Custom agents

Claude Code skill pack: edit short-form videos end to end — style-clone a reference reel, build a branded motion-graphics edit, ElevenLabs sound design, frame-level QA, timeline-comment review loop

Open-source Canva alternative — design editor for social media graphics. Fabric.js + Preact + Hono + SQLite. Part of the OpenClaw ecosystem.

FACET (Feature‑Aware Contracted Extension for Text) is a human‑readable, machine‑deterministic markup language for AI prompting, orchestration, and tooling

Ready-to-use customizable multi-agent AI system with Telegram integration. Combines plug-and-play simplicity with framework-level flexibility.

Multi-agent pathfinding via Conflict Based Search

Build autonomous AI agents for the Zero-Employee Enterprise (ZEE). Create intelligent, context-aware agents with unprecedented ease and functionality.

The simple yet powerful long-term memory manager between AI and you💕

Apple developer docs and WWDC transcripts with RAG retrieval and Jev relevance ranking.

A live benchmark and evaluation framework for open-ended deep research in the wild.

Designing Multi-Agent Systems with Zero Supervision

Autonomous executive assistant with persistent memory and a multi-agent architecture

Source codes for paper "MACRec: A Multi-Agent Collaboration Framework for Recommendation" at SIGIR 2024

A Simple, Distributed and Asynchronous Multi-Agent Reinforcement Learning Framework for Google Research Football AI.

A library of components to help agent builders boost their agent performance (tool-calling, instruction following, policy, etc.)

Personal Overnight Helper Agent. Runs while you sleep. Serves up a morning brief before your alarm.

Self-Hosted AI Agent for Kubernetes & DevOps. Approval-Gated. Deterministic Control Loop.

⚡ A local, privacy-focused AI desktop assistant for Windows. Control your PC remotely via Telegram or locally with Voice commands. Powered by Ollama.

Hyprdots, Hyprland Omarchy, Quickshell, Agentic Local-Ai, Custom Integrated, Minimal

AI Agent Skills for Security Auditing to generate triaged, industry grade report findings, code locations, pocs, attacker story flow graphs and more

Iron man inspired Personal virtual assistant

Your personal CTO Team for Claude Code . These Subagents will help you challenging yourself while you plan and execute.

🤖 Autonomous Solana trading bot with transparent execution

Private Skill distribution platform for AI coding agents: publish, install, update, and rollback team skills across Cursor, Claude Code, Codex, and OpenClaw with a minimal server + skb CLI.

Small response modes for AI agents when your head is in a different state.

Agent OS: keep specialist agents in a hub, spin up a temporary orchestrator per task. Local-first, works with any model.

hyperliquid ai trading agent with LLM models

Self-hosted AI SRE for Kubernetes — zero-instrumentation eBPF observability plus a copilot that fixes issues through guardrailed, self-verifying actions. BYO-LLM, air-gapped capable.

A Simple Baseline for Video World Models with Memory

Dynamic Workflows for hermes

A comprehensive Python learning repository!Easy reading of learning documents:

Console is a private, native Android app for your self-hosted Hermes Agent: chat that shows the agent's work, voice, bots and rooms, cron, tasks, models and an SSH terminal. One code to connect. No account, no telemetry. GPL-3.0.

Turn photos into source-faithful editorial artworks with an Agent Skill — adaptive layouts, controlled abstraction, and a Strict Fidelity composition path.

An AI Agent tool to automate Android devices reliably

One window for all your AI coding agents. Run Claude, Codex, OpenCode, Gemini, Antigravity, Cursor, and Copilot side-by-side. Terminal and chat, any layout.

Local-first agent platform: board + role agents + agent CLI runs (Claude Code, Cursor, Antigravity, OpenCode) or local and API models (Ollama, LM Studio), all on your own Pc

动手学大模型全栈：CS336 中文精讲 · PyTorch 手搓 Transformer · 单卡复现 Pretrain/SFT/LoRA/DPO/GRPO/RLVR · PEFT/Agent/RAG 落地（含真实实验、曲线与复现脚本）

SparkWork is a local-first desktop Agent workbench for professional development and complex work. Orchestrate workflows, collaborate across Agent sessions, route tasks to the right models, and extend the workspace with custom tools and apps. Reviewable, steerable, reversible runs on macOS, Windows and Linux.

基于麦当劳中国官方 MCP 的营养搭配工具：套餐逐件展开求官方营养、官方计价并标出每个金额的价源、取不到就如实标"未知"而不填 0。离线可跑，无需 Token。不提供下单能力。

An efficient durable harness for collaboration across people, models, and devices

Generate publication-ready, editable draw.io figures for research papers from a methods section, using LLM agents.

Open-source agentic security operations platform:

Nohrs Explorer: Develop a fast, flexible, and extensible file explorer using Rust and gpui as a modern alternative to macOS Finder, aiming to deliver a seamless, high-performance interface and AI agent capabilities that surpass those of claude cowork.

Template to quickly start working with Bee Agent Framework.

DBpedia Chatbot

🚀 FaasJS is an agent-friendly full-stack TypeScript framework for building predictable, type-safe applications with minimal dependencies.

🤝 The code for "Can Large Language Model Agents Simulate Human Trust Behaviors?"

An operating system built for AI agents — talk to your NixOS server instead of SSH-ing in. Typed, audited tool access with atomic rollback on every change. Research-grade; run it on a disposable box, not production.

