Custom agents

Nova-Proximity is a MCP and Agent Skills security scanner powered with NOVA

The NodeQuery agent collects selected linux server data and sends them to our monitoring system for further processing.

A suite of Rust CLI tools for agentic trading and market intelligence. Each exchange has its own dedicated binary — hyperliquid, binance, coinbase, okx, polymarket — plus a shared fintool for exchange-agnostic market intelligence (quotes, news, SEC filings). Supports crypto, stocks, commodities, and prediction markets.

TranscriberBot for Telegram

function calling-based LLM agents

Record and Replay AI Agent Trajectories.

Lightweight self-hosted AI agent. Open-source OpenClaw alternative in Go.

Put the world's smartest AI agents & plugins in your pocket

Open-source directory of agent-bot prompts for Grok Bot, Rakazo, and any agent — botdirectory.ai

Open-source AI security verification for model artifacts, live endpoints, MCP servers, and recorded agent traces. Reproducible evidence for release decisions.

Type-safe, real-time backend with Vite, Rsbuild and Rspack support, deployed on Cloudflare Workers and Durable Objects. Auth, storage, scheduling and an MCP server for AI agents. Convex-style DX.

The Cloud for AI Agents — secure, real-world environments that spin up in milliseconds.

PostBot 3000 is an open-source project that shows how to build a powerful AI agent and stream responses and generate artifacts. This project makes it easier for anyone looking to implement similar solutions.

Firefox Voice is an experiment in a voice-controlled web user agent

Hulken is a stress testing tool for everything speaking HTTP. Hulken supports multiple urls, GETs and POSTs, static and dynamic payloads, multiple agents and more. Hulken is highly configurable but defaults to some reasonable settings. Hulken works both as a library and a stand-alone command line tool. Hulken is swedish for The Hulk.

Xircuits toolkit for creating and experimenting with BabyAGI/AutoGPT-style agents

Bringing Human Capabilities to AI Agents

AI-powered login automation. Uses Claude to classify login pages and Playwright to interact with them.

A multi-agent workflow system for GitHub Copilot in VS Code that brings structure, quality gates, and long-term memory to AI-assisted development with Flowbaby.

Practical guides and scripts for AI coding agents, terminal customization, and remote dev tooling. Each documents a real problem and a copy-paste fix: git safety hooks, WezTerm/Ghostty setup, MCP config repair, swap flushing, local LLM serving, and more.

The authentication CLI & Proxy for AI agents. Give agents access, not your credentials.

Claude Code harness engineering plugin — plan mode on steroids. Product design-driven agent orchestration with sub-agents and agent teams, tuned for developers and designers shipping real features. Phased adoption from PRD execution to automated review, code review, and CI-friendly agent teams

Revornix is an open-source, local-first AI information/markdown workspace. It helps you collect fragmented inputs, turn them into structured knowledge, generate reports with images and podcast audio, and deliver the output through automated notifications.

See at a glance which tmux sessions have Claude/Codex working vs idle

Measuring agents' ability to get work done on a computer

On-demand Linux computers you can hand to an AI — real Firecracker microVMs with a browser, terminal, coding agents, and an AI that drives them.

AI Agent Guide 通识教程，现提供小程序版本（搜「小傅哥AI Guide」）

Emotion Ball 是一套面向 AI 助手的表情引擎:32 种状态表情全部由纯 SVG 与原生 JavaScript 实时驱动,零框架、零图片资源。AI 侧只需输出一个 emotionId,小球即可切换到对应表情,可直接用作聊天机器人、桌面宠物、悬浮助手的情绪表达层。

Neuro-symbolic agents with verified memory. MCP math tools, an algebra repair Skill, and an open challenge. Verify solutions, learn checked rules, and reuse.

Lifecycle-managed, auditable project context for AI coding agents

Photoreal Blender scenes from a one-paragraph brief, built by AI agents: image→3D props on fal, scripted layout, lighting, camera and grade.

KEras Reinforcement Learning gYM agents

llmbasedos — Local-First OS Where Your AI Agents Wake Up and Work

DEPRICATED! Use the multi-agent suite instead!

AI-assisted development for the Godot engine.

Matrix (Multi-Agent daTa geneRation Infra and eXperimentation framework) is a versatile engine for multi-agent conversational data generation.

An open-source, AI-powered application using Agentic CAG to chat with any public GitHub repository or developer profile, offering deep code analysis, visual architecture maps and security audits

🧠 AI Agent Skills Repository - A curated collection of specialized skills for AI coding agents (Claude Code, GitHub Copilot, Cursor, Windsurf). Created by Yuval Avidani using GitHub Copilot via VS Code Insiders.

