Custom agents

Local-first semantic search, Related Notes & RAG chat for your Obsidian vault — an Obsidian plugin (vault-search-obsidian) and an MCP server (vault-search-mcp) over one LanceDB + Ollama index, with Personalized-PageRank graph retrieval.

12-week, project-driven Obsidian curriculum: cloud/infra engineer → AI Agent/LLM engineer. Companion narrative + interview prep for shaneliuyx/agent-prep labs.

基于大语言模型的智能研发效能助手。深度解析需求文档，精准识别逻辑漏洞；多维度生成测试用例，提升用例设计效率；构建可复用的测试知识库，将个人经验转化为团队资产。赋能 QA ，实现质量保障智能化。

Ready-to-fork starter for an AI-maintained knowledge base on the Open Knowledge Format (OKF) v0.1 — Markdown + YAML frontmatter, with a Claude Code skill, conformance validator, and EN/TH docs.

Ash — offline survival assistant for iOS. Gemma 4 E2B/E4B fully on-device (text · image · voice) with RAG-grounded answers over 56 emergency-response packs. Built for the Kaggle Gemma 4 Good Hackathon.

Portable marketing second brain for Codex, Claude Code, and Agent Skills with 502 sources for strategy, SMM, content, growth, CRO, and buyer psychology.

Local-first engine that grounds an AI agent's answers in your own Markdown and captures what it learns back into the KB — Node · TypeScript · MCP.

The runtime for production agents — bring your own model. Open-source, self-hostable, isolated Docker workspaces per session.

Deterministic 0-100 health score and agent fix-loop for Android Jetpack Compose. Wraps detekt + compose-rules

A long-running agent harness for building software from ideas.

Seu agente. Sua máquina. Suas regras. — agente pessoal de IA 100% local, com supply chain provada (SLSA + SBOM + builds bit-a-bit reproduzíveis)

Self-hosted toolkit of tools for AI agents & LLMs — web search, PDF, OCR, Office, sandboxed code execution. Python SDK + MCP, no API keys.

VS Code extension that opens Antigravity CLI (agy) in a dedicated right-side terminal panel — bringing AI-powered coding assistance into your editor, just like Claude Code and Codex.

File-first process system for governed repeatable AI-workflows

Browser automation & web scraping for AI agents — drives your own logged-in Chrome, then distills one successful run into a free, deterministic skill you can rerun daily. Claude Code / Codex / Qoder compatible Agent Skill.

Universal novel-writing skill for AI coding assistants: 5-stage pipeline (interview, setup, craft specs, writing loop, revision & release), 28 craft specs, 34-writer technique library, 8 genre styles, memory system for long-series continuity.

MCP server giving AI agents instant access to 1,500+ free public APIs — search, probe, and generate code snippets

71 research-backed Semantic SEO rules packaged as an AI agent skill — works with Copilot, Claude, Gemini, and Cursor. Includes companion prompts and Ubersuggest MCP integration.

Native paper workflow and AI-assisted editing for reMarkable Paper Pro Move.

高保真原型设计 Agent：自然语言 → 可交互、可离线打开的原生 HTML 原型

Oh-My-PM - Product Manager AI Agent Workflow System via Claude Code Skills

拆抖音对标 · 输入一个抖音账号，全量采集公开作品数据并产出对标调研报告（原始数据 + Markdown + 浅色杂志风 HTML）。Agent-friendly skill.

A self-evolving project builder. Given a vision and spec, it autonomously builds and improves a project session after session. Just drop it into your existing project and go.

Architecture optimization skill: six decay risks (R1-R6), quality metrics, regression guard. Five stdlib-only Python scanners, zero dependencies. Architect-programmer dual-agent workflow.

Open-source chat frontend + agent server for the Mastra AgentController (Agent Harness). Tool approvals, subagents, observational memory, schedules, and a live workspace — ~50 controller events wired to Vercel AI Elements. Clone the whole stack, or install either half with shadcn.

Autonomous lab-machine engagement loop for Claude Code — Kali in a container, a skill that drives it, and a methodology that rewrites itself after every run

Verified agentic AI evaluation labs, public-sector assurance tools, reproducible failures, real-model evidence, and provider-neutral test contracts.

Open Agent Security Fabric — red-team agentic AI, MCP firewall SDK, action oracles & SARIF CI gates. Assure, Enforce & Govern. Python + TypeScript. OWASP LLM/Agentic/MCP Top 10.

Repository-aware context and validated workflows for Codex, Claude Code, Cursor, Copilot, Gemini CLI, and OpenCode.

