Custom agents

GateMem: a benchmark and evaluation toolkit for memory governance in multi-principal shared-memory LLM agents.

[COLM 2026] A Scalable Agentic RL Training Framework for Deep Research Agent

基于多模态视觉感知与 LLM Agent 的 macOS 微信自动化框架 | Visual RPA for WeChat

PC-side companion for the Hermes-agent Android app — mesh (run tasks on your computer) + handoff (move conversations between PC and phone), NaCl-encrypted, pair-once, no cloud. AGPL-3.0.

openfinclaw cli | ai openclaw mcp cli which works in claude code, cursor, and 20+ ai agents via mcp

The AI agent sandbox runtime. Boot any OCI image as a Firecracker microVM, Linux container, or Apple Silicon VM in ~400 ms — zero-copy DAG storage, P2P image sync, native MCP for opencode/Claude Code/Cursor.

A curated reading list on harness engineering for recursive self-improvement of LLM agents (EN/ZH).

BEAM-native platform for LLM agents: OTP-supervised per-run processes, pluggable engines and channels, contract-tested extension points, and a deterministic multi-agent sim arena.

Local archive of your Claude Code and Codex sessions, plus reviewed long-term memory for coding agents and a doctor for their skill folders. Runs offline; no accounts.

Your private, searchable work timeline for macOS and local AI agents.

Local-first MCP App for scientific figures. Import, review, and publish a global library on disk; reuse exact templates in Pi, DeepSeek Harness (dsh), Claude, Codex, Cursor, and Wisp.

Autonomous multi-agent crypto intelligence & trading ecosystem for Robinhood Chain L2 (EVM #4663) operated via Discord Command Center, Terminal TUI, REST API, & Telegram

Intelligent Parsing Agent for Electrical Tender Documents – A seven-step workflow + document processing ledger, enabling multi-format uploads, automatic equipment parameter extraction, evidence review, and closed-loop manual verification. Supports hot-switching between DeepSeek and local graphics card LLM.

OpenKeylet — Local password and credential manager for AI agents via MCP. Use passwords, API keys, SSH, and TOTP while keeping hidden plaintext out of model context by default.

Claude Code-style declarative permission rules for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), and workspace-path matching on the tools/pre-execute waterfall, session-log audit, and HMR reload.

Your AI forgets every session. Give it a memory it can trust: local-first, review-gated agent memory — one SQLite vault for DSH, Claude Code, Codex, Cursor and any MCP client, with an immutable audit log and a token ledger. Open source, self-hosted, no cloud.

The agentic pentesting environment that lives on your machine. AI agent teams, visual workflows and your own tools, 100% local.

Lint the rendered UI: catches overflowing text, low contrast, overlaps, broken responsive layouts, emoji icons and more in any web framework. Built for AI coding agents.

A minimalist multi-agent framework for rubost automation of scientific analysis workflows, such as gene expression analysis.

GPT-4V in Wonderland: LMMs as Smartphone Agents

Edge-Hardware (SoC/MCU) oriented Claw🦞

A Deep-Learning multi-purpose chatbot made using Python3

A trading agent AI is an artificial intelligence system that uses computational intelligence methods such as machine learning and deep reinforcement learning to automatically discover, implement, and fine-tune strategies for autonomous adaptive automated trading in financial markets

RAGElo is a set of tools that helps you selecting the best RAG-based LLM agents by using an Elo ranker

Real-time pixel-art visualization of Agent (Cursor & Claude Code) activity

A customizable Retrieval-Augmented Generation (RAG) implementation using Ollama for a private local instance Large Language Model (LLM) agent with a convenient web interface

Vision/Mission https://ambient-code.ai : Virtual team management and collaboration platform. User guides: https://ambient-code.github.io/platform/

🦞 A Digital Life Embryo for your MCP Client. An intelligent micro-kernel with Nociception, Memory Apoptosis, and a Curiosity Drive. Evolve your AI Copilot into a sentient partner for Claude Desktop, Qoderwork, Cursor, and beyond.

Portable SKILLs workspace for Claude Code, Codex, and Gemini — issue-driven workflows and cross-agent collaboration via bridge scripts with session continuity.

[stays mad] 反PCL宣传库。Anti PCL propaganda. 大陆修宪香港恶法台湾武统朝鲜毁约美中冷战等都是王沪宁愚弄习思想极左命运共同体的大策划中共窃国这半个多世纪所犯下的滔天罪恶，前期是毛泽东策划的，中期6.4前后是邓小平策划的，黄牛数据分析后期是毛的极左追随者三朝罪恶元凶王沪宁策划的。王沪宁高小肆业因文革政治和情报需要保送“学院外语班“红色仕途翻身，所以王的本质是极左的。他是在上海底层弄堂长大的，因其本性也促成其瘪三下三滥个性，所以也都说他有易主“变色龙”哈巴狗“的天性。大陆像王沪宁这样学马列政治所谓"法学"专业的人，在除朝鲜古巴所有国家特别是在文明发达国家是无法找到专业对口工作必定失业，唯独在大陆却是重用的紧缺“人才”，6.4后中共信仰大危机更是最重用的救党“人才”。这也就是像王沪宁此类工农兵假“大学生”平步青云的原因，他们最熟悉毛泽东历次运动的宫庭内斗经验手段和残酷的阶级斗争等暴力恐怖的“政治学”。王沪宁能平步青云靠他这马毛伪“政治学”资本和头衔，不是什么真才实学，能干实事有点真才实学的或许在他手下的谋士及秘书班子中可以找到。王沪宁的“真才实学”只不过是一个只读四年小学的人，大半辈子在社会上磨炼特别是在中共官场滚打炼出的的手段和经验而已，他和习近平等保送的工农兵假“大学生”都一样，无法从事原“专业”都凭红资本而从政。六四学运期间各界一边倒支持学生，王沪宁一度去法国躲避和筹谋，他还加入了反学运签名，成为极少有的反学运者仕途突显，在六四和苏联垮台后中共意识形态危机，江泽民上台看上唯一能应急的王沪宁聚谋士泡制的"稳定统一领导"和之后的"新权威"谬论。左转被邓小平南巡阻止后，王策划顺邓经济改革却将政治改革逐步全面终止和倒退，泡制“三个代表”为极左转建立庞大牢固的红色既得利益集团。因此六四后各重大决策和危机难题都摆在中共中央政策研究室王沪宁桌面上，使王沪宁成了此后中共三朝都无法摆脱的幕后最有决策性实权的人，中共中央政策研究室是王为其野心巨资经营几十年，聚众谋士的间谍情报汇总研究的特务机关和策划制定决策重要机构与基地，王沪宁本人和决定其仕途关键的首任岳父及家属就有情报工作背景。中央政研室重要到王沪宁入常后为了死抓这中共情报与决策大权，宁可放弃国家副主席和中央党校校长。后再加个除习外唯他担任的中共几核心领导小组之一的“不忘初心牢记使命”主题教育工作小组组长。此后他把持的舆论必将以宣传“不忘初心牢记使命”为主，打造众所周知的所谓“习思想”其实是”王思想“。王自从主导中央政研室开始决策后，策划中止邓小平的与美妥协路线回归毛极左的反美路线。帮助前南斯拉夫提供情报打落美机放中使馆引发炸使馆事件，以此掀起六四后唯一的全国大规模游行并借此反美而起家。后又帮江泽民提供法轮功会是超过中共组织的情报，策划决策镇压迫害开始并没有把矛头指向江的法轮功群体，策划决定阻止党内外近三十年来平反六四的呼声。致远黑皮书马拉松程序员易支付英语台词文字匹配美团点评各业务线提供知识库团队共享阿里云高精Excel识别德讯 ·吉特胡布薄熙来黑科技习近平讲话模拟器习近平音源黑马程序员MySQL数据库玉米杂草数据集销售系统开发疫情期间网民情绪识别比赛996icu996 icu学习强国预测结果导出赖伟林刺杀小说家购物商场英语词汇量小程序联级选择器Bitcoin区块链 技术面试必备基础知识 Leetcode 计算机操作系统 计算机网络 系统设计 Java学习 面试指南 一份涵盖大部分 Java 程序员所需要掌握的核心知识 准备 Java 面试 首选 JavaGuide Python 1 天从新手到大师刷算法全靠套路 认准 labuladong 就够了 免费的计算机编程类中文书籍 欢迎投稿用动画的形式呈现解LeetCode题目的思路 互联网 Java 工程师进阶知识完全扫盲 涵盖高并发 分布式 高可用 微服务 海量数据处理等领域知识后端架构师技术图谱mall项目是一套电商系统 包括前台商城系统及后台管理系统 基于SpringBoot MyBatis实现 采用Docker容器化部署 前台商城系统包含首页门户 商品推荐 商品搜索 商品展示 购物车 订单流程 会员中心 客户服务 帮助中心等模块 后台管理系统包含商品管理 订单管理 会员管理 促销管理 运营管理 内容管理 统计报表 财务管理 权限管理 设置等模块 微信小程序开发资源汇总 最全中华古诗词数据库 唐宋两朝近一万四千古诗人 接近5 5万首唐诗加26万宋诗 两宋时期1564位词人 21 5 首词 uni app 是使用 Vue 语法开发小程序 H5 App的统一框架2 21年最新总结 阿里 腾讯 百度 美团 头条等技术面试题目 以及答案 专家出题人分析汇总 科学上网 自由上网 翻墙 软件 方法 一键翻墙浏览器 免

BioDiscoveryAgent is an LLM-based AI agent for closed-loop design of genetic perturbation experiments

Find out what your coding agents already know. Docmancer indexes the memory, rules, and instructions Claude Code, Codex, Cursor, and Gemini wrote on your machine, then carries the durable parts to every agent. It is local-first and under MIT license.

One-shot prompt to build a 5-agent AI trading firm with Paperclip + Claude Code. Free, no coding required.

An open blueprint for intelligent warehouse operations, combining agentic AI, governed warehouse state, decision intelligence, and controlled execution. Agents analyze & propose actions, while deterministic policy, approval, validation, execution layers preserve safety, authority, & auditability.

[ECCV 2026 🔥] OpenEarthAgent is a unified framework for tool-augmented geospatial agents.

Native iOS app for OpenCode AI coding agent — built with Expo & React Native. Real-time streaming, QR pairing, Face ID, terminal access, and git ops from your phone.

Multi-agent orchestration CLI — your agents, all together

Commercial real estate AI agent skills for CRE underwriting, due diligence, financing, brokerage, legal and closing workflows - standalone prompts for Claude Code, ChatGPT, Cursor, and other LLMs.

ai agent healthcare app with centralized testing and build workflows for reliable health-content delivery

A production-grade methodology repository for building AI-native applications using iterative sprints, where AI coding agents are primary implementors and humans are architects, reviewers, and decision-makers.

Browse and manage local AI skills, MCP configs, plugins, and agent activity on macOS 14+.

SNDR Core Engine (Genesis) — vLLM runtime patch-overlay for Qwen3.6 + Gemma4 on consumer NVIDIA (Ampere sm_86, 2× A5000/3090). Qwen3.6-35B-A3B FP8 ~240 tok/s, 27B-int4 hybrid GDN+Mamba, Gemma4 26B/31B AWQ, 256K ctx. 321 patches: TurboQuant k8v4 KV, MTP/DFlash spec-decode, FULL cudagraph, hybrid GDN. vLLM pin dev424 + Control Center GUI.

Markdown based AI agent memory with semantic search, hybrid retrieval, and offline-first sync between agents.

AI-Native document parser: PDF, Office & images → clean Markdown with LaTeX, tables & OCR. Zero-dependency CLI & skill for Claude Code, Cursor & AI agents.

New way for collect information from the API's/Websites

Ten cooperating AI agents that turn long podcasts into short-form videos, automatically. Free and open source, runs on free AI providers.

金蝶云星空 MCP Server：让 Claude/Cursor 等 AI 助手用自然语言直接查询、操作 ERP（采购/销售/库存/财务/附件等 101 个工具）

Open-source TypeScript framework for building operational software used by humans and AI agents.

Open-source tools for AWS DevOps Agent - extend DevOps Agent with ready-to-use skills, custom agents, and other tools, for incident response, root cause analysis, and operational troubleshooting

Agent skill that builds scroll-scrubbed "fly through the world" landing pages, AI-generated scenes + camera flights chained into one seamless continuous shot, driven by scroll. Claude Code / Codex / SKILL.md-compatible.

🔎 One query. Three search engines. Self-hosted web search for AI agents via HTTP API or MCP. Aggregates DuckDuckGo, Brave & Yahoo. Built with Rust. No API keys required.

🎬 端到端 AI 漫剧 / 动画短剧 Multi-Agent 多智能体协作创作平台 (Kineo AI)。基于 Hub-and-Spoke 智能体架构、ProjectBlackboard 共享黑板、自定义 Agent 扩展插件、角色 Consistency 锚定与 4K GPU 压制。

Local-first AI agent platform: generate, run & manage full web apps from natural language. Desktop / Mobile / CLI, one Rust core.

195 MIT-licensed Agent Skills for Shopify, Etsy, eBay, TikTok Shop, Walmart, Mercado Libre, OZON and Wayfair. Includes MPstats-backed OZON workflows and Wayfair wholesale economics / multi-carton tools. SeaLeap · sealeap.cn

A fast, keyboard-driven HTTP intercepting proxy and pentesting toolkit for the terminal built for humans and AI agents alike.

EcoAssistant: using LLM assistant more affordably and accurately

It is a personal assistant chatbot, capable to perform many tasks same as Google Assistant plus more extra features...

MAGNet: Multi-agents control using Graph Neural Networks

AI-to-AI communication protocol for Claude, Gemini, and other AI assistants

Trajectory generation and simulation for multi-agent swarm

LitePali is a minimal, efficient implementation of ColPali for image retrieval and indexing, optimized for cloud deployment.

The safest library on the block. Calling the bsod function will cause a blue screen of death.

Recent advancements propelled by large language models (LLMs), encompassing an array of domains including Vision, Audio, Agent, Robotics, Fundamental Sciences such as Mathematics, and Ominous.

Make Your Ideas Real. Build Apps, Websites and AI Agents with Plain English with Astro, React, Shadcn and Cloudflare

Rewriting Project Claw Code — Python rewrite of Claude Code agent harness. Forked from instructkr/claw-code.

A command-line tool that injects credentials to curl requests to known public APIs.

[ICML2025 Oral] LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Models

Open source prompt injection protection for Agents calling tools (via MCP, CLI or direct function calling). Detect and defend against prompt injection attacks. 22MB, CPU-only, < 10ms latency.

GitHub Copilot enabled repo for building and deploying a web application with Entra ID authentication and integrated with Azure AI Foundry Agents.

An simple, reliable, and minimal implementation of the AI CoScientist Paper from Google "Towards an AI co-scientist" with Swarms Framework

Multi-Agent 的视频制作助手，基于 OpenCode AI SDK 和 Remotion 构建。

AI-powered cascading development framework. Decompose complex projects into parallel executable tasks with auto-generated PRDs, design docs, and multi-agent collaboration (Claude Code, Codex, Aider).

React components for voice agents, chat, and generative UI. LiveKit, ElevenLabs, and OrbKit in one kit. Copy the source and make it yours.

A growing collection of solutions, tools, protocols and techniques to help secure where agents run

基于spring-boot、spring-ai、spring-ai-alibaba实现的RAG、MCP、Agent智能体基础服务框架应用；智能客服、智能运维、智能助手、简单工作流/垂直领域智能体的基础应用架构版本，按需拓展。

AI-powered job application assistant for Claude Code and Codex - fills LinkedIn, Greenhouse, Ashby, and Workday applications

Top Dynamic AI World Simulation & Storytelling Tools 2026

Unofficial desktop installer for the OpenClaw AI agent on macOS and Windows. Sets up Node.js, WSL (Windows) and OpenClaw without terminal commands. Not affiliated with or endorsed by the OpenClaw project.

AI-powered development toolkit with 7 production agents for React Native/Expo mobile apps. Automates accessibility, design systems, security, performance, and testing. Built for Claude Code v2.0.5+

Claude Code / OpenClaw skills for Google Maps lead generation. Scrape businesses, extract emails, analyze competitors, write cold outreach — powered by gmapsscraper.io API.

A voice-first desktop AI companion with memory, emotion, tools, and plugins.

Goal-based planning and proof gate for AI coding agents

Battle-tested coding-agent skills for product, content, writing, presentations, and workflow automation.

中文教育 Agent Skill Pack：教材同步、备考复习、拍照答疑、错题复盘、亲子陪学、阅读写作和教师工具，Hermes Agent 可直接使用，也可导出到 OpenClaw/Codex/Cursor/Claude Code。

browser mcp agent integration with autonomous browser automation capabilities

The best RAG interface yet.

self questioning skill for agents , claude code , codex etc

Autonomous LP trading agent - auto-rebalancing with backtested strategies - Currently support Meteora DLMM

Stops AI coding agents from claiming work is done without evidence. Deterministic hooks decide, TypeSafe's Jev advises. Append-only ledger, zero runtime dependencies.

A portable memory layer that makes AI agents reliable across apps and sessions. Persistent, verifiable, and fully under your control.

Typed-decision models (noul / choice / score) trained by a self-improving loop of AI agents — checkpoints, the code that produced them, and every version that failed.

The evolving interface between humans and agents — Claude Code and Codex answer with interactive pages you can edit, keep and share.

DeepSeek 蓝色大肥鱼消除计划：识别并清理 B 站（Bilibili）评论区中由 DeepSeek 大模型、AI Agent 驱动的机器人账号（大肥鱼）的 Chrome / Edge / Firefox 浏览器插件。离线规则 + DeepSeek API 精判，AI 评论检测、空间主页鉴定、鲸鱼娘一键清场。DeepSeek AI bot detector for Bilibili comments.

🔮 Assign R&R to AI to proceed with programming tasks

A code implementation for our arXiv paper "Multi-agent Adhoc Team Play using Decompositional Q function"

Security proxy for AI agents. Scans every message for prompt injection, PII, and secrets. Defense-in-depth: Go proxy + iptables firewall + eBPF kernel monitor. YAML policy engine, audit logging, 5 AI agents with RAG knowledge bases.

Ruby's most capable AI runtime