Custom agents

Pi coding agent 的桌面工作台：Web UI + Electron 壳，内置右侧浏览器控制、Univer 表格/文档/PPT 深度集成、会话可视化与团队协作

Your AI agent writes code — but does it know WHY your code exists? Decision provenance, quality contracts, and AI anti-pattern detection for coding agents. 19 languages. MCP compatible.

Embeddable agent runtime and workbench for teams that need sandboxed execution, host integration, platform governance, and reusable AI infrastructure.

A reusable image-generation skill for quiet folk-print stamps and photo-to-stamp transformations.

A native desktop app that gives non-technical users a personal assistant with persistent, learning memory. You talk; it captures, organizes, remembers, and improves over time.

Fedora Kinoite 45 based Linux distro with agentic AI features.

A Claude skill and standalone CLI for inspecting, debugging, and injecting code into a running Steam client (desktop or Steam Deck) via the Chrome DevTools Protocol (CDP)

基于 DeepSeek Harness + AKShare 的本地 A 股 AI Agent 工作台：数据获取 / 每日晨报 / 交易复盘三大技能，只做分析、不做交易。

An open-source AI agent that tests your investment thesis (why you own a stock) against new company filings—with exact citations, human review, and version history. Built for investors who care about the business behind the stock—whatever their investing style.

⚡ Structural code intelligence & call-graph engine for C# and .NET — built for AI coding agents under hard token budgets.

Drop-in operating systems for knowledge workers. Product Manager OS: 53 skills scored 100/100 in CI, an operating brain, a memory that learns your product, and a loop that builds you new skills from the work you repeat. Runs on Claude Code, Cowork, Codex, Cursor, and Gemini CLI.

Configurable, unobtrusive Web Audio lifecycle notifications for DeepSeek Harness (dsh): 10 events, custom sounds, offline playback.

Codex、Hermes 与 Claude Code 的本地桌面协作中枢

Rust backend daemon for Intent — agent orchestration, workspaces, and the JSON-RPC wire protocol

One local dashboard for many Git repos - status, Docker, and your Codex/Claude/Gemini CLI sessions.

Persistent knowledge and validation-gated skill evolution for coding agents, based on arXiv:2608.27454.

Practical patterns, starters & CLI tools for memory engineering with AI coding agents. Stop re-explaining the repo — design the memory. Get a Memory Ready score.

Markdown templates generator for agentic-assisted coding

Use the official Grok Build CLI as a controlled external subagent for Codex via ACP and MCP.

自托管跨平台远程开发与自动化平台，提供 Node、Hub、MCP、Web Console 与 AI 控制能力

Drop-in .claude/ config that turns Claude Code into an autonomous academic paper production system. 6 agents, 47+ skills, 5-phase pipeline from literature search to submission-ready manuscript.

Free, open-source MCP server for Roblox Studio. 31 tools, a console panel that runs coding agents, editor-safe script edits.

TradingView alerts MCP server: create, list, pause, resume and delete TradingView alerts from Claude, Claude Desktop or Cursor. Pine strategy alerts with webhook support.

🤖 Explore essential AI engineering resources, from research papers to tools, to help software engineers transition into AI roles effectively.

An Autonomous AI Agent with a custom MCP server that does Duolingo for you and sends Discord notifications when done

Livingcolor plugin for Hermes agent

Real-time options intelligence for AI agents — 20 MCP tools for 0DTE SPX analysis

A Claude Code skill that checks a branch the way a careful reviewer would, then pushes it. Two adversarial model reviews, a blocking security pass, a coverage gate, and a live run. No dependencies.

Stealth browser automation for AI agents — unattended, headless, N parallel persistent logged-in Chromes. One MCP server + CLI, credential vault with TOTP/IMAP 2FA, vision clicking, prompt-injection scanning. Self-hosted, real Chrome. 1,061 tests.

Companion tools and reference patterns for SPECLAN, the VS Code extension for spec-driven development with hierarchical Goal/Feature/Requirement specs as Markdown files in Git.

Bipa CLI — payment rails for AI agents. Pre-built binaries and managed installer.

Turn recorded screen activity into deployable n8n workflows.

Let AI agents QA your macOS app in the background. No synthetic input, no stolen focus.