Medusa is an open-source AI agentic red-teaming framework powered by LangGraph and a Re-Act Architecture.

Praxis Kubernetes Operator

eNSP配置助手：华为 eNSP 拓扑点选、VRP 一键配置、学习对照与 AI 助手

本象协议 Benxiang · 一源万影：保存本象，按需投影。面向 AI 的持久对象表示层——AI 只提交语义事务，确定性编译器校验后才落地，每个字段都能回答「凭什么」。A2 消融实测（2026-08-13，README §5）：唯一幸存的分类性主张是结构性的——提示词结构上产不出证据链；A3 全套机制给 15.0%/27.5% 受测字段可溯源证据，所有纯提示词基线均为 0%（A0→A2 +41.3pt 显著 p=3.3e-5，A2→A3 +2.5pt 不显著）。四方言共用核心仅加 4 行；87 条语言无关一致性向量 + 两份实现。

Luna is an advanced, native power-user BYOK Roleplay & AI Ecosystem for Android with Hierarchical RAG, Visual Novels with action options, and zero censorship.

Your network's first AI employee. Self-hosted autonomous agent that discovers, monitors, and manages your entire infrastructure — no IT department needed.

AI-powered education infrastructure platform for assessment, grading, OCR, analytics, and learning intelligence.

An automated, agentic exploratory testing tool that performs comprehensive QA testing on web applications, simulating human user interactions through various input methods (mouse, keyboard, TAB navigation, arrow keys, etc.).

政企会议纪要skill

Native Rust and Slint meeting overlay for Windows and Apple Silicon macOS, with real-time transcription and local or cloud AI answers.

Reference implementation of Double Ratchet: co-evolving an inspectable evaluation metric with a lifecycle-managed skill library for self-improving LLM agents (arXiv:2607.12790)

Household decision simulation through persona-enriched multi-agent negotiation. The HDSim method core.

Defense-in-depth against prompt injection in tool-using LLM agents. Semantic drift detection catches synonym-evading attacks that bypass regex. Self-play red-team, calibrated scoring, ablation study.

Diagnose Chrome Manifest V3 extension pitfalls — and teach AI coding agents to avoid them.

A group management bot written in python3 using the python-telegram-bot library.

📈 Prediction of Particulate matter 10 value of air pollution to help people with breathing problems.

Template copier para proyectos de Data Science con uv, Sphinx y estructura modular

AI and data architecture portfolio: temporal legal search, Azure agentic RAG, and production engineering.

跨框架 Agent Skills 合集：视频笔记生成、本地识图、Windows 桌面/浏览器自动化，外加 Hermes 语言路由插件。DSH 插件已拆分为独立仓库。

DSH-TUI: a lightweight and fast terminal plugin connected directly to the DSH runtime.

Run Cursor Cloud coding agents from Hermes, on hosted VMs or isolated workers on your own machine.

配置驱动、可恢复的 Agent Runtime：CLI/TUI、TypeScript/Python SDK、Protocol v2、宿主验收、有界 Loop、上下文压缩、Replay、Child Run 与安全执行环境

Structured decision comments (ADCs) for agent-written, human-reviewed code.

Own your agent security: a deterministic, offline firewall for AI agent tool calls. Same call, same verdict, no model in the path.

Production reference for agentic commerce: protocols (ACP, AP2, x402, MCP), stablecoin rails, agent skills, and the merchant playbooks specs leave out — refunds, multi-chain settlement, catalog discovery, fraud, jurisdiction, receipts. Maintained by Cryptorefills.

Open-source B2B product marketing skills for AI agents, built from 10+ years at Salesforce, Dropbox, Zeplin, ServiceNow, and startups.

x402 buyer SDK for AI agents — deterministic multi-chain routing (Base + Solana), RPC failover, and spend-before-signature guardrails. TypeScript + Python.

Unofficial local-first Polar AccessLink Dynamic API v4 MCP server for AI agents

RAVERSE: AI Multi-Agent Binary Patching System with MCP Server (35 tools, npm/pip/docker)

Universal quality evaluation plugin for Claude Code — 7-dimension scoring (correctness, completeness, adherence, efficiency, safety), configurable rubrics, threshold blocking, auto-hooks & /judge command.

A deepseek harness plugin for tensorlake sandbox

Agentic TCS proof search with statement review, persistent authoring, independent criticism, and LaTeX editing.

AI-driven architecture browser: MCP server + desktop app. Claude Code, Codex & other AI agents explain your codebase with guided walkthroughs, diagrams and visual artifacts. Read-only, local-first. Tauri + Rust + Svelte.

