆系统。通过 FTS5 检索、语料清洗与长期报告生成，将聊天记录转化为高拟真的数字分身。

为 Cline、Codex、Claude Code、Droid、OpenCode、CodeBuddy、ZCode 和 Qoder CN 提供 obra/superpowers 的中文友好适配，支持中文触发、中文文档输出和更稳的安装更新体验。

Cross-vendor agent-to-agent protocol — Claude, Codex, and Gemini communicate via file-based P2P messaging.

WaSP — WhatsApp Session Protocol. The missing infrastructure layer between WhatsApp and your application.

🛡️ DeepSentry 是一款本地 AI 安全应急与智能运维 Agent。支持本地、SSH、Telnet、FTP、Fleet 与 WebShell，用自然语言完成巡检、日志分析、授权演练和事件处置；可从微信、QQ、飞书等聊天渠道指挥，并生成可审计的 Markdown / Word 报告。

AI-powered FinOps and InfraOps agent for Azure. Replace a multi-week assessment with one conversation: maturity scoring, quantified savings, CFO-ready deck, ready-to-run remediation scripts. Read and write on your behalf, never delete.

AI-powered bid analyzer — 100页招标文件10分钟读完，投标文件自动审查零遗漏

Agent native CLI for querying ChatGPT Pro and Deep Research through your own logged-in web session, managed from your terminal.

Run AI coding agents in sandboxed containers communicate via ACP

Turn any folder or Git repo into safe, token-efficient context for LLMs, AI chats, and coding agents like Claude Code, Codex, and Cursor — local-first GUI, TUI, CLI, and a read-only MCP server with Live Context, agent journal, Smart Ignore, secret/PII redaction, Git scopes, and code compression. Windows, macOS, Linux.

轻量白盒多智能体平台 —— 可视化编排工作流，多 Agent 协作，高精度知识召回，企业级权限管理，统一对话管理。支持低成本嵌入第三方系统，200MB 低资源即可运行。

One-click deployment for OpenClaw + KasmVNC. Browser-based remote desktop with full container lifecycle management.

Data Curation Tool is a local-first dataset curation, tagging, model-management, downloader, 3D generation, media metadata, and tool-orchestration application. The current documentation set is stored in docs/wiki/

专注于crypto策略交易的AI Agent

Open-source runtime attribution and context observability for data access by AI agents and applications

PostgreSQL SKILLs for AI Agent

Interactive visual analytics for Claude Code sessions, costs, context usage, and agent workflows

filesystem as an agent framework based on LangGraph. Built for python users

A Serper MCP Server

A dependency-free Python genetic-algorithm engine with pluggable fitness criteria — the reusable search core for an LLM/AI autoresearcher.

LLM Agents Can See Code Repositories [ASE 2026]

ClinicalAgent: Clinical Trial Multi-Agent System with Large Language Model-based Reasoning. BCB '24: Proceedings of the 15th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics.

A comprehensive, step-by-step guide and code repository for building autonomous AI agents from scratch with zero framework dependencies.

Agent-native disposable email — Cloudflare Workers + Durable Objects, with CLI & MCP. https://smails.dev

A constitution generator for autonomous, agent-run projects: an interview-driven meta system prompt (and installable skill) that scaffolds a CEO-orchestrated sub-agent + skill + CLI architecture. Presented by MacroAlpha.io and Leowang.net

Agent3σ-Canary is an evaluation framework for AI Agent security in realistic runtime environments.

Self-hosted AI agent memory server with MCP, evidence provenance, typed claims, conflict detection, embeddings, recall, PostgreSQL, and pgvector

Single-file, zero-dependency AI coding agent for the terminal.

Omnigentx Jarvis — voice + chat AI assistant powered by Fast Agent (MCP) with Vue dashboard. Single-user, self-hosted, multi-skill orchestration.

Contains clause skills that can be installed to AI agents.

Agentic Reinforcement Learning 101. A pragmatic course for AI/ML Engineers based on "The Landscape of Agentic Reinforcement Learning for LLMs: A Survey" https://arxiv.org/abs/2509.02547

Agent Skills for Robot Framework

Spec Kit writes WHAT. Superpowers enforces HOW. Thin handoff bridge for Codex and Claude Code.

外贸主动获客 Codex Skill：支持一句话找客户、产品图片找客户、客户线索质检、表格输出和批量个性化开发信。

Homekit gives any AI agent direct, physical control over Apple Home. Flip lights. Lock doors. Read sensors. Through a single open interface.

Open-source, self-hosted personal travel app by Giovanni Brees - keep every flight, hotel, ride and trip on one living timeline. Built with AI agents, runs on Cloudflare Workers.

Django manage.py context for coding agents — and tab completion for you

Native AI inference for PHP 8.3+ - run ONNX, GGUF (llama.cpp) and RubixML models directly in your PHP process via FFI. Chat, streaming, embeddings, RAG and vector search. No Python, no HTTP microservices, no Docker sidecars.

Python SDK for Programmable Multi-Agent Orchestration

一个人格 AI Skill 实验：别人垂直赛道，我垂直人格。

Agent-native graph orchestration for Codex, Claude, and skill-compatible agents

MCP tool that leverages your agent's LLM to document what happened during your current session, in a specified user folder.

