Custom agents

Teach your AI coding agent to run Meta ads: API setup, programmatic campaigns, browser control, and conversion tracking that's actually proven to work.

Open-core registry of animated React components, blocks, design systems, and templates. Real, editable code: install with one shadcn CLI command or let your AI agent pull it over MCP.

git checkout for releases that span many repos. Version tags that restore your whole product. No server, no database, any language.

Turn a video — or an animated GIF, APNG, or WebP — into a timeline of still frames so an LLM can "watch" it as a series of images.

My ongoing WIP 🏗️ AI prompts, custom agents, skills & instructions - curated by me (and Copilot, ChatGPT, and Claude).

AI Image to 3D Mesh Rigging and Roblox Asset API Cost Tracker 2026

MCP server that gives AI agents a real Chrome: Google/Bing search and JavaScript-rendered page fetches over CDP (Linux/macOS).

AI-Powered Roblox Luau Code Execution Server for Live Game Testing 2026

Add a talking 3D AI avatar to any web app. Samples and tools for the Perxona Connect SDK: <sv-presenter> web component, lip-sync, text-to-speech and VRM avatars. Clone to talking avatar in under 15 minutes.

DSH skill v1.0 · Blender 建模与装配流程：多 Agent 分工范式（冻结 spec/写作用域/接口表）、参考图形体还原、六条必踩的坑、十道数值门装配审计；23 条配方；配套插件 dsh-blender-plugin v1.0.0

DSH Android 客户端：内置 Termux 环境跑 Node，在 Node 上跑 DSH 引擎，WebView 加载官方 Web GUI

An autonomous multi-agent IDE for screenplays🎮 & novels📖. One-click to share web performances or drive Unity dialogue systems. Empowering vibe game dev with AI!

Run Claude Code, Codex or any coding agent on any of your computers, and jobs across all of them at once. Free, MIT, no relay, no limits.

BloxAgent 2026: AI-Powered Luau Reverse Engineering and Roblox Script Automation Framework

Linux patch review and testing CLI with a multi-stage agentic workflow

Make videos with your coding agent: pick a style, then point at the frame and say what to change. Works with Hyperframes, Remotion or any video tool, over MCP.

Holdings exposure, what-if scenarios, cost and capacity, backtest checks, and published research.

Semantic CLI tool for process management. Target by port, PID, name or path.

WeVisCut is a 9B tool-using agent that turns knowledge articles and narration scripts into multi-minute videos through planning, asset retrieval, editing, inspection, and repair. Built on Qwen3.5, it operates in a stateful 12-tool workflow and includes an editable Studio runtime.

MCP: Python Tools for Turning AI Prompts into Game Assets

The open-source thread-plane for agents: chat, durable threads, persistence, human approvals, and generative UI for Angular, on LangGraph and AG-UI.

Using tensorflow, this agent can autonomously train itself to play Out Run and potentially be modified to play other games or perform tasks other than gaming

🧠 Simple and easy agent framework, include various of structured data manipulation, agent and function compositing, code editing, fs and more!

以 AI Agent 为核心的智能客服系统。

Microsoft Bot Framework is a wrapper for the Microsoft Bot API by Microsoft

A Neural Network based Chatbot

chatterbot written in es6 (es2015), fork from hubot

Challenges for general-purpose web-browsing AI agents

AI Agent fleet manager for parallel agentic systems like claude code and codex

Smith, also known as Agent Smith

Rust executable for Refact Agent, it lives inside your IDE and keeps AST and VecDB indexes up to date, offers agentic tools for an AI model to call. Yes, it works as a LSP server from IDE point of view.

TypeScript SDK for MCP server observability, built on OpenTelemetry. Gain insight into agent usage patterns, contextualize tool calls, and analyze server performance across platforms. Integrate with any OpenTelemetry ingest service including the Shinzo platform.

AI Document Assistant for PSPDFKit Demo showcases how to interact with PDFs using natural language commands powered by AI, integrated with PSPDFKit for Web.

Discord bot that uses KoboldAI. Supports tavern cards and json files.

[MCP Server] The Security Agent for AI assisted coding

AI gateway and observability server written in Rust. Designed to help optimize multi-agent workflows.

