Custom agents

Client-side runtime for AI agents on the web.

Full-spectrum wireless security MCP server — WiFi, Bluetooth, RF/SDR, NFC/RFID, Cellular/5G, IoT, MouseJack, air-gap, UWB, WIDS/WIPS, compliance. 34 tools, 9 knowledge bases.

A backend-agnostic web workspace for coding agents (Claude Code, Codex, …) — manage many concurrent agent CLI sessions with a tiling window manager, structured chat view, file explorer, and code editor.

Momo — our first attempt at a digital store manager, and the start of this journey. Now carried forward as Saros (in preparation).

Docker-based sandbox that runs AI coding agents with no git, no SSH, and can only access project folder. Built because permission prompts aren't real protection — you end up accepting everything by reflex, that's not a decision, it's fatigue. pi and opencode built-in. Extendable to use other agents running a single register command.

狗头军师 · Kynsage — 给不写代码的人用的 Claude Code 指挥台。一个窗口同时指挥一群 AI 同事，谁在忙、谁等你拍板、谁改了文件一眼看清。

A Claude Code skill: indie-maker checklists inspired by Pieter Levels' MAKE, organized by Idea/Build/Launch/Grow/Monetize/Automate/Exit.

IRCv3 platform adapter for Hermes Agent (SASL, observe-mode, runtime channel agency, chathistory persistence)

Open-core, AI-assisted drafting workspace for O-1A / EB-1A / NIW petitions.

Stable local-first terminal coding agent with durable sessions, consequence-gated autonomy, any-model providers, skills, MCP, and ACP. TypeScript + Bun + Ink. By Meiiie / The Wiii Lab.

Make opencode fully uncensored — ayushanzarai agent config

AI deleted my files? ai-trash intercepts rm from Claude Code, Cursor, Copilot, Codex and others — moves files to recoverable trash instead of permanent deletion. macOS, Linux, Windows.

🤖 Jarvis — Ein hochmoderner, deutschsprachiger KI-Assistent basierend auf Gemini Live. Mit nativer Sprachausgabe, MCP-Unterstützung und Vision-Features.

面向电赛视觉的泰山派 RK3566 Linux Codex/CC Skill：从题目分析、板端探测到 OpenCV/V4L2、UART/GPIO/RKNN 验证与工程验收。

不動産鑑定士が公開する白箱方式の土地査定OSS。MLIT取引データからヘドニック回帰係数を都度推定、業者用シート（係数全開示）と顧客用シートを生成。Claude Coworkerシリーズ。White-box AVM skill for Japanese land price assessment. Re-estimates hedonic coefficients on every run from MLIT transaction data, generating broker-side worksheets (full coefficient disclosure) and client-facing assessment reports (xlsx). Part of the Clau

Agentic Browser Extension

AILinkX 是一个连接于数字世界的独立智能体。它不依赖特定 IM 软件，而是通过视觉感知与模拟交互，为用户构建全息记忆宫殿、情感计算雷达与自主事务执行官，通过 AI Agent 彻底重构您的数字生活体验。

Daily tech-news zine for engineers — Claude-authored prose, bespoke HTML, CJK typography. Deployed on Cloudflare Pages.

Evidence-first Agent Skill for economics and management paper writing, polishing, peer review, citation integrity, method safety, LaTeX, and auditable revision.

Live crypto trading signals and market data served to AI agents.

A terminal agent for long running coding sessions

A skill that analyzes A-share trading signals using chip structure, resonance, KDJ, Wyckoff, and Chan theory. 利用筹码结构、共振、KDJ、威科夫和缠论分析A股信号的skill。

Hermes-webui（directly importing AIAgent）

Native Windows AI agent workspace with observable runs, controlled tools, MCP, and provider debugging — built with C# and WinUI 3

Voice teammate for Claude Code: talk to your live session hands-free, hear replies spoken. Local whisper STT + macOS TTS. /voice-on in any session.

BCI Research - 脑机接口技术调研 + BCI Agent Demo

Local-first AI coding agent desktop: Electron + Rust host core + pi Agent Harness + user-installable plugins

TikTok Shop GMV Max diagnostic framework - 4 steps + Layer ABCD (bilingual EN/中文)

Feishu-native Codex plugin for project reports, Docs, Wiki, Bitable, private updates, and guarded local assistant workflows.

A lightweight CLI AI agent that can read files, write files, and list directories.

One-click Render deploy template for nanobot — a lightweight self-hostable AI agent

Universal 5-layer book distillation skill for AI agents (Codex / Hermes / Claude Code). Turn books into compounding knowledge via 求同存异 cross-book synthesis.

