Custom agents

Agent-native LLM, RAG and Agent knowledge system with traceable Markdown, MCP tools and MkDocs.

arcade/ 游戏大厅 A lightweight framework for text-based simulator games played by AI agents. Share energy, gold, and trophies across multiple games. Drop in a game directory, write a cmd(text) function — done. 一个给 AI 玩的文字模拟器游戏框架。跨游戏共享精力、金币、奖杯系统。把游戏放进目录，写一个 cmd(text) 函数，就接入了。

Persistent memory for AI coding agents — SQLite + FTS5 + vector search in a single file

🔁 Write loops, not prompts. Free skill that generates overnight autonomous AI runs for Claude Code, Codex & Cursor: master prompt, plan, verifier, one command. By AI Guy Official.

Archived first-generation Claude Code framework with agents, commands, rules, templates, and MCP integrations.

Cyberful is an open-source application-security workbench for discovering, exploiting, verifying, and remediating vulnerabilities.

AI-Powered Multi-Agent Crypto Investment Analysis Platform

The complete collection of Kiro IDE configs, agents, skills, hooks, and MCP integrations for maximum productivity.

An agent-native workspace for quantitative research: an in-terminal notebook, a high-performance time-series database, and a high-throughput backtesting engine. Written in Rust.

Run one AWS CLI command across hundreds of AWS accounts in parallel. MCP built in for AI agents.

JanSahayak AI – A multilingual AI assistant that helps citizens understand and access government welfare schemes through conversational voice and chat.

VexFS is a Linux kernel-native file system with built-in vector search and semantic memory. Designed for AI agents, RAG, and LLM workloads, it merges POSIX storage with vector-native indexing. Built in Rust, bootable via QEMU, and engineered for AGI infrastructure.

🍞 记得住、学得会、能进化的个人 AI 助手。持久分类记忆 · 闭环经验引擎 · 子代理并行 · 长任务不漂移 · 9 大平台 · 4 类 LLM · MCP 生态 · 桌面自动化，只有你需要的轻量。｜ The AI assistant that remembers, learns, and evolves. Persistent memory · Experience engine · Sub-agents · 9 platforms · 4 LLM providers · MCP tools.

Simple code sandbox supporting jupyter notebook style code execution. Used for agent training

Multi-Agent Deep Reinforcement Learning for Large-Scale Traffic Signal Control

基于 EdgeOne 的自托管免费微信推送与标准 MCP Server，支持 Agent / IDE、Webhook 风格 API、多应用和订阅群发。Self-hosted free WeChat push service and standard MCP server on EdgeOne, with Agent/IDE support, webhook-style API, multi-app support, and subscription broadcast.

Rapidly build a multi-Agent management dashboard based on Claude Code, integrating daily work and remote IM collaboration. It includes Claude Code monitoring, channel configuration and message notifications, with a Codex GUI optimized for non-technical users.

🔧 LRA - AI Agent长任务超稳定执行框架 ⚡ 轻量 | pip一键安装｜突破上下文限制 📌 7种状态管理 | Long-Running AI Agent Framework • One-click pip install｜Break context barriers • 7-status management. 5.0全面支持CLAUDE/OPEN CLAW/OPEN CODE/CUSOR/TREA 等全部Agent编程工具，仅需运行 lra init命令，就会生成Agent.md/CLAUDE.md/lra.md. 你的agent会自动学会如何使用

Research Harness for Claude Code. Keep your agent grounded in context, not lost in vibe coding.

University AI Agent and GPT

Converts skill/framework documentation into compressed AGENTS.md indexes for AI coding agents. Based on Vercel's research showing AGENTS.md achieves 100% pass rate vs 53% baseline.

The DeepSeek-native Agent Framework

The declarative reasoning layer for AI agents. A portable, framework-agnostic file format for specifying how an agent thinks — strategy, step DAGs, contracts, quality gates, and fallback policies — declared in YAML rather than hardcoded in Python.

Private, local-first AI "life OS": any model per life-domain over a markdown vault on your machine. Council mode, open source (GPL-3.0).

Drop-in skills that stop AI coding agents from shipping garbage — kill-slop, security-review, PR hygiene

Resources for building and deploying agents using Claw and agent harness in Microsoft Foundry — patterns for agent orchestration, testing, and production deployment. From Microsoft Build 2026.

Claude Code iMessage MCP channel. Text with blue bubble, Apple-native iMessage to work on your Claude Code sessions. Open source for developers, purpose-built on top of the Claude docs "Channels reference" guide.

CLI and AI agent skills for the Tokenomist crypto data API: token unlocks, vesting, emissions, allocations, fundraising, burns and buybacks.

A local-first second brain for scientists, researchers, coders, and nerds.

Local pre-flight linter and architecture gate for AI agents. Uses tree-sitter, Stack Graphs, and Datalog to mechanically block structural drift, layering bypasses, and scope creep on virtual ASTs before code changes land.

