Custom agents

The Unified Agent Kit for AI-Driven Development - A comprehensive toolkit for software development powered by AI Agents.

AI-powered Excel assistant that lets you query, analyze and visualize data using natural language. No SQL or coding required.

AI Agent Visualization and Runner written in Pure TS

Distributed Heuristic Multi-Agent Path Finding with Communication - ICRA 2021

SigmaRL: A Sample-Efficient and Generalizable Multi-Agent Reinforcement Learning Framework for Motion Planning

无需付费的控制手机并完成你指令的Agent！让Agent帮你操控手机点外卖，打网约车，给微信或者QQ等好友发消息.......解放你的双手！并且无需调用GPT-4o等付费api！

/* JS */ gapi.loaded_0(function(_){var window=this; var ha,ia,ja,ma,sa,na,ta,ya,Ja;_.ea=function(a){return function(){return _.da[a].apply(this,arguments)}};_._DumpException=function(a){throw a;};_.da=[];ha="function"==typeof Object.defineProperties?Object.defineProperty:function(a,b,c){a!=Array.prototype&&a!=Object.prototype&&(a[b]=c.value)};ia="undefined"!=typeof window&&window===this?this:"undefined"!=typeof window.global&&null!=window.global?window.global:this;ja=function(){ja=function(){};ia.Symbol||(ia.Symbol=ma)}; ma=function(){var a=0;return function(b){return"jscomp_symbol_"+(b||"")+a++}}();sa=function(){ja();var a=ia.Symbol.iterator;a||(a=ia.Symbol.iterator=ia.Symbol("iterator"));"function"!=typeof Array.prototype[a]&&ha(Array.prototype,a,{configurable:!0,writable:!0,value:function(){return na(this)}});sa=function(){}};na=function(a){var b=0;return ta(function(){return b<a.length?{done:!1,value:a[b++]}:{done:!0}})};ta=function(a){sa();a={next:a};a[ia.Symbol.iterator]=function(){return this};return a}; _.wa=function(a){sa();var b=a[window.Symbol.iterator];return b?b.call(a):na(a)};_.xa="function"==typeof Object.create?Object.create:function(a){var b=function(){};b.prototype=a;return new b};if("function"==typeof Object.setPrototypeOf)ya=Object.setPrototypeOf;else{var Ba;a:{var Ca={a:!0},Da={};try{Da.__proto__=Ca;Ba=Da.a;break a}catch(a){}Ba=!1}ya=Ba?function(a,b){a.__proto__=b;if(a.__proto__!==b)throw new TypeError(a+" is not extensible");return a}:null}_.Fa=ya; Ja=function(a,b){if(b){var c=ia;a=a.split(".");for(var d=0;d<a.length-1;d++){var e=a[d];e in c||(c[e]={});c=c[e]}a=a[a.length-1];d=c[a];b=b(d);b!=d&&null!=b&&ha(c,a,{configurable:!0,writable:!0,value:b})}};Ja("Array.prototype.find",function(a){return a?a:function(a,c){a:{var b=this;b instanceof String&&(b=String(b));for(var e=b.length,f=0;f<e;f++){var h=b[f];if(a.call(c,h,f,b)){a=h;break a}}a=void 0}return a}});var Ka=function(a,b){return Object.prototype.hasOwnProperty.call(a,b)}; Ja("WeakMap",funct

2024 Alibaba Global Mathematics Competition AI Track Global 2nd Place Project (Agent Universe)

Improved Heuristics for Multi-Agent Path Finding with Conflict-Based Search

Django BM25 full-text search using PostgreSQL - a lightweight Elasticsearch alternative

Visual Test-Driven AI Development for AI Agents

Evaluation package that allows benchmarking of agentic AIs from various sources and frameworks by producing statistical results which can be compared across different use cases and datasets.

KUNO CMS A full-stack blog application with Go backend and Next.js frontend, containerized with Docker for easy deployment.一个i18n的CMS系统

Airut is a system for running Claude Code tasks from email and Slack. It handles workspace provisioning, container isolation, network sandboxing, session persistence, and cleanup — a secure foundation for autonomous agentic development.

Chatsemble is a real-time, multi-user chat application with integrated AI agents, built on the Cloudflare stack.

Webhook integration skills for AI coding agents (Claude Code, Cursor, Copilot). Step-by-step guidance for setting up webhook receivers, signature verification, and event handling for Stripe, Shopify, GitHub, and more. Built on the Agent Skills specification.

Serve markdown versions of your HTML pages to AI agents and bots

Open-source firewall for AI agents. Policy engine that audits and controls what OpenClaw, Claude Code, Cursor, Codex, and any AI tool can do on your machine.

The first pure SNN language model trained from scratch with a fully original architecture. 618M parameters • 93% sparsity • Runs on phone • Online learning via STDP • $260 total training cost

AI-native terminal workspace. One command to launch colored Zellij tabs per git worktree, each with LazyGit + AI Agent + Workbench.