Frontend AI coding agent platform with CLI, VS Code extension, desktop app, MCP server, RAG planning, Skills, SDD guardrails, browser automation, and LoRA planner models | 面向前端工程的 AI Agent 平台，支持 CLI、VS Code 插件、桌面端、MCP 服务、RAG、Skills、SDD、浏览器自动化与 LoRA 规划模型

Cursor-style Debug Mode skill for coding agents. Hypothesis-driven debugging with runtime log instrumentation and autonomous verification, with human fallback.

Run OpenCode Agent on Kubernetes

Фреймворк агентной разработки на 1С

You've heard Claude Code can do amazing things. Skills, hooks, agents, memory systems — but who has time to figure all that out? Claude Prime sets it up for you in one command.

Open-source desktop and web coding agent with a first-party host and harness, durable sessions, model connections, streaming chat, and workspace tools.

An LLM-powered agent for Datasette

多Agent智能广告投放与优化系统 | Python/Java/Go三语言实现 | 面试项目+八股文+STAR话术 | LangGraph + ClickHouse + Streamlit

A web-based AI workspace with a local execution daemon, with an emerging control-plane architecture for remotely operating AI coworkers across machines.

Build faster with an Agentic Workforce. Safe, secure, and compliant is now the default.

Top Agent Swarm Simulation Tools for LLM World Modeling 2026

Login-less, bring-your-own-key desktop agent that turns plain English into browser automation — and generates runnable Playwright, Cypress, and Selenium scripts.

Stop re-explaining yourself

Agent Deck

AI-powered mobile automation agent — describe what you want in plain English, AppClaw reads the screen, reasons, and acts. LLM-agnostic, open-source, zero telemetry.

The Autonomous AI Writing Agent — a secure, author-focused AI for fiction and nonfiction authors (Planning, Revision, Promotion, and more)

Multi-agent department framework for long-form complex tasks, fighting AI hallucination, validated on academic research. 共识管线：多智能体部门长线任务解决框架，对抗AI幻觉，以学术研究为验证场景。

Kernel-enforced authority and spend platform for AI agents

Governed, provenance-sealed creative rendering for Databricks — a Streamlit App + Unity Catalog ai_render() function that turns any governed source (Sample Lakehouse, UC, Genie, or BYO data) into infographics, reports, decks, video briefings, music, and podcasts.

Local-first A-share research workbench for DeepSeek Harness: market dashboards, watchlists, valuation, four investor agents, versioned reports, and continuous post-report chat.

🌊 34 free curated AI models (up to 1M context) for Oh My Pi & Pi. Thin by design — model list, relay proxy, tool-call diagnostics — add your own relays to spread requests across more IPs.

Open-source Edge side-panel agent that filters jobs, matches your resume with AI, and applies only after human review.

Small local-first agent kernel: bounded tools, reversible edits, auditable runs. CLI + Web, Ollama + compatible APIs.

基于麦当劳官方 MCP 的对话式 AI Skill，支持餐品推荐、门店比价、优惠查询、营养计算和探索记录，并通过 Python 生成体素风格分享图片。

A HUD for Claude Code, Codex and 16 more coding agents. Know your quotas, tokens and sessions at a glance, answer requests and jump back in one click. On your screen, phone and watch.

A Discord Bot for chatting with LLaMA, Vicuna, Alpaca, MPT, or any other Large Language Model (LLM) supported by text-generation-webui or llama.cpp.

Simple cross-LLM AI Agent library

Messenger chatbot builder for Node.js. https://intelligo.js.org

DeepRolePlay is a groundbreaking multi-agent role-playing system that completely solves the character forgetting problem of traditional large language models through Agent collaboration mechanisms.

Variant calling tool for long-read sequencing data

A framework for generative software.

mini-OpenCode is a lightweight experimental Coding Agent inspired by Deer-Code and OpenCode. It explores how LLMs can plan, reason, and iteratively write code with minimal infrastructure, aiming to provide a simple, hackable foundation for understanding and building agentic coding systems.

BEAM-native personal AI agent built on Elixir/OTP. Runs on your hardware. Your data stays yours.

Community-based extensions for the python-telegram-bot library.

A framework for evaluating AI audit agents using recent real-world data

Sample App using Agent Framework for analysis of investment opportunities.

PATIENT-Ψ: Using Large Language Models to Simulate Patients for Training Mental Health Professionals (EMNLP 2024)

CLI Tool for 8k context ai models

A unified CLI for discovering and invoking tools across OpenAPI, MCP, GraphQL, gRPC, and JSON-RPC

A Survey of Personalization: From RAG to Agent

Production-grade Claude Code configuration: skills, agents, hooks, rules, and permissions working as a system.

Local-first RAG memory for AI agents: hybrid + GraphRAG search, MCP server with OAuth 2.1, plugin for Claude Code / OpenCode / Codex.

Fully autonomous and agentic lorebook, tracker, and summary retrieval for SillyTavern!

AI-powered biologics design campaign agent — multi-agent orchestration with BoltzGen, PXDesign, Protenix, and 200+ cloud tools. Antibodies, nanobodies, de novo binders, and beyond.

Declarative AI pipelines in one YAML file. Tokens, audio chunks, and video frames flow between isolated components. Compose 100+ components for models, agents, speech, vision, and live broadcast. Run local models, cloud APIs, or both. Inspired by docker-compose.

基于 [Andrej Karpathy]提出的 [LLM Wiki 模式]构建的 Agent Skill，通过四阶段流水线将碎片化信息转化为结构化、可检索、持续增长的个人知识库。

Edit Videos and Design Images with Claude code or Codex

Curated tools, official sources, OSS, templates, and guides for EU AI Act compliance.

AI Coding Agent Multiplexer

DexPaprika MCP server for real-time crypto token data, DEX trading activity, and DeFi analytics across multiple blockchains.