MCP-first AI foundation for TYPO3. Bring AI agents into TYPO3, on your terms.

Real-time observability dashboard for AI agent runs: live task progress, journal events, and orchestration state. Published on npm.

European Parliament MCP Server - Political intelligence for AI agents

MCP server and CLI for connecting AI agents, OpenClaw/Hermes workflows, local automation, and coding harnesses to your RemNote knowledge base via the RemNote Automation Bridge.

Convert AI coding sessions between Claude Code, Codex, OpenCode, Zed, Aider, Gemini CLI, Cursor, Cline & more — lossless, round-trip tested. MCP server + CLI.

Bootstrap a fully personalized Obsidian vault with AI. Interactive onboarding, document ingestion, and automatic knowledge base generation for Claude Code and compatible AI agents.

A cognition kernel that wraps a frozen LLM in a persistent identity + trust + governance loop — testing whether capability comes from structure, not weights. Research-stage; honest about what's real vs mocked.

Local dashboard to run parallel Claude Code & Cursor agents — kanban fleet view, one permission inbox, in-app diff review. macOS, MIT.

The terminal workspace for AI coding agents. Run dozens of agent sessions on a 2D canvas. macOS.

Clint is the AI Era Outreach System. It is a Python library and CLI (Command Line Interface) designed for production-grade lead discovery, evidence-based personalization, and safe outreach automation. It bridges the gap between raw data scraping and personalized human-like communication.

Log Claude Code sessions to Opik, the open-source LLM observability and evaluation platform, built by Comet. Tracing, evaluation, and skills for observable AI applications.

SQL queries for CSV files. The analytical CSV query engine for AI agents cli: csvql.

A centralized cross-platform cheat sheet for Git, Linux, macOS, and Windows terminal commands, shell scripting, and AI agent setup guides.

The AI Autonomous SOC & Purple-Team Engine

An open standard for discovering the legal context of agentic commerce transactions.

A kanban board for managing projects with tickets, columns, labels, and activity tracking — designed to be driven by AI agents via its API.

My daily AI agent skills for Claude Code, Codex, frontend QA, reviews, and workflow automation.

Governance-grade, OKF-compatible knowledge-base format with a single-writer MCP server and CLI. Pre-release.

The first Algorithmic Trading DePIN. Get paid to trade via Proof-of-Trade mining & Swarm AI. A self-hosted visual crypto bot with a No-Code builder.

Embedded long-term memory database for AI agents & LLM apps. Six-layer cognitive architecture, knowledge graph, hybrid BM25 + vector search, sleep-time memory consolidation. One .meh file, zero infrastructure, pure Go.

A minimal CLAUDE.md template that turns any LLM CLI into a personal knowledge base. Drop in one file, start ingesting articles. Karpathy's LLM Wiki pattern.

Open-source, token-frugal agents for real teams — private memory, shared packs, your hardware.

Personal knowledge vault plugin for Claude Code — session recording, memory distillation, and hybrid semantic + BM25 retrieval.

Agent-assisted vulnerability research across Rust, Android APKs, and AI agents: independent discovery, skeptical triage, verification, and patch review.

The tested, tool-agnostic AGENTS.md kit — verified templates, a CI linter, and migrators from .cursorrules/CLAUDE.md/Copilot/Windsurf/Cline/Aider.

CLI and a Chrome Extension designed for you to review AI generated code locally and on GitHub PRs

Open-source continuation of Daytona — secure, elastic sandbox infrastructure for AI code execution and agent workflows. Community fork of the last AGPL-3.0 release (v0.190.0).

Portable, self-contained sandboxes for AI coding agents - microVMs, containers, isolation harnesses.

Agentic Theorem Prover for Rocq for Program Verification

Typography skill for AI agents - audit and produce publication-grade text. Butterick's Practical Typography for your coding agent.

Elixir SDK for Fly.io Sprites: computers for agents. Manage Sprites and run remote commands from Elixir, with APIs that match the language's conventions.

Discover and connect with GitHub developers who actually match your stack — powered by social graph traversal, repository analysis, similarity scoring, ML followback prediction, and a modern analytics dashboard

Turn an economics paper into a seminar-ready Beamer talk with a timed speaker script — conference, job-market and discussant slides. Agent Skill for Claude Code & Codex.

A local-first permission firewall and approval layer for AI agent tool calls.

Lightweight and Effective Preference Construction in PIBT for Large-Scale Multi-Agent Pathfinding (SoCS-25)

Kubernetes operator for Gas Town multi-agent orchestration. OpenShift-native, FIPS-compliant.

Collection of useful skills for Claude Code - AI agents, frontend design, and more

A personal AI operating system built on OpenClaw/Claude Code, MCP servers, and structured markdown. Feedback RL, voice cloning, Screenpipe integration.

This framework provides the architecture, assets and samples for creating own virtual agents, also called non-player characters (NPCs), in Unity.