[WWW '25 Oral - GenMentor] Official code of our paper "LLM-powered Multi-agent Framework for Goal-oriented Learning in Intelligent Tutoring System", accepted by WWW 2025 (Industry Track) as an Oral Presentation.

ClaudeChrome - Native browser context awareness for agents.

FSPEC: The Spec-Driven, Multi-Agent Coding Factory. It is infrastructure for the "Dark Factory"—the emerging model of fully autonomous software development where AI agents handle all implementation while humans focus on defining what to build and why.

Pi coding agent extension that routes bash commands through rtk for LLM token savings.

Technical webinars on reverse engineering, malware analysis, and software protection.

Skills for AI coding agents to integrate with the Jupiter ecosystem.

SemaClaw is an open-source framework for general-purpose personal AI agents.

A Context Engineering Framework for AI-Assisted Multi Agent Applications Development

MCP server for managing ad campaigns across Google Ads, Meta Ads, LinkedIn Ads, and TikTok Ads. 100+ tools for campaign creation, performance analysis, keyword research, and budget optimization. Works with ChatGPT, Claude, Gemini CLI, Cursor, Codex, and Windsurf.

Self-hosted AI workspace built around context management. Works solo, scales to teams.

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

Staged self-improvement engine for Hermes-style memory, skill, and fact updates with explicit review and apply/discard gates.

A curated list of 100+ AI-powered tools, platforms, and resources for Site Reliability Engineering (SRE) — agents, incident management, observability, AIOps, chaos engineering, and more.

YantrikDB memory provider for NousResearch/hermes-agent — self-maintaining memory with benchmarked recall, self-tuning ranking, contradiction tracking, proactive hygiene, and explainable recall.

Declarative governance framework for AI-augmented software development lifecycles

A Local-first Windows desktop AI agent that can control your device seamlessly

A lightweight, single-file AI character chat application with full SillyTavern compatibility. Free, open-source, and runs instantly in any browser.

ExploitGym is a large-scale, realistic benchmark built from real-world vulnerabilities designed to evaluate AI agents' ability to develop exploits.

Serverless, 100% free, and open-source Evernote alternative on Cloudflare with native MCP | 无需服务器、0费用、原生支持 AI Agent 的开源自托管『印象笔记』

Self-contained UV scripts for data & ML tasks — OCR, vision, audio & more — run one in a command, locally or on Hugging Face Jobs. Built for humans and agents.

HitKeep is privacy-first analytics for humans and AI agents, self-hosted or in managed EU/US cloud regions.

Visualize Pydantic AI agent workflows from Logfire traces as an interactive HTML diagram — tools, nested sub-agents, tokens and exact cost.

Millisecond microVM sandbox forking for AI agents on Kubernetes. Firecracker VMs that restore from memory snapshots in milliseconds, fork a running VM into N copies, and persist durable, versioned workspaces. Self-hostable, declarative CRDs.

Run AI coding agents in parallel on one git repo and safely auto-merge their work — only changes that build and pass tests land. On top of plain git; bring your own model.

Enhanced MCP server for Godot 4.5-4.7: 33 tools / 199 actions, 3-layer architecture (headless + editor + game bridge), secure sandbox, recording & frame-verify, cross-version CI.

An open-source demo UI built on top of the Letta Agent SDK

[ARCHIVED — superseded by skillos] Browser-native markdown agent workspace. Not related to llm_os.

An OKF (Open Knowledge Format) knowledge base + Karpathy-style LLM wiki synthesized from Cole Medin's entire long-form YouTube catalog. Drop it next to any project for agent-ready, cited reference. No database, no embeddings.

Gemma models running 100% local on an 8 GB Jetson Orin Nano: voice assistants with RAG, multi-agent NPCs, live EN-JA translation, and a Gemma 4 voice + vision agent that decides when to look through the webcam. The demos from the Gemma 2 launch at Google Tokyo.

a simple message reply suggestion system

Official Channel Web SDK Loader

vector-ai-agents-lab

Compact and Agent-Native MoE Training System

Code for reproducing the ACL'23 paper: Don't Generate, Discriminate: A Proposal for Grounding Language Models to Real-World Environments

⚡️ Devex — A Fast, Secure, and Scalable Repl-as-a-Service Platform built for Developers 🚀

Multi-modal & multi-domain customer service agent with real time text, voice and soon video

ChatGPT puppeteer for firefox

Explore the latest AI Agent Toolkit!

A curated list of awesome resources for Google's Agent Development Kit (ADK)

Multi-agent orchestration for Claude Code. Persistent memory, tasks, rules, and skills that make AI agents actually coordinate.