Agent skills for UnityCLI - AI agents develop Unity games from the terminal: 140+ live Editor commands (scenes, assets, tests, builds) without an MCP bridge, plus editor installs and CI automation

Swarm collective learning & coordination framework with MCP-enabled ASK agents for enterprise-scale AI collaboration

Autonomous marketing agency powered by Claude Code agent swarms — multi-agent pipeline for content, SEO, campaigns, and more

Open source LLM observability for the waste axis - 4 deterministic detectors + LLM-as-Judge, waste-rate metric verified across 3 corpora / 16,864 sessions

Deterministic, scripted, unattended Claude Code execution.

Cross-platform TokRepo search skill for Claude Code, Codex, Cursor, Gemini CLI, and AGENTS-compatible tools.

Your AI research lab

EdgeResearch — autonomously improve any named artifact (prompts, copy, code, system, perf) through measurable experiments. Methodology port of @karpathy's autoresearch.

Hosted MCP server for ContextWire web search, academic research and page extraction

Local-first theme customization tool.

zephex Hosted MCP skill pack 10 tools, 13 editors (Claude Code, Cursor, VS Code + 10 more). Live repo analysis package upgrades, codebase scoping. No token waste.

MCP server for SendSoon — send email, IP lookup, and file-to-Markdown from AI agents.

Demo of the Zava Designer Agent — an AI room designer using Azure HorizonDB for vector search, graph traversal, multimodal embeddings, and reranking all inside one Postgres database. From Microsoft Build 2026.

AgentReady — Transform any legacy repo into an AI-agent-ready codebase. Generates agent-context.json, AGENTS.md, CLAUDE.md, MCP config, and tool scaffolds via a single GitHub issue or Actions workflow.

Self-hosted agent native Slack / Teams / Linear substitute. Built to enhance how i work:)

ZK-gated community where humans and AI agents coexist. 🏅 1st Place — The Synthesis Hackathon (Agents That Keep Secrets). Built on ZKProofport, Base, Noir circuits.

Your app generates its own verified UI transition graph — screens as nodes, guarded (event, effect) edges. Proof-gated verification, trust tiers, model-free MCP for AI agents.

rviz-mcp — MCP server for RViz2 displays, frames, and views (mock + live) for AI agents

一款轻量化的任务/日程可视化提醒程序，基于语音识别与大模型分析简化日程创建流程；轻任务（LiteTask）；

17 installable agent skills for distinctive web design: art direction, implementation, critique, accessibility, and visual QA for Codex, Claude Code, and Cursor.

AgenticStore: The secure toolkit for AI agents. Instantly equip Claude Desktop, Cursor, and Windsurf with 75+ MCP tools, persistent memory, and SearXNG search, all protected by a built-in PII prompt firewall to protect your data from being exposed to AI agents.

Your AI agent reads the codebase. You speedread the report. An agent skill + one-file RSVP reader for markdown reports.

specframe is a zero-dependency CLI that scaffolds the minimum set of context files a modern repo needs to collaborate with AI coding agents (Claude, Copilot, Codex): ADRs, rules, guidelines, runbooks, a glossary, agent prompts, slash commands, and skills.

A native macOS desktop pet and agent companion that tracks Claude Code, Cursor, and other AI agents in real-time. Built with native AppKit & Core Animation.

MCP server registry and marketplace — discover, install, activate, and manage MCP tools on demand

AI-powered welfare scheme eligibility engine for India — reasons over real eligibility rules instead of keyword search. 5-agent pipeline, FastAPI + Next.js.

A child repo for your repo — gitignored, shared, auto-synced

Director: AI-first local system for producing live-app presentation videos and decks.

LinkedOut — a satirical LinkedIn for the unemployed, built on DeepSpace. Live at linkedout.app.space

Universal Shared MCP Memory Server - Multi-tool compatible memory management for AI assistants across Claude Desktop, Cursor, Windsurf, Cline, and more.

Zero-trust security runtime for AI agents with deterministic policy enforcement, guarded execution, approvals, redaction, MCP protection, and tamper-evident auditing.

Run a fleet of agent coding agents from Neovim

医学科研 AI 智能体团队：面向中文临床研究者的 OpenCode 工作流插件

10-stage SEO content pipeline built using Claude Code skills. Research-deploy, with human approval gates after each step.

🛡️ Local privacy firewall for AI coding agents — masks API keys & personal data before they reach the cloud, then restores them transparently.

Agentic quantitative research framework for data pipelines, notebooks, and trading strategy development.

Project-aware multi-model harness for Claude Code with account routing, isolated sessions, LeanCTX, and MCP integrations.