Implementation of Multi-Agent Reinforcement Learning algorithm(s). Currently includes: MADDPG

A pluggable AutoML experiment agent for multi-task hyperparameter optimization

Proxy Claude Code Requests through LiteLLM to Arize

[EXPERIMENTAL] Eidetica-Native AI Agent framework

AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks

Dynamic multi-cell selection for cooperative multipoint (CoMP) using (multi-agent) deep reinforcement learning

Hook-driven multi-agent CLI — one prompt to specs, code, tests, and a shipped release.

Multi-Agent workflow running into a Laravel application with Neuron PHP AI framework

Science-driven chatbot development

Agent Colony for Pi — bootstrap and package distribution for a multi-agent Pi plugin for complex coding tasks.

[ICLR 2025] The offical implementation of "PSEC: Skill Expansion and Composition in Parameter Space", a new framework designed to facilitate efficient and flexible skill expansion and composition, iteratively evolve the agents' capabilities and efficiently address new challenges

[IROS-2025] MAPF-GPT-DDG is a scalable decentralized multi-agent pathfinding (MAPF) solver based on imitation learning. It builds upon MAPF-GPT by introducing a novel fine-tuning method called Delta Data Generation (DDG) — a reward-free active learning approach that identifies and corrects failure cases in the policy.

A local proxy that strips web pages down to clean text before they enter your AI agent's context window. 704K tokens → 2.6K tokens. No LLM required.

[ACL 2025] GUI-explorer: Autonomous Exploration and Mining of Transition-aware Knowledge for GUI Agent

LLM inference in Fortran

A fully simulated business demo built on Databricks — streaming data, AI agents, and apps you can deploy, explore, and extend.

RAG AI Agent with Realtime Source Validation (Human in the Loop) - Built with CopilotKit + Pydantic AI

Multi-session Claude/Codex/Github CLI orchestrator with graph visualization, cross-session context sharing and notifications.

Local AI chatbot for Matrix with infinite personalities, tool calling, and MCP — powered by Ollama

MUA-RL: MULTI-TURN USER-INTERACTING AGENT REINFORCEMENT LEARNING FOR AGENTIC TOOL USE

TUI dashboard for managing AI coding agents (Claude Code, OpenCode, Codex CLI, Gemini CLI) in tmux

Caterpillar is a security scanning library for AI agent skill files (e.g., Claude Code skills) for dangerous or malicious behavior

Iterative specification refinement tool: feeds your docs through GPT Pro Extended Reasoning via Oracle for multiple revision rounds until production-ready

[ECCV 2026🔥] This is the official implementation of our paper "SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning"

Local first Second Brain RAG for any Obsidian Vault (works with any Markdown). Works with DuckDB. Also includes a web-app👇.

MiniMax LLM + Pi05 VLA Robot Agent Demo

The open-source skill registry for AI coding agents. Create, manage, and distribute SKILL.md files across Openclaw, Claude Code, Cursor, Codex, OpenHands, Antigravity, and more.

Offline prompt-contract auditor for Hermes, Claude Code, Codex, OpenCode & OpenClaw. Pre-write guard before agents ship vague code. Zero deps. No model API.

Open source Claude Managed Agents template. Build your own agent.

A self-hosted AI agent built to drop into business workflows: customer ops, internal automation, knowledge retrieval, scheduled reporting. Deploys on a laptop, a workstation, or your own server — never sends data to a third party unless you tell it to.

A composable agent runtime — pair any frontend with any agent backend.

Codebase Context gives AI agents understanding of your codebase through semantic code search, team conventions, patterns, and memory, so they use fewer tokens, spend less time, and produce better, more familiar output.

Agent Knowledge Manager (akm). A CLI tool to manage AI agent knowledge, memories, skills, and more.

Semantic Scholar API wrapper for agents — search 200M+ papers, traverse citations, find authors. Python, rate-limited, multi-agent.

MCP server that lets any llm (i.e. Claude Desktop) delegate tasks to a local Hermes Agent — cron jobs, web search, email, documents, and more.

