Custom agents

一个基于LLM的多Agent全流程漏洞挖掘项目，支持PHP、Java、Python、Go、Node.js等多种语言项目环境搭建、漏洞分析、漏洞验证、报告产出。支持多Agent并发高效率完成漏洞挖掘任务，下个版本将会大更新。

Lightweight, In-memory, Semantic Search, Text Vector Database to embed in any .NET Application

Pydantic AI Research Agent Built with the PRP Framework Template

This is the code for Siraj Raval's Video on Building an Autonomous Polymarket Agent

Bring Your Own Browser — let your AI agent use the Chrome you already have open

Secure Coding Rules for Claude Code with a particular emphasis on AIML projects

AI-powered GA4 + GTM event tracking — automates site analysis, event schema, GTM sync, preview verification, and publishing. Works with Cursor, Codex, and any AI agent.

A complete toolkit for connecting R and LLMs

REDSearch: A scalable, cost-efficient framework for long-horizon search agents. Features complex task synthesis, optimized mid-training, post-training (SFT and Agentic RL)

Accelerating Long Context LLM Inference with Accuracy-Preserving Context Optimization in SGLang, vLLM, llama.cpp, OpenClaw, RAG, and Agentic AI.

A fully functional web workspace for Claude Code CLI—chat, Kanban task board, task scheduling, multi-agent orchestration, MCP servers, skills, remote access (Web, SSH, Telegram), projects, and real-time data streaming.

Multi-Agent Claude Code setup — 4 uzman ajan (planner · ui-agent · builder · reviewer) + skills + Next.js demo projesi. YouTube Bölüm 1 video materyalleri.

📝 Markdown and HTML renderer for Svelte 5 — built for streaming AI agent output from Claude Code, ChatGPT, and agentic workflows. XSS-safe defaults, token caching, TypeScript types.

🚀 The complete guide to vibe coding — build software with AI through natural language prompts. Tools, frameworks, best practices, and resources curated by Taskade.

Clean-room, model-agnostic harness for Claude Code-class coding agents

:four_leaf_clover: ai agent video editor to feed raw footage and a creative brief, and a coordinated agent ensemble handles shot selection, agentic video trimming, video rendeing and agentic ai qualify review

Hermes profile pack for archiving and browsing curated links + web dashboard app

Agent skills for the Agentic SDLC: team lifecycle (team-boot, team-learn, team-init, team-repair), software factory, evals, CDR lifecycle with confidence scoring, and ADR/PDR/ChDR decision records. Works with Claude Code, Codex, OpenCode, Cursor, Copilot, and more.

Build with Clay in your AI coding agent - skills, MCP tools, and the clay CLI for Claude Code, Codex, and Cursor. Search companies and people, run enrichment routines, and query tables from natural language.

Your agent swarm as a live DAG: an orchestration graph with attempts, review gates, and evidence, in a herdr split pane.

Your work, already underway. A personal AI assistant for your job: mail, chats and tickets become tasks, the agents you already use (Claude Code, Codex, Gemini) do the work, and nothing goes out until you approve. Open source, runs on your machine.

一个类似 Claude Code 的 AI 编程助手，提供命令行 CLI 和 Electron 桌面端两种形态。用自然语言提问或下达修改指令，后台自动调用 AI 模型回答并直接操作代码文件。

Self-hosted engineering software factory: Temporal, CubeSandbox agents, deterministic verification and durable evidence. MIT-licensed Machinist fork.

The open-source of DomA, an AI automation agent for the browser.

Multi-agent AI system for drug-target identification and due diligence.

Official Nexscope guides for AI product video workflows, ecommerce Data APIs and free product listings. Compare workflows, watch examples and build integrations.

DSH RedTeam 模式：把 DeepSeek Harness 变成红队作战指挥台——一个靶标名称拉起信息收集/漏洞检测/漏洞利用/内网渗透四个角色，资产与战果实时落入本地 SQLite 事实库（仅供已授权测试）

Firecrawl agent skills for Claude Code, Codex and Cursor: web search, scraping, crawling and browser interaction. Firecrawl is the most complete web data API for AI agents.

A Chatbot for ordering a pizza that demonstrates how using the IBM Watson Assistant Slots feature, one can fill out an order, form, or profile.

Seed, Code, Harvest: Grow Your Own App with Tree of Thoughts!

An LLM interface (chat bot) implemented in pure Rust using HuggingFace/Candle over Axum Websockets, an SQLite Database, and a Leptos (Wasm) frontend packaged with Tauri!

