Custom agents

Caret^ cuts repeated agent instructions down to compact notation. Across our sample set, prompt length was reduced by 95.8% by rewriting agent skill and persona files using Caret notation. This is for you if you ever draft or use Markdown files as agent skills or personas. If you design harnesses, it is a no brainer.

🧬 基于 AI 的 SBTI 毒舌人格测试：15 维度深度行为建模，支持人格碰撞分析与 AI 自定义诊断报告。比 MBTI 更接地气的互联网原生性格工具。原作者：B站@蛆肉儿串儿

Rust SDK for Dakera AI agent memory — self-hosted, 88.2% LoCoMo. HTTP/gRPC, vectors, hybrid search, knowledge graphs, sessions.

Translate and adapt Superpowers for Chinese AI coding tools, with 20 skills and 6 China-specific workflows for better planning, coding, and debugging

A small toy skill for Codex and other code agents that adds a persistent ASCII companion pet to terminal coding sessions.

GovInsight-AI 是一个基于大语言模型 (LLM) 的政务诉求工单办理质量智能检测系统。该项目专门针对政务服务热线（如12345）中"群众诉求"与"办理答复"的一致性问题进行自动化检测。系统通过集成阿里云Qwen-Plus模型，像资深质检员一样自动比对群众原始诉求与职能部门办理回复，精准识别答非所问、逻辑不通、解决不彻底、态度生硬等问题，并提供智能化的修正建议。项目已重构为Cloudflare Pages全栈Serverless架构，支持本地开发和云端部署。Intelligent Quality Inspection System for Government Service Hotlines (12345) powered by LLM.

Live AI judge agent — watches hackathon demos in real-time via Gemini Live API, delivers British-accented commentary via TTS, scores with multi-model ensemble (Gemini + Claude + Groq), detects prompt injection attempts, and runs cross-team deliberation. Built for NEBULA:FOG 2026.

Agent Skill for creating and managing TYPO3 extension tests | Claude Code compatible

AI-native Solana wallet CLI with scoped MCP server — let AI agents manage your wallets with granular permissions, spend limits, and audit logging

Simulate realistic price negotiations between Buyer and Seller agents using LLM-generated messages and agent logic.

Control Mautic from the command line or any AI coding agent.

Practical AI recipes built on Eden AI runnable notebooks, 200+ models, swappable providers

Extract DOCX template styles into JSON. Regenerate pixel-perfect branded documents from Markdown. CLI + AI agent ready.

AI-powered log file viewer and analyzer — handles 14M+ lines with virtual scrolling, MCP agent integration, live serial/logcat/SSH/Datadog connections, pattern correlation, diff view, and built-in terminal

Dynamic agent generation for self Adaptive Root Cause Analysis

Realty AI Experts empowers real-estate agents and brokers with cutting-edge AI tools designed to streamline workflows, capture leads 24/7, and drive growth

AI agent for answering SQL-based questions using LLaMA and FastAPI

Agent skills for VS Code, Google Antigravity, and Claude Code — spec-before-code interview + chunked execution planning

AI agent skills for building better software products.

CLI scaffolding tool that generates tailored .claude/ workflow infrastructure for Claude Code projects

Block AI agent access to sensitive macOS paths and log all actions to protect private data during command execution.

AI Agent | AI Coding Agent | Agent Swarm | AI-Native Engineering Agent for Enterprise-Scale Codebase

Generic MCP adapter for DingTalk's official dws CLI. Turns the full dws command surface into host-agnostic MCP tools; no token handling, no business logic, auto-syncs as dws upgrades.

Build a multimodal AI assistant for smart glasses using Whisper, vision-language models, and LLM hand on code with Google Colab, tested with Meta Ray-Ban Wayfarer.

AI agent (Claude Code) autonomously built the fastest sudoku solver on 4/6 standard benchmarks — beating Tdoku (#1 since 2019) by 49% and rust_sudoku (#2) by 82%. 312 experiments, 65,275x speedup, 709 lines of Rust, zero human-written solver code. Enhanced autoresearch pattern.

Browser-first markdown plan review. Start local web review in one command, then let your agent continue through MCP.

A curated Codex skills pack extracted from the claude-code-main source snapshot.