A next-generation AI-powered infinite canvas workspace built for creators and developers. Experience the future of Generative AI with a drag-and-drop node interface that combines Google Gemini 3 Pro, Veo 3.1, and LangGraph Agents into a seamless creative workflow.

🌱 Argus 是一个基于 RAG 架构的开源知识库平台，后端采用 Java 21 + Spring Boot + MyBatis-Plus + PostgreSQL/pgvector，前端采用 Vue 3 + TypeScript + Element Plus，AI 层基于 Spring AI Alibaba（通义千问）+ ReactAgent 图引擎，以 MinIO + Elasticsearch 为存储与检索引擎。

BrandDocs is a set of agent skills that learn your existing Word, PowerPoint and Excel templates and generate new on-brand documents from them. Unlike generic AI document generators, it preserves brand, structure, styles and formulas by construction. Built for Claude Code, Codex and compatible AI agents.

The professional studio for modern development — build it, ship it, host it without leaving the app. Free, local-first, works with any CLI based coding agent, including Claude Code / Codex / OpenCode / Cursor.

Robinhood Agentic Trading agent — a fully automated AI trading bot placing real orders through Robinhood's Agentic Trading MCP, under mechanical, auditable risk rules the model cannot override. Able to run unattended on Claude Pro, no metered API spend. Not financial advice.

Turn Google Search, Papers, and Codebases into an Automatic Local Knowledge Graph for AI Agents.

Hyperliquid trading desk for AI agents: 7 roles, 17 skills and keyless market tools. Research first; execution requires your API wallet and approved tickets. Grok Bot, Claude Code, Cursor, Codex, Gemini CLI and Grok Build.

Embodied 3D AI desktop companion powered by Ollama, dual voice synthesis (Fish Audio S2.1 & local GPT-SoVITS), real-time lip-sync, and custom VRM avatar support.

Remote control for your pi coding agent. Pi-Remote mirrors live pi terminal sessions to any browser, so you can watch runs, answer prompts, and send commands from your phone — end-to-end encrypted over a self-hosted relay.

aipdd开源的集成画布与agent，实现短剧制作

🔐 Firewall Your Data, Control Agents. Prevent agent data exfiltration. Gain visibility into AI's interactions with your data / systems of record / existing software. https://discord.gg/tXjATaKgTV

SE-Agent is a self-evolution framework for LLM Code agents. It enables trajectory-level evolution to exchange information across reasoning paths via Revision, Recombination, and Refinement, expanding the search space and escaping local optima. On SWE-bench Verified, it achieves SOTA performance

[ICML'25 Oral] Multi-agent Architecture Search via Agentic Supernet

通过多智能体（Multi-Agent）打造的革命性的安全运营解决方案

利用claude code agent框架一步一步实现deep research！很强大很简单的skills。我一步一步介绍实现deep research，因为deep research就是agent框架第一应用，对比一下各个框架实现这个deep research，就知道哪个框架才是真厉害。简化版：https://github.com/liangdabiao/deep-research-agent-skill

A SAST skill that gives AI coding agents structured vulnerability detection across 34 vulnerability classes.

qKnow is an open-source agent platform for enterprise knowledge intelligence and industry AI. It provides knowledge graphs, RAG, and bot building, encapsulating industry AI into standardized modules for rapid deployment. Supporting unified integration of documents and data, it helps enterprises quickly build knowledge hubs and AI solutions.

An AI agent that brings Augment Code's power to the terminal.

Operational framework and patterns for high-quality, AI-assisted software development. This repository provides a single canonical guide for AGENTS.md and a lightweight workflow for repeatable, auditable, and architecture-first delivery.

Cross-runtime skills for Claude Code, Codex, and multi-agent workflows.

Agentic OSINT toolkit. Autonomous identity triangulation, 6-dimension cognitive profiling, breach analysis. CLI-first. 30+ platforms. 5 languages.

Modex · MH Agent — AI 全自动数学建模智能体,兼顾科研全流程:从赛题到竞赛级论文一夜跑完,国赛/美赛/华为杯全覆盖(架构展示)

Agentic RAG for any scenario. Customize sources, depth, and width

High-performance web crawler API optimized for LLMs. Turn any search or website into clean Markdown using remote browsers. Firecrawl alternative

Governed execution layer for AI coding assistants: clarify intent, route capabilities, review evidence, verify results, and write back lessons across Claude Code, Codex, OpenClaw, and Cursor.