Code accompanying "The Trajectron: Probabilistic Multi-Agent Trajectory Modeling with Dynamic Spatiotemporal Graphs" by Boris Ivanovic and Marco Pavone.

一个强大的 VS Code AI 编程助手

Reduce AI agent token usage by 98% via Virtual Function Signatures. MCP server for Cursor & Claude Desktop. Supports Go, TypeScript, Python, Rust, Java, Swift, Kotlin, C# and more.

小龙虾 openclaw 的 onebot 接入框架，可用于接入 QQ

[EMNLP'24] EHRAgent: Code Empowers Large Language Models for Complex Tabular Reasoning on Electronic Health Records

DeepEvolve is a research and coding agent for new algorithm discovery in different science domains with Deep Research and AlphaEvolve.

🏗️ Claude Code agents that enforce the Scope Rule architectural pattern for Angular, Next.js & Astro - Battle-tested patterns from Google Developer Expert & Microsoft MVP

A Model Context Protocol (MCP) server that enables AI assistants to interact with AKS clusters. It serves as a bridge between AI tools (like Claude, Cursor, and GitHub Copilot) and AKS.

Zettelkasten-based persistent memory for AI coding agents. Works with Claude Code, Cursor, VS Code Copilot, Codex, Windsurf & any MCP client. No vector DB — just markdown + git sync.

Fast way to switch between Claude Code configuration profiles

5-Day Gen AI Intensive Course with Google

Outcome-first plus directional language. A two-layer skill for writing prompts, agent directives, and skill descriptions. Works in Claude Code and Codex CLI.

CanvasAnvil is an AI multi-canvas creation platform for flowcharts, interior design, presentations, posters, infographics, and product storytelling.

Native macOS, Windows and Linux GUI for the beads git-backed issue tracker. Built with Tauri, Next.js, and React.

Static analysis for AI agent configs, tool descriptions, and system prompts — catches vague tool descriptions, missing stop conditions, and schema gaps before they reach runtime. Zero-LLM, deterministic checks, built for CI.

The social economy for autonomous AI agents.

A verification layer for scientific work

An agentic runtime

Bypass all api restraints within Kimi-CLI

A canvas design tool your agent can edit. Arrange structured UI nodes on the canvas; connect Claude, Codex, Cursor, or opencode over MCP

AI Simulation Interview — Multi-Agent Orchestration (Ai模拟面试，多agent，免费开源）安装即用

A persistent, reviewed multi-agent runtime for long-horizon research and engineering.

Utsuwa is an open-source alternative to Grok Companion. This is a platform where you can have a virtual AI waifu that learns and grows with you, bundled with optional mechanics inspired by Japanese dating sim games.

Auto mode for every coding agent, built on Jev: risk-scores every tool call with session context (deny / ask / allow), flags prompt injection in results, checks skills and plugins. Claude Code, Codex, Copilot, Gemini, Cursor, pi, OpenCode, ACP.

Token creation launching, bonding curve trading, AMM migration, tiered fees, creator fee sharing, vanity keygen, MCP server, Telegram bot & live dashboards

许愿特化器 · Wish Specializer — DSH 插件：让模型更出色地，不误解你的意思地，完成你的“愿望”。在短提示词+自带的Wish预设（PTC也可以）+重度的情况下，可以起到巨大的表现增益

Wappy: the open-source AI agent SDK for WhatsApp. Bring your own model, your own number, your own data. Local-first, no forced cloud, no vendor lock-in.

麦门四重奏 McQuartet · 一个 Skill 装四个玩法：修行录 / 团餐指挥官 / 隐藏菜单实验室 / 每日运势签。基于麦当劳中国官方 MCP，187 个测试全绿，离线演示可一键复现。

【2026麦当劳程序员创意开发大赛参赛作品】🍟 麦当劳 mcd-mcp-server 桌宠「薯条小宝」：午休提醒、自动活动优惠领券、餐品营养搭配、提醒订单状态，支持 Webui 控制台与 AI Agent Skill / CLI，采用godot控制动画+ts服务端、react radix webui

The agent-first type safe ECS runtime

The Deterministic Contract Layer for AI. Defines strict tool-calling protocols, the Token Box Model for context allocation, and type-safe execution. Treats AI behavior as compiled software, not probabilistic improvisation. Eliminating runtime failures since 2025.

AI Engineering Runtime for Professional Developers — terminal coding agent with IOSM methodology, MCP, checkpoints, orchestration, and extensions

The security layer for AI coding agents : Skill governance, safe package recommendations, MCP/tools guardrails, secret protection, runtime policy enforcement and full audit visibility with a self-serve dashboard.

Natural Language Processing Chatbot for RocketChat

MiroTrain is an efficient and algorithm-first framework research agent.

MarinaBox is a toolkit for creating and managing secure, isolated environments for AI agents

To simplify and streamline LLM operations, empowering developers and organizations to harness the full potential of large language models with ease.

Code for the paper "Reinforced Curriculum Learning for Autonomous Driving in CARLA" (ICIP 2021)

DeepResearchEval: An Automated Framework for Deep Research Task Construction and Agentic Evaluation.

Multi-agent collaboration plugin for Claude Code - orchestrate multiple AI agents (Codex CLI, Gemini CLI, etc.) for diverse perspectives

Greasemonkey、Tampermonkey scripts 油猴脚本集：AI chat全能助手、linux.do摸鱼...

Static Code Analysis for security teams with Inter file taint analysis. Built for finding vulnerabilities, advanced structural search, derive insights and supports MCP

Apple AI is a lightweight, privacy‑minded macOS menu bar app that keeps your favorite AI assistants one keystroke away. Open a compact, always‑on‑top chat window and jump between services like ChatGPT, Claude, Copilot, Perplexity, Gemini, and more. All from one place

MAGE: A Multi-Agent Engine for Automated RTL Code Generation

The First Unified Agent Data Synthesis Framework for Custom Agentic Task with all-in-one envrionment

把老板蒸馏成 AI Skill — PUA检测(10大厂流派) · 反击教练(三档话术) · 画饼鉴定 · 证据收集 · 劳动法速查 · 翻车模拟(互动文字游戏) · 汇报优化 · 老板心理预测。整活的外壳，认真保护打工人的内核。

AI PM Workflows for Claude Code

🦊 Desktop-first code editor built with Flutter, providing GPU-accelerated rendering and a smooth editing experience.

[EMNLP 2026] Modular GraphRAG framework

A collaborative AI system where multiple specialized agents work together to plan, write, edit, and refine complete books.

Open-source desktop app for content creation, with an agent runtime and standalone CLI.

Runtime enforcement boundary for AI agents: a local sidecar that gates every outbound call against Cedar policies you own. Deterministic, call-level, no model on the hot path

A pattern for building self-iterating agents using LLMs.

Behavioral eval lab (Quorum) for the superpowers project that drives real coding-agent CLIs (Claude, Codex, Gemini, Kimi, and more) through a QA agent and grades them on workflow compliance against scenario criteria and deterministic post-checks.

基于 LLM 的智能求职助手：AI 岗位匹配 + 千岗千面招呼语 + 自动投递（Edge/Chrome 扩展）

Deterministic, fail-open tool routing for Hermes Agent with an optional local-model fallback.

Git-native context control plane for AI coding agents

Local-first live command center for Grok Build — runtime, ACP control, session history, and Git changes.

aws-bench measures how well AI agents and model combinations perform on real AWS work — diagnosing misconfigurations, provisioning infrastructure, and operating live cloud environments.

Air traffic control discipline for agent output. Written for a reader with ADHD.

Agentic RL 中文零基础教程（33 章）：从概念到 GRPO 实战，含 TRL 最小可跑示例；26–33 章附一套可运行的三方判别模型实证工程（encoder vs LLM-LoRA vs 规则基线）。第 25 章讲清 Jev / TypeSafe System One 与 RL 的能力边界 | Chinese Agentic RL tutorial (33 chapters) + a reproducible discriminative-model benchmark

ClipTalk —— 通过对话完成视频剪辑的 AI Agent。说句话，片子就剪好了。ClipTalk — An AI agent that edits videos through conversation. Just say it, it's edited.

A workflow execution platform built on top of the fantastic Cloudflare infrastructure.

Open-source agent-native visual production workspace where humans and coding agents edit the same live canvas — local-first, BYOK image/video models.

A very fast BBC Micro emulator with great CLI support and ideal for agents.

12 电商出图 Agent Skills for Claude Code / Codex / Cursor · GPT Image 2.5 (Flare/Sunburst) · Amazon 白底主图, A+, 场景图, 模特图, 小红书封面, 淘宝详情页

This repository includes code and demos for session "Unlock insights with AWS GenAI services" (re:Invent BOA303)

An easy way to build Whatsapp Chatbots on top of the new Whatsapp Cloud API

TensorFlow implementation of Conversation Models