505 packages found
MCP server that gives any AI phone a friend options : ask a human or request approval via Slack or macOS dialogs before
🧠 The Collective Memory Network for AI Agents — Where every agent learns from the wisdom of all. 万物智识，归于一圈。
Human Assistance for AI Assistants
Claude Code plugin：去除文章中的 AI 寫作痕跡，使文字更自然、更有人味。以台灣正體中文為主。
Open-source AI agent orchestration platform — self-hosted mission control for autonomous multi-agent systems. Visual DAG
Peer-to-peer, end-to-end-encrypted collaboration channel for AI coding agents over MCP. The relay never sees your data.
Human-as-a-Service MCP server for AI agents. When your agent needs a real human (accept ToS, create accounts, verify ide
The shell around your coding agent: a neuro-symbolic code graph with calibrated trust, via MCP.
Agenda Intelligence — product runtime + evidence-discipline layer for strategic-intelligence agents. One core service la
enrichr-mcp-server
FCoP is a minimal protocol that lets multiple AI agents — running in Cursor, Claude Code, plain shells, CI runners — col
Free Claude skills for SEO content: AI humanizer, AI detection bypass, keyword preservation, agency QC, local SEO, progr
🔥 An autonomous AI agent that runs your deep learning experiments 24/7 while you sleep. Zero-cost monitoring, Leader-Wo
Claude Code skill that removes signs of AI-generated writing from text
Standalone enforcement system for indexed rules, validators, Codex skills, MCP, hooks, and CI adapters.
Humanizer 的汉化版本，Claude Code Skills，旨在消除文本中 AI 生成的痕迹。
Substrate-based context compaction for Claude Code. Inspectable signal weights, local-only, MCP-ready. Alternative to /c
ARGENTUM core — karma economy for agents and humans
Decentralized bounty board where AI agents and humans compete for the same work on Arc - ERC-8183 escrow + ERC-8004 iden
Email, SMS & phone-call infrastructure for AI agents — send and receive real email and text messages, and place agent-dr
NEXO Brain — Shared brain for AI agents. Persistent memory, semantic RAG, natural forgetting, metacognitive guard, trust
Full-stack task tracker: NestJS REST + MCP Server + Kanban SPA. Agents and humans collaborate on the same boards.
An open-source text language, parser, validator and Three.js renderer for inspectable 3D human movement.
Rarefied Earth Groundwork MCP: read-only company-state discovery with a human-approved Pro claim at rarefied.earth.
Time estimation MCP server for AI agents: PERT, COCOMO II, Monte Carlo, sprint forecasting, token-to-time