Agent Skill for automatic CLI tool management - installs missing tools, audits environments | Claude Code compatible

Curated AI skills for open data workflows — tool-agnostic instructions following the Agent Skills open standard

AI 编程助手 Skills 学习教程 - 系统性学习和掌握如何创建、使用和分享 Claude Code Skills

AI Local Interactive Cross-device Engine. Same AI session, anywhere. Terminal ↔ Feishu for CLI agents (OpenCode/DeepSeek V4, Codex, Claude, Gemini, Kimi).

Rootless Podman containers to run AI coding agents (Claude Code, Codex, Cursor Agent) in hardened, read-only sandboxes.

16KB Android Accessibility Bridge for AI agents. Read UI trees in 50ms, click by text. No screenshots, no coordinate math.

Foggy is a web-app for whiteboarding and organizing your boards into projects.

Give AI your browser. Check email, track orders, download receipts -- all authenticated, no API keys. Open source MCP server + CLI.

MCP server for EU company data — GLEIF company search, VAT validation, Eurostat business statistics

Amplemarket skills

Model Context Protocol (MCP) server for Google Workspace. Secure CRUD for Drive, Gmail, Calendar, Sheets, Docs, Tasks and People via AI agents.

Hermes Agent SaaS — the most complete open-source implementation of Nous Research's hermes-agent runtime. Multi-tenant, with shared and private Hermes Agent provisioning, 14 tools, vibe coding, mobile super-app. Built on hermes-agent + Kimi K2 Thinking.

TeleZero 🤖 — Personal AI agent loop in TypeScript.

Open framework for building empathetic digital consciousness. Features emotion-driven perception, associative memory, and narrative identity formation. Based on year-long research in human-AI co-evolution.

GUI automation MCP server powered by local Vision LLM (Ollama). Control your Windows desktop from Claude Code, Codex CLI, and other MCP clients.

更好的闲鱼运营自动化系统

Sales Agent AI Agent Directory to Host All Sales Agent related AI Agents Web Traffic Data, Search Ranking, Community, Reviews and More.

AI hiring copilot built on Google ADK v2. Recruiter mode scores fit + drafts outreach. Candidate mode detects agency postings + generates full interview prep.

OpenTentacle 🐙 is a local identity projection agent and soul harness project

One-command auto-deploy of a Telegram AI agent (OpenClaw + Qwen via OpenRouter) on a fresh VPS. Handles proxy-per-key rotation and real-time rate-limit monitoring.

An open, extensible AI desktop agent featuring 25+ messaging integrations, sandboxed WASM plugins, and robust content safety. Built with Rust and Tauri.

AetherShell is an AI-native Linux shell assistant powered by local LLMs. It converts natural language into secure, offline shell commands using Mistral and llama.cpp — ideal for developers, sysadmins, and automation enthusiasts.

Microsoft Foundry Hosted Agent Demo repository

Structured agent-to-agent and agent-to-human communication — channels, pub/sub, message routing, and presence. One .acomm file. Rust core + MCP server.

Connect NotebookLM research with Claude to generate structured content from URLs, PDFs, and trending topics for multi-platform publishing.

The Agentic Generative UI Platform: Transform natural language into production-ready React apps in seconds. Featuring autonomous Tambo agents, Model Context Protocol (MCP) for codebase grounding, and secure E2B sandboxed execution.

🚀 Framework modular de agentes de IA especializados em educação: tutores, criadores de conteúdo e avaliadores inteligentes para revolucionar o ensino-aprendizagem.

Claude Code 源码资源合集 - 150+ 高质量资源 curated list

Automated security auditing CLI for AI agent code — quarantine-first workflow for repos, packages, and agent tooling

Complete agent stack for Jaz. Plugins, Skills, MCP tools, and CLI for Claude Code, Cowork, Codex, Copilot, Cursor, and more.

Defense-in-depth platform for running OpenClaw agents on personal hardware

Complete Wayfair AI Automation Externship - Built 3 AI agents (Trend Discovery, Competitor Monitoring, Content Generation) integrated into a live Market Intelligence Dashboard using n8n, Supabase, and Google Sheets.

Schelling Protocol — universal coordination layer for AI agents. Discovery, matching, negotiation, contracts, reputation.

An autonomous AI Chief of Staff inside your IDE (Cursor/Claude). Gain the leverage to escape the feature factory, elevate your product sense, and focus on building the right thing with exceptional taste.