Open-source, self-hostable system of record for team decisions capture the why, review the outcome.

Cross-tool persistent memory for AI agents — local, private, no API key required

13 negotiation & persuasion skills for AI agents, distilled from 36 books: CIA psyops, FBI behavior files, propaganda science, dark psychology. Plain English. MIT.

Multi-project mission control for Hermes Agent users.

Content-addressed SKI compute core with bit-exact consensus. Spec-first, multi-model reviewed, machine-verifiable conformance.

基于 Bridge Framework 的同花顺工具，提供基本数据服务与简易量化，可用于数据基座与起步项目。

Decision boundaries and installable skills for AI coding agents.

Work anywhere. Orchestrate coding agents and real terminal workflows from one Web command panel.

Local action firewall for AI coding agents: scans what the agent reads, taints the session, blocks dangerous follow-up actions

Batuta, an independent community orchestration extension for CompozyOS

Postey MCP server and agent skills. Draft, schedule and publish social posts to nine platforms from any AI agent.

Terminal-based AI coding agent — provider-agnostic, MCP-ready, with live reasoning streams, prompt caching, plans mode and a skills system. Pure ES modules, zero build step.

Local AI automation workbench for Siemens PLC and industrial-robot R&D: MCP, TIA Portal V21, PLCSIM, guarded writes, and offline-first verification.

Open-source identity and authorization layer for AI agents. Issue verifiable credentials, manage decentralized identifiers, and enforce scoped permissions — self-hostable, standards-compliant, and built for autonomous AI systems.

Multi-Agent Harness for Visual Design

Portable session history for AI agents and harnesses.

An MCP server for orchestrating multi-agent workflows inside herdr, enabling real-time communication, pane management, and contextual handoffs.

Watch your Herdr coding agents as an 8-bit town. Read and answer them without leaving it.

Astucia Wiki is a flat-file, AI-enabled, Git-enabled, self-hosted wiki that combines Markdown pages, draw.io diagrams, spreadsheet lists, and team chat — all stored as plain files on disk. No database.

Private, local-first continuity for terminals and AI coding agents—from desktop to phone, with a self-hosted encrypted PWA.

Open-source multi-platform ads management for AI agents — connect your ad accounts, manage them via MCP + CLI with policy-guarded writes

Measure a repository as a place for a coding agent to work, and lay the foundation where it has none. A Claude Code plugin: hooks, guards and gates proven to turn red, layered docs, a repo graph, and a five-dimension assessment you can take again later.

A reusable Codex playbook for structured AI agent workflows, architecture documentation, and project-specific coding guidance.

An intelligent WhatsApp Food Ordering System built with n8n that automates order management, inventory checks, and customer interactions — all through WhatsApp. This project is designed to help restaurants and food businesses manage customer interactions efficiently using AI, Google Sheets, and the WhatsApp Business Cloud API.

A curated list of persistent AI frameworks, seeds, individuals, covenants, lineages, and research

Self-hosted AI assistant for WhatsApp, Discord, and Telegram — powered by Claude, Gemini, or GPT, with all data on your own infrastructure.

Turn the product you design for into ready-made context for your AI tools: navigation mapped, key pages captured as editable snapshots, design tokens extracted from the running product. Then wireframe your next feature on top of the real thing instead of describing it from memory. Built for designers, no code required.

GPT Image 2 ecommerce Skill for product-preserving main images, white-background product photos, PDP prompts, and QA｜电商商品图 Agent 工作流

Roslyn code intelligence for AI coding agents, over MCP. Navigate C# by structure — symbols, references, call graphs, surgical edits — for 81% fewer tokens than reading files. Works with Claude, Cursor & Copilot.

🕷️Browser CLI built for agents, powered by Bun WebView with Kitty graphics rendering

Automate the Doubao AI web client via Playwright. Send/receive messages, upload files, manage conversations, and persist session URLs across restarts. 通过 Playwright 自动化控制豆包 AI 网页端。

JARVIS is a powerful Python-based AI assistant that automates tasks through voice commands, including scheduling, web searches, and smart device control. With over 230 files, it’s designed for easy customization and scalability, making daily activities more efficient.

CHAT BOT WITH UI

RAG-tool for workshops and pilotprojects.