This repository will contain the presentation and python jupyter notebooks for my DataHack Summit 2025 conference talk, Building Effective Agentic AI Systems: Lessons from the Field. Drawing from my experience building deploying Agentic AI systems, we’ll focus on three pillars: Architecting, Optimizing, and Observability for Agentic AI Systems.

Multi-modal Critical Thinking Agent Framework for Complex Visual Reasoning

AI Side Panel Extension: Enhance your productivity with this browser extension that adds a convenient side panel for quick access to popular AI sites like Gemini, ChatGPT, Copilot, Claude, and Deepseek. Easily toggle the panel using the extension icon or ALT + Q shortcut. Perfect for seamless integration of AI tools into your browsing experience.

🧬 KIP is a Knowledge-memory Interaction Protocol designed for LLMs, aiming to build a sustainable learning and self-evolving memory system for AI Agents.

Unified Agent + reusable Go agent core.

Possibly futile attempt at grounding hype with theory and fundamentals

Wizard-style app to help people generate specs that AI coding agents can execute & keep track of status

Agent Skill providing expert Swift Testing guidance for AI coding tools: covering test doubles, fixtures, async patterns, XCTest migration, and testing best practices.

LaCAM: Search-Based Algorithm for Quick Multi-Agent Pathfinding (AAAI-23)

Active Ragdoll Training with Unity ML-Agents

This Guidance demonstrates how to address the complexity of troubleshooting Amazon EKS environments with multiple metrics and logs by implementing an agentic AI workflow that uses generative AI with RAG-enabled knowledge bases and chat interfaces to accelerate problem diagnosis.

Ready to estimate AI agent work effort using tool-call rounds as the base unit instead of human time anchoring.

LLM proxy to observe and debug what your AI agents are doing.

Dynamic tool discovery and selection for Spring AI, enabling LLMs to work efficiently with large tool libraries by discovering tools on-demand instead of loading all definitions upfront.

Give your AI agent persistent memory with markdown files. Starter kit from the video: My AI and I Share a Brain.

A cognitive memory system for AI agents. Single SQLite file. MCP server included.

An MCP to expose process monitoring and ETW tracing functionally to AI agents to assist in security work

GoFrame Agent Skills empowering AI to deeply understand GoFrame conventions and best practices, generating high-quality, production-ready code.

AI-powered Git CLI that analyzes your staged and unstaged changes, splits them into atomic commits, and generates conventional commit messages via LLMs.

Agents and tools for using Quint with LLMs

Planning copilot for coding agents

Extract full product DNA from any live URL. Brand voice, UX patterns, content strategy, visual design, accessibility, SEO, performance, tech stack detection, CRO audit, design system maturity, PLG detection, enterprise readiness. 64 extraction passes. 20 intelligence engines. 138 tests.

GNAP — Git-Native Agent Protocol. RFC Draft for git-based agent orchestration. Zero servers.

The explainable, local-first memory engine for AI agents. One ~9 MB binary fuses vector + graph + columnar under VelesQL; why() returns the evidence path behind every recall. No cloud, no glue code — runs on server, browser, mobile and desktop.

AI slides and presentation editor. Agent slides and presentation skills. HTML as source files. HTML editor. AI PPT 幻灯片编辑器工具。AI Agent 幻灯片Skill。HTML 编辑器。

Build a production-ready AI-powered customer support platform with Laravel's official AI SDK. An 11-episode video series covering agents, tools, embeddings, RAG, streaming, and security.

Credential gateway for AI agents. Log in once via Oauth2 or API Key. Every agent stays authenticated — headless, no SaaS, agents never see your credentials.

Real-time AI ChatBot and voice-enabled AI VoiceBot using Deepgram (STT ↔ TTS) and Groq LLM for natural conversations.

The Quality Playbook is an open-source skill that turns AI coding agents into rigorous quality engineers. Point it at your code, in any language. Feed it whatever docs you have: READMEs, GitHub issues, Discord threads, AI chat history. It figures out your intent, creates a real requirements spec, and does quality engineering to find real defects.

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.

AI agent skills for applying Feature-Sliced Design (FSD) v2.1 in frontend projects.

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

Secure local trace capture and inspection for Codex and Claude agent sessions.

Headless MCP server for Screaming Frog SEO Spider – run crawls, export and analyze crawl data via the CLI. Small locked-down tool surface for scheduled audits, CI, and unattended AI agents.

An Agent Skill that teaches an AI coding agent how to scaffold, write, build, and package Ableton Live extensions with the Ableton Extensions SDK (@ableton-extensions/sdk, TypeScript).

EurekAgent: an autonomous research system for metric-driven tasks, built with Claude Code. Define the problem and metric. Get breakthrough results.

The environment engine for agent worktrees - zero-config dep sync + port/DB/compose isolation

Standardized tool schemas and SDKs that expose Sciverse Open Platform retrieval capabilities to LLM agents.