ThreeJSON is a JSON-driven declarative scene runtime for Three.js, designed for persistent, mutable and extensible 3D worlds — from human-authored scenes to AI and Agent-driven generation and control.

FRP-based LLM agent framework with git-like memory model.

BCI-assisted neurodivergent productivity suite — self-reported or EEG-driven cognitive metrics + an agentic AI task planner (Claude) that adapts to how your brain is actually performing.

MUSE-Autoskill - A self-evolving LLM agent that builds, tests, and reuses reusable skills — getting smarter with every task.

LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents

Autonomous multi-agent orchestration engine for software repos — L0/L1/L2 agents, leases, gates, audits, git-worktree isolation. Detached dispatch by default. GPL-3.0.

Spec-driven development (SDD) CLI for AI coding agents (Claude Code, Cursor) - initialize, validate, and sync .specs/ across TypeScript & Node.js projects

AI Reputation Manager for Claude Code. Analyze online reviews, score brand sentiment, benchmark against competitors, generate review responses, create crisis playbooks, and produce PDF reputation reports — 14 skills, 5 parallel agents.

Agent skill that helps Claude Code, Codex, Gemini, and Cursor write correct Swift App Intents code for Siri, Shortcuts, Spotlight, widgets, Control Center, and Apple Intelligence.

Web dashboard for OpenSpec — one kanban board across every repo, showing which artifact is next and what is blocked. OpenSpec 1.6 compatible.

Self-host AI companion platform — characters with schedules, memory, and a life of their own (BSL 1.1)

AI工具集导航收录了国内外数百个不同类型的AI工具，每日更新和添加最新AI工具，AI工具集还推荐了AI学习开发的常用网站

Production-grade software delivery for coding-agent teams on Multica — dynamic planning, deterministic execution, verifiable delivery.

🚀 $150k+ Polymarket Trader & Developer: Polymarket Trading Bot • AI Agents • GameFi • Provably Fair Casinos • DeFi

Velane is agentic cloud for deploying your basic workflows, agents and sub-agents. 800+ OAuth integrations, sandboxed Bun and Python execution, and a full deployment pipeline managed via MCP

Get your repo ready for AI.

One native macOS supervisor for every local development server.

Whitebox & Blackbox AI red-teaming framework for LLMs & Agentic AI apps. It analyzes your app's source code to discover tools, roles, and guardrails, then generates new attacks chains across several categories and adapts over multiple multi turn rounds to find vulnerabilities

A fully transparent in-editor agentic harness for large language models inside Godot Engine. Connect to any LLM provider via API (or use your ChatGPT sub) and provide your agents the tools, context management, and guidance to effectively complete most tasks in Godot. Every action the agent takes is fully surfaced and persists in session history.

Build UI apps with your AI assistant — together, live. An agent-native, cross-platform declarative-UI runtime in Go: describe UI as JSON, let your AI scaffold/edit/verify it over MCP, package for web/iOS/Android/desktop/mini-program.

Multilingual source-grounded research workspace with agentic RAG, cited chat, podcasts, PowerPoint, and video.

AI Agent - It can book rides, order food, post tweets and also control basic tasks on device.

ARIES is an open-source experimentation framework for agent serving systems research.

Autonomous AI research: an LLM agent searches for the best algorithm to fit the Mandelbrot set.

给AI伴侣增强时间感的小器官（电脑端专用）

A flexible, production-ready agent orchestration system that enables multiple specialized AI agents to work together to solve complex tasks through coordinated execution with proper concurrency handling, retries, and timeout management.

Agent Skills that teach AI coding agents how to build applications with the Genkit framework (JS/TS, Go, Dart).

Android device bridge for Claude Code via MCP + Shizuku. No root, no model polling.

High-performance zero-dependency static analysis tool enforcing NASA Power of Ten rules across 20 programming languages, plus AI agent skill, MCP server config, prompt template, and LLM model security auditing.

AI agent skill bundle for Storybook on React + Vite — audit real-vs-slop components, capture flows, write CSF3 stories, ship. Claude Code / Codex / Cursor.

Rigol Scope MCP for use in Claude Code, Cursor, Codex etc. for agentic electrical engineering

dsh-agent-team gives DeepSeek Harness agents that don't reset: durable Members with their own memory, notes, and skills across sessions, rollovers, and restarts. You set the direction; agents coordinate through Channels and Tasks.

Forge Agent is a free, autonomous AI coding agent that requires no API key or subscription. It uses browser automation to communicate with any web based AI assistant, turning it into a fully autonomous coding agent that can read files, write code, run terminal commands, search codebases, and build complete projects from a single prompt.

Stop your AI coding agent from reinventing the wheel. A Claude Skill that checks Free vs. Build vs. Buy before writing code, and actually vets what it finds (license, maintenance, security) instead of stopping at star count

Community-curated DeepSeek Harness (dsh) plugins, tools, skills and learning resources. Searchable bilingual directory | DeepSeek 插件、工具与技能精选

AI-assisted coding setup that helps you spend less time re-explaining context, and more time shipping with better output. Includes a custom spec kit, memory, agent and skill framework.

🛡️ 大模型攻防渗透测试靶场 · 提示注入CTF / OWASP LLM Top10 / 脆弱Agent / 资料聚合。目标模型可切换：DeepSeek直连、OpenRouter中转站(国产+国外十余款小模型)、本地Ollama(DeepSeek-R1 8B离线)。一键本地部署。