Production-grade RAG system for AEC design management with GraphRAG, Ollama, and FastAPI. Supports CAD/PDF parsing, version tracking, and impact analysis.

A local-first desktop workspace that turns your notes, documents, and workflows into context for AI.

Fast, offline-first code editor and web IDE for Android - AI agents, terminal, LSP. No ads, no account.

看清 AI 编码智能体的每一次可观察行动。 · Trace your agents, down to every tool and MCP.

Open-source reseller toolkit for the Proxies.sx Pool Gateway — SDK, drop-in React component, and Next.js storefront template

Local-first AI media generation and video editing toolkit for coding agents, with a Bun CLI, TypeScript SDK, MCP server, and Agent Skill.

An open-source framework for agentic PCB design.

Local-first shared memory for AI agents — zero-dependency, governed writes, citations, MCP. Source behind the ihow-memory npm package.

An agent orchestration platform with a simulated software company on top

An open library of security skills for AI agents - pentest, bug bounty & defense. 85+ trigger-loaded skills across 16 domains (web, API, cloud, AI/LLM, AD, mobile, and more). Load into Claude Code, Codex, Gemini, or a local model.

An autonomous AI agent for intelligently updating, maintaining, and curating a LightRAG knowledge base.

A general-purpose agent fleet you run yourself — any model, in a sandbox, on a budget, connected to your data.

Agent skills for AI coding agents — trip planner, Obsidian vault, and more

Multi-agent AI 🤖 with Apache Airflow and Gemini meets child development 👧🧒. Like a diet needs balance, so does play. With Gemini 3, O*NET data, and an intuitive UI, you get a personalized roadmap, because parenting is hard enough.

MCP server + desktop app for the Defold game engine: AI agents can build, bundle, run, hot-reload and inspect Defold projects, drive the running engine, and search the API reference

Proof of Done — The Agentic Software Development Manifesto. When agents write the code, done is a state of the system that can be proven.

Progressive Spec-Driven Development (SDD) toolkit for AI coding agents — Claude Code, Copilot, Codex. Slash-command Skills + structured AI Knowledge + MCP server; Progressive Disclosure cuts 70–80% tokens. Brownfield & greenfield.

A Claude Code setup where the skills fire on their own: situation-routed skills, subagents, a session routing hook, and a verification gate whose every check is mutation-proven falsifiable. Installs global, per-repo overlay, or plugin marketplace.

A self-improving ML agent that compounds capability across projects through knowledge crystallization, reusable skills and shared ML/MLOps infrastructure.

OS-level security supervisor for AI coding agents. Gates security-relevant syscalls on Linux and pauses ambiguous actions for human review.

Stop reinventing the wheel. MCP server + CLI that makes AI coding agents search GitHub for existing open-source solutions before implementing — scored 0-100 with adopt/adapt/inspect/avoid verdicts.

Process-focused TCAD simulator for semiconductor fabrication, featuring voxel-based wafer modeling, lithography and mask workflows, deposition, etch, CMP, implantation, annealing, oxidation, metrology, 3D visualization, WebUI, and recipe design tools.

Quality and trigger-evaluation gate for reusable AI agent skills.

Conversational AI. Sweded. A self-hostable home for voice agents: mix and match the LLM, voices, and MCP tools that fill every stage, spoken through small ESP32-S3 boards.

Autonomous Security & Zero-Trust Governance Guardian for Enterprise AI Agent Fleets powered by Gemini & Google Cloud. Built for #AllThingsAgenticHackathon.

Static-only binary analysis CLI and Agent Skill with bounded, evidence-backed output

Local-first persistent memory for AI agents: Chinese-first recall, forgetting-aware ranking, conflict candidates, SDK + CLI.

macOS menu bar SSHFS mount manager with an MCP server — 30+ tools so AI agents can mount, heal, wake and operate your remote machines

Live visualiser for Technocore agent rooms. Every figure on the field is one real signing key that posted.

See which notes your coding agent actually reads — a live radar for Claude Code and your Obsidian vault.

Lightweight prompt injection detector for LLM, RAG and AI agent applications using Sentence Transformers + scikit-learn.

Skill template for AI agents

Track your AI subscription usage. Works with Claude Code, Codex, OpenCode and Grok.