MCP server exposing financial data using Yahoo Finance via yahooquery. Provides stock insights, historical prices, earnings, recommendations, and ownership info. Built for Zentickr AI tools and compatible with research agents or financial copilots.

Write social cards as React components — tooka renders 1080×1350 carousels, exports IG-ready PNGs, and one-click publishes to Facebook, Instagram, and Threads.

The framework for building stateful agents. Your agent is a folder of state, served over MCP, used from any runtime.

Let AI agents manage your Zotero library: headless CLI + Python API to search, import, enrich, export BibTeX, and attach PDFs (Web API + WebDAV) — no desktop app required. Ships with an agent skill & AGENTS.md.

AI agent workflow platform — visual flow orchestration, drag-and-drop forms, knowledge base RAG, multi-model LLM, digital workers, Tauri desktop & DingTalk bot. Open source, self-hosted.

Multi-account email MCP server for SMTP sending, IMAP search, replies, attachments, and inbox organization

MCP server for Rockwell/Allen-Bradley Studio 5000 — parse L5X project exports and give AI agents structured access to PLC tags, UDTs, routines, and programs.

AI agent system designed to help solo founders build and ship products efficiently

Manage, review, and migrate cloud AI agents with Git and YAML. The open-source IaC control plane for managed AI agents.

Give every agent session its own VM. One command up, zero burn when idle.

🛠️ Awesome ADE — a curated list of open-source Agentic Development Environments: orchestrators, TUIs, tmux harnesses, sandboxes and the agents they run.

一个基于FastAPI和React的智能体系统，支持多智能体管理、mcp管理、知识库、聊天对话等功能。An intelligent agent system based on FastAPI and React, supporting multi-agent management, mcp management, knowledge base, chat dialogue, and other functions.

API-based skills for AI coding agents — one contract that works with Claude, Codex, Cursor, OpenCode, Gemini, Windsurf and Pi, and any MCP host.

This is a single NeuroDynamic Brain that can be adaptable across the agents , just point your claude or any agent session to load it one time.

An OpenClaw-based agent framework designed for college students.

Agent-ready portfolio of Ruben Marcus, AI Fullstack Engineer. A cinematic WebGL site for humans and a protocol surface for agents: a remote MCP server (io.github.rubenmarcus/portfolio, on the official MCP Registry), a public Agent Skill, llms.txt and a plain-text resume over curl. Built with Astro 5, Svelte 5, Three.js and GSAP.

Local semantic project map with live agent work and session navigation

命理圆桌会 · A multi-school Chinese BaZi (Four Pillars) roundtable reading skill for Claude

Run AI agents in Zulip as @mentionable bots — or wire into any MCP client.

Your AI coding agents keep working while you sleep. Drive Claude Code, Codex, Gemini, opencode & more from your phone: resume past usage limits, hand off between agents, loop until tests pass. Self-hosted, zero deps.

Orkestrai is a visual orchestration tool for teams of AI agents that can work ranging from ideation, planing, architecture, design, devops, content creation and marketing..

Package manager for AI agent assets — 42 skills, 5 CLIs, 1 plugin. Skills for AI/LLM agent engineering, eval-driven dev, spec-driven dev, database (MySQL/PG/Redis/Kafka/Mongo/Oracle/NL2SQL), K8s/Docker diagnostics, infra ops (Dify/Nexus/Harbor/SonarQube) & docs/patent. Runtimes: Codex, Claude Code, Cursor, Kiro, DSH.

Free NVIDIA DLI course: build, coordinate, and secure AI agents with NemoClaw and OpenShell. Browser-based, no GPU required. Available in English, Spanish, and Brazilian Portuguese.

[ACL 2025] Official respository for EvoPatient: LLMs Can Simulate Standardized Patients via Agent Coevolution

Free universal agent skills for federal contracting: SOW/PWS builder, three IGCE builders (FFP, LH/T&M, cost-reimbursement), OT project description, and OT cost analysis. Portable SKILL.md format, runs on Claude, Codex, Gemini, Copilot, Grok, Cursor, DeepSeek Harness, opencode, and LibreChat. For GS-1102s and small businesses.

One format, two readers. People and AI agents now co-write the same document. Legible for people; addressable, verifiable, and versioned for machines. GEML is plain text — organized by one typed block for everything, remembered by a .gemlhistory sidecar.

A curated list of protocols, specs, SDKs, and tools powering the emerging agentic commerce stack.

Safe, scene-aware MCP bridge for Blender with reversible editing and visual evidence.

温病派大师吴鞠通（1758-1836）中医 Agent Skill。基于《温病条辨》《医医病书》《吴鞠通医案》359 案、《温热经纬》吴氏按语蒸馏。三焦辨证·卫气营血·22 温病方剂·9 诊断公式·凉开三宝·白虎四禁·湿温三禁。与倪海厦 skill 合参互补。TCM Wu Jutong warm disease sanjiao differentiation AI agent skill.