Control your local Claude Code from a mobile-friendly browser UI, anywhere. Self-hosted, end-to-end encrypted, with multi-host multi-device support.

Self-hosted WhatsApp and Telegram CRM gateway with multi-session messaging, AI auto-reply, knowledge base, REST API, webhooks, media support, real-time dashboard, Whatsapp Official API, and external agent integration.

多 Agent 对抗式投研助手：多空各持一方举证、第三方裁决 | 自用工具，不声称盈利、不构成投资建议 | Multi-Agent stock analysis with Bull/Bear debate (Claude + DeepSeek)

An agent-native sandbox runtime: run many isolated sandboxes (beds) from one process, with an OpenSandbox-compatible HTTP API.

AI Agent Skills library to facilitate technical lead in a software project

Claude Code skill for local LinkedIn lead scouting and outreach automation.

Crest -- The desktop app for Claude Code. Hybrid chat + terminal, multi-agent orchestrator, super agent.

A high-performance Rust CLI for the Semrush API. Agent-friendly with structured JSON output, rate limiting, caching, and batch workflows.

Cross-agent skill manager — one global store, clean agent folders, activation via skill.config. Works with Claude Code, Codex, Cursor & Gemini.

基于 Dify + Ollama + MCP 实现的全本地化电商客服智能体

A Claude Code skill that evolves your ideas through Darwinian selection — scoring, crossbreeding, mutation, and structured deepening.

One agent SDK, hand-ported to 8 languages — JavaScript, Python, Go, Java, C#, Elixir, Clojure, Rust — every port held to the same spec by a CI-enforced cross-port conformance suite, all eight at full tier. MCP · skills · native · HTTP · built-in · A2A tools behind one interface. Docs: https://muthuishere.github.io/toolnexus/

Code for 'Evaluating Collective Behaviour of Hundreds of LLM Agents' (AAMAS SE 2026)

Build self-evolving AI agent harnesses with portable harness units, artifact-aware testing, trace-backed diagnosis, and evidence-gated promotion.

Chat between the AI agents on your machine — they coordinate, ask each other questions, and get notified. No server to run.

A governance framework for multi-agent AI systems. Structure, lifecycle, and quality controls for AI agent orchestration.

Assemble your AI team — a multi-agent product management framework for Claude Code

Run Claude Code, Codex, OpenCode and other AI coding agents side by side in tmux as one fleet: they message each other by name, flag when they need you, and resume after a reboot.

A virtual life form dedicated to progress together with you and your team / 一个致力于与您和您的团队共同进步的虚拟生命体

A Claude Code orchestration protocol prototype for approved plans, bounded agent roles, and verified parallel work.

OpenCode + Ollama multi-agent workflow with builder/reviewer agents, headless runs, skills, validation gates, local session evidence, and redaction tools.

Multi-agent orchestration for teams and individuals — local-first AI, custom experts, Slack integration, and collaboration with human approval.

The React framework for building agents into real apps — one definition serves humans (streamed HTML, zero client JS) and agents (markdown, JSON, MCP), nothing duplicated. Web-standards core, deploys to Cloudflare Workers.

🤖 AI Voice Assistant with Memory, Wake Word & Smart Device Control

Autonomous content-publishing pipeline that learns from its own audience and rewrites its own prompts (agentic, self-improving)

DataClawEval: A Benchmark for Engineering Data Agents in Real Industrial Harness

Agentic Ops Harness | Superpowers Like AI Harness for Ops. Currently works with Hermes Agent

Universal agentic engineering layer for Google Antigravity. Features autonomous multi-agent orchestration, epistemic grounding, 9 strict verification gates, AST blast radius analysis, and target project adaptation.

Eticas AI Risk Taxonomy: Open, machine-readable AI risk taxonomy mapped to the EU AI Act, NIST AI RMF, ISO/IEC 42001, and 15+ other frameworks.

Shared, versioned memory for AI coding agents — MCP server with git-style history (log/diff/blame) for Claude Code, Cursor & Claude Desktop

Companion code project for the ebook Vector Database Engineering for AI — Building High-Performance Retrieval Systems for LLMs, RAG, and Agentic AI.

AI-native QA patterns for governed automation, RCA triage, agentic workflows, and deterministic Quality Gates.

Own your agents, not rent them. Import them into one multi-harness dashboard, with memory and agentic apps powered by a workflow engine. No lock-in.

Starter Kit for AI Native Applications - Vite Plus (Vite+) TanStack Start monorepo with Paraglide.js (i18n), drizzle-orm, better-auth, Feature-Sliced Design (FSD)

Post to Tiktok, Instagram, Facebook, Linkedin using API

Local viewer for VS Code GitHub Copilot Chat sessions. Reads transcript & debug JSONL files locally and shows session metadata, turns, models, tools, agents, token usage and estimated AI costs. No data leaves your machine.

Agentic Component Manifest (ACM) — universal, schema-first manifest format describing UI components from any framework for AI agents and tooling. Canonical JSON interchange, token-frugal Agent View, executable conformance suite.

Penalize the Path, Reward the Outcome — verifiable per-action penalties as a dense channel for deployable, sample-efficient agentic RL (GRPO). Paper: arXiv:2607.07435

🏆 Dell Cloud Native Award Champion, Agent M

An OPC-UA MCP Server - talk to your robots and PLCs

Phased planning and execution for Claude Code. Roadmap, plans, and progress live in files that survive a /clear.

Cloud-native smart token & queue management system - real-time queues, AI assistant, team messaging, ML predictions. React + Express + Firebase.

一套由本地 Markdown 驱动的长期 AI 协作模板，让背景、此刻、方向与选择不再随对话丢失。

HermitDoc — Hermes Agent configuration expert & system doctor. 23 skills covering config, delegation, channels, MCP, voice, security, and troubleshooting — grounded in real CLI verification. Inspired by ClawDoc.

ReferralHub is a MERN stack platform designed to streamline and manage referral-based campaigns. It allows businesses to create campaigns, track referrals, and analyze campaign performance while providing users with an easy way to participate in referral programs..

Welcome to the digital thunderdome, you keyboard-smashing lunatics! This ain't your grandma's chatbot, it's a CLI-powered, LLM-fueled beast! And guess what? It also supports Telegram integration right out of the box. Get ready to unleash the madness!

A high-performance coding agent - fast, context-efficient, and deeply integrated.

Workflow slash commands for AI coding agents. Spec-driven. Guardrails, not autocomplete.

A practical AI/ML engineering playbook for real-data-first, baseline-driven, production-aware AI/ML projects.

Self-hosted document intelligence for RAG — parse, classify, split, and extract from PDF/DOCX/PPTX and images: searchable, cited, retrieval-ready chunks and schema-driven extraction

Query-aware context trimming for LLM requests. Your context could use a trim.

Open-source platform for university students

A production-grade Retrieval-Augmented Generation (RAG) system built for 10,860+ Indian Legislative Acts. tackling the unique challenges of processing Indian legal documents—spanning multiple languages, diverse formats, and complex legislative structures

Local-first persistent memory for AI coding agents (Claude Code/MCP). Reliable semantic recall — $0, offline, open source.

LES: local and distributed evidence system for project documents, verifiable retrieval and model tools.

Sovereign, sub-millisecond semantic search for Rust and the browser

The open benchmark for measuring the reliability, reproducibility, and determinism of AI context systems. Transparent metrics, reproducible tests, vendor-neutral results. Context Trust Levels CTL 0-4.

Windows WSL2부터 Docker·Compose, 온프레미스 DevSecOps, Ollama·RAG 기반 AI 애플리케이션 개발까지 다루는 한국어 실습 교육 자료

嘉立创EDA专业版扩展：基于本地Embedding模型的RAG知识库。EasyEDA Pro Extension: The local RAG knowledge base based on an embedding model.

Free offline AI with complete Wikipedia knowledge - 100% private

Lightweight Python package for Ollama & 10+ open-source LLMs. No install, no login, no API keys. Free cloud RAG development.

Production Modular RAG System: a compact, production-minded Retrieval‑Augmented Generation (RAG) service built with FastAPI: file ingestion, chunking, embeddings, vector indexing, semantic search, and configurable LLM backends (built with strong software base).

Migrate vector DBs to a new embedding model without re-embedding. Linear maps from ~2K calibration texts, ~87-91% retrieval retention (BEIR-benchmarked).

🇲🇽 Toda la ley federal de México en Markdown, versionada y autoactualizada a diario desde el DOF/Diputados. AI-ready Mexican law dataset.

A doctor-assistive AI system that interprets medical knowledge and patient images simultaneously. It utilizes a Dual-Encoder architecture to cross-reference textbook theory with visual pathology, generating clinically grounded diagnoses.

local-first persistent memory for Claude Desktop, enabling private hybrid RAG search across past conversations without API calls

AI-first multi-agent SaaS platform. Plug your applications as plugins.

Nyx — 夜之感知层。Veil Bloom Filter + Mist Phantom 寻回失落记忆，Thalamus 路由 + Hypnos 梦境的第三子系统。