# 飞书 AI 效率系统 — 20 大工作流 Skill > 基于 Claude Agent/OpenClaw Skill + 飞书 CLI (lark-cli) 构建的个人 AI 效率基础设施。 > 将 Claude Agent/OpenClaw 10 大实战用例完整迁移到飞书生态，适合 Claude Agent Skill 和 OpenClaw，用飞书各模块实现所有工作流功能。

34 AI agent skills for marketing tasks, built for Claude Code and similar AI coding assistants

更新、移植、提取碧蓝档案/蔚蓝档案mod的工具 | Updating&Porting&Extracting Mods for Blue Archive | Steam&Android

Dispatch your task backlog to local, interactive AI coding agents. One git worktree per task, sandboxed by default.

The benchmark tasks and evaluation harness for "PhysicianBench: Evaluating LLM Agents in Real-World EHR Environments".

Agentic AI is the fast evolving technology landscape and this repository is an effort to consolidate the accelerators, frameworks, patterns, and more.

Cross-agent memory for AI coding tools: one self-hostable knowledge graph shared by Claude Code, Codex, OpenCode, Cursor, and the agents you build.

Guardrailed video editing MCP server for AI agents. FFmpeg, Hyperframes, repurposing tools, Python client, and CLI. Local, fast, free.

The whole local AI stack in one executable: it runs and manages local AI models across every GPU, and it's a search engine you can talk to, with cited answers from your files, code, and the web. MCP server for coding agents, web crawler, TUI, CLI, REST API, Python library. No Ollama or LM Studio needed, works with both.

Open source local-first knowledge base maintained by an LLM agent. Implements Andrej Karpathy's LLM Wiki pattern.

AI red-teaming tool and LLM security framework to evaluate agentic AI applications. Tests prompt injections, handles vulnerability assessment, SBOM generation, and static analysis.

An omni-plugin for harness engineering workflows with multi-agents, programmatic gates and skills.

Spec2Case 是生产级 AI 测试用例生成智能体，支持图片/文本需求理解、人工确认、LangGraph 流程编排和 Excel 用例导出。

EGC gives every AI coding agent the same brain. Shared memory, skills, and live context across Cursor, Claude Code, Copilot, Aider, and 29 AI coding tools with zero configuration. Every tab, terminal, and AI stays automatically synchronized. One brain. Everywhere.

Open survey and evidence map for AI agent evolution, self-evolving agents, memory, skills, harnesses, benchmarks, and agent-swarm systems.

Local-first desktop API client built for developers and AI agents

🌊 Security-Driven Hardening: Blue Spec is a defensive workflow to help AI agents detect what your system actually does and harden the defenses that matter, whether you're a developer or not.

Platform-agnostic AI agent: one Full-Stack Software Engineer brain, compiled into ready-to-paste adapters for ChatGPT, Claude, Copilot, Gemini & Cursor. Zero-dependency, MIT.

Make any repo AI-first - write sustainable code from the start, or refactor a legacy codebase to prepare it for agent-driven development.Building blocks for Claude Code: subagents, slash commands, hooks, and workflow patterns. Copy what you need. A working developer's stack for Claude Code.

SUZENT: The sovereign AI agent - own its memory, govern its actions, choose its intelligence, and keep its continuity.

2026 swarm Agent 年，swarm Agent 、Agent team、 ai coding、skill、memory、evolve、agentic RL 等 AI Agent集合

RHO: Evolving Agents in the Dark — Retrospective Harness Optimization via Self-Preference. Improving LLM agents from unlabeled past trajectories (arXiv:2606.05922).

🐬 A pink qFlipper fork with LOTEI — a 100% local AI dolphin (Ollama) that chats, talks, watches your Flipper's screen, and one-click-installs custom firmware.

Grok Build resources, reusable .grok/skills, AGENTS.md templates, hooks, prompts, and starter workflows.

Open-source, voice-first AI mock interviewer. Upload your CV + a job description, practice out loud with an adaptive multilingual interviewer, get scored and coached on your weak areas. LiveKit · LangGraph · Next.js

Find which script, notebook, data, command, or AI agent produced a file — locally, with evidence and honest uncertainty.

Pinecone.io Golang Client

personal entropy reduction system