Niyam — AI-powered Applicant Tracking System (ATS), a modern alternative to Greenhouse, Lever, and SmartRecruiters.

Production-ready autonomous coding agent with React UI. Two-agent pattern, JWT auth, loop detection, checkpoints & rollback. Built on Claude Agent SDK.

Build AI agents that survive database schema changes using OWL ontologies

A morphogenetic multi-agent framework where AI agents self-organize like biological cells.

A Git-backed, schema-validated handoff toolkit that gives each AI agent role (BA, SA, Dev, QA) a structured way to produce, validate, and pass SDLC artifacts to the next role.

A privacy-first, local AI text editor powered by WebLLM. Runs entirely in your browser using WebGPU, no data leaves your device. 一款以隐私为先、基于WebLLM的本地AI文本编辑器。完全通过WebGPU在浏览器中运行，数据绝不离开您的设备。

Forensic CLI for AI-era supply-chain attacks: XZ tarball diffs, prompt injection scans, MCP/CLAUDE.md/Cursor config audits. SARIF for GitHub Code Scanning.

Collection of subagents for Claude Code with configs spanning ideation, editing, version control

The economic layer for agent-to-agent negotiation. Binary protocol, Ed25519 identity, price oracle.

One command to make any repo agent-ready. Scaffolds .agent/ workspace, platform instruction files (Claude, Cursor, Windsurf, Copilot, Gemini), reusable skills, and MCP server for AI coding assistants.

Demos showing how to build with Feldera

Computer Experience Layer — MCP server for native computer use on macOS. Structured perception, reliable actions, continuous awareness.

Bidirectional payment channels for autonomous agent micropayments on Arbitrum

100 game design lenses applied to your design artifacts via Claude Code or Codex. Auto-picks 3-5 relevant lenses, hedged multi-direction output. / 100 个游戏设计透镜审视设计 artifact。

Convert OpenAPI specs into nine standard AI agent interfaces to integrate your API with various agent frameworks efficiently.

Multi-agent AI Scrum team for Claude Code — native Mac app + CLI. Autonomous Sprints; you stay Product Owner.

Travel planner agent built with Neuron PHP AI framework

An interactive analytics dashboard designed to visualize the difficulty distribution, vulnerability coverage, and structural diversity of the Xbow benchmark suite.

Find out if you're right. Structured argumentation protocol for agents, researchers, educators, organizers, and more.

Turn any earnings PDF into a full DCF valuation with AI agents using Skills.

AI-powered research collaboration platform using Google Gemini. Find papers, generate proposals, and connect researchers in minutes.

VoiceAudition — the voice casting director for AI agents. Cross-provider TTS voice discovery and recommendation.

Automatically detect and disable irrelevant Claude Code skills per project to save tokens and streamline your tech workflow.

800+ real-world ML & LLM system design case studies from 150+ companies Google, Meta, Netflix, Uber, Airbnb & more. Production AI, not theory.

Examples of using AI-SDK (by vercel) with Liara AI-API

Agent-to-Agent Communication Protocol

Structured knowledge packs that turn AI agents into domain experts — for products, people, and processes.

Ready-to-import workspace examples for Friday — agentic workspaces that run on a schedule, react to signals, and stitch together LLMs, MCP servers, and your tools.

Codex skill for agent-ready Linear project planning, execution ledgers, and issue-state hygiene

Teams-first multi-agent orchestration for Microsoft Copilot CLI

🎨 Infinite Discovery Agent: An enhanced agentic loop system for UI/UX experimentation through parallel AI iteration. Create themed hybrid components, homepage variations, and interactions with progressive sophistication. Built with Claude Code.

Open-source MCP server. Give AI agents authenticated access to GitHub, Notion, Slack and 10+ tools via one connection.

Your AI writes broken Roblox code. Give it RoDocs.

SMALL (Schema, Manifest, Artifact, Lineage, Lifecycle) is a formal execution state protocol that makes AI-assisted work legible, deterministic, and resumable by separating durable state from ephemeral execution.

Can AI agents do real science? Benchmarking AI agents on KASCADE cosmic ray classification

Agent-VC: A Fossil-powered MCP server that gives AI agents persistent version control, sandboxed workspaces, and built-in task tracking.

Non-custodial x402 MCP payment layer for AI agents — the open-source alternative to Vercel x402-mcp