A curated list of battle-tested tools, frameworks, and best practices for building scalable, production-grade Retrieval-Augmented Generation (RAG) systems.

Russian text quality for AI agents — neuroslop cleanup, typography, information style, editorial standards, UX writing, business correspondence. Scores text 0–10. 2,000+ linguistic atoms.

A safe bridge for Codex and ChatGPT to hand off coding work, save tokens, and keep local execution under control.

Durable coding-agent harnesses (Claude Code, Codex, OpenCode, Pi, fx) on a Workflow SDK World

Clouds Coder is a local-first coding agent platform centered on separating the CLI execution plane from the Web user plane, with Web UI, Skills Studio, resilient streaming, and long-task recovery controls.

A python wrapper for the Doc2X API and comes with native texts processing (to improve PDF recall in RAG). | Doc2X API的python封装，同时附带本地的文本处理(提升PDF在RAG中的召回率)。

ToolQA, a new dataset to evaluate the capabilities of LLMs in answering challenging questions with external tools. It offers two levels (easy/hard) across eight real-life scenarios.

better git cli for agents

Mimir - Fully open and customizable memory bank with semantic vector search capabilities for locally indexed files (Code Intelligence) and stored memories that are shared across sessions and chat contexts allowing worker agent to learn from errors in past runs. Includes Drag and Drop multi-agent orchestration

Provides integration of any AI agent (Gemini CLI, Claude Code, Codex CLI, etc.) with the Unity editor using Agent Client Protocol

AI Agent for Istanbul Stock Exchange and Turkish Investment Fund Data

Fully Autonomous AI Research System with Self-Evolution, built natively on Claude Code

A single CLAUDE.md file to improve Claude Code behavior, derived from Linus Torvalds' observations on coding pitfalls.

Kubernetes enhancements for Network Topology Aware Gang Scheduling & Autoscaling

Community collection of Apify agent skills for AI coding assistants

鸿蒙(HarmonyOS NEXT)开发知识包,一份源文件自动产出 Claude Code / Cursor / Copilot / Codex / Gemini CLI / Windsurf / ChatGPT 等 11+ AI 工具的配置文件,让 AI 像熟读华为文档的工程师一样帮你写 ArkTS / ArkUI。

Local-first persistent memory for AI coding agents (Claude Code, Cursor, Codex) over MCP. Decisions, lessons and facts live in one SQLite file on your disk. Offline, multilingual.

Earn RTC crypto by contributing to the RustChain ecosystem. Bounties from 1-150 RTC. Star, code, write tutorials, find bugs.

Mimeograph an expert into a SKILL.md or AGENTS.md for your agent.

Agent skills synthesizing years of software engineering discipline into a prescriptive methodology for solo developers

Open-source skills that empower any AI agent (Claude, Cursor, Hermes, etc.) to generate end-to-end marketing campaigns - UGC videos, ad videos, product photography and more.

Session-scoped /goal workflow for OpenCode with fail-closed persistence and an independent completion verifier. Maintenance mode: OpenCode 2.2.1+ ships a built-in /goal.

A robotic harness that gives LLM agents a visual-geometric control panel so that they can directly understand and invoke embodied tasks.

Multiplatform Client for ChatGPT using SwiftUI, support iOS, iPadOS & MacOS

top-style TUI for monitoring AI coding agent sessions

A recursive evidence-gated cognitive runtime for memory-native AI agents, combining hybrid retrieval, temporal reasoning, async learning, and plug-and-play tools.

Persistent multi-model workflow teams for DeepSeek Harness — dynamic lead planning, bounded DAGs, per-agent model/tools, Run Center and Token insights.

Agent skills for building iOS apps on iPhone Duo, Apple's first foldable iPhone — adaptive layout, vertical bars, hinge & scenes, camera, and design review.

An auto-documenting, model-agnostic AI workflow for any project, framework, and language. It reduces hallucination and keeps delivery predictable: the developer controls the path, AI executes the steps, and project standards stay consistent.

Find best-response to a fixed policy in multi-agent RL

Home of the AI workforce - Multi-agent system, AI agents & tools

A Foreign Function Interface package for calling C libraries from Python.

Opinionated AI-enabled workflows for product engineering

API gateway for purpose-based authorization for AI agents. Human approval for tasks, AI-native enforcement for agents.

Standalone agent runtime core with neutral LLM types, provider clients, tool loop, and extension protocols.

Reusable AI agent skills for Codex, including a PowerShell skill for safe Windows command invocation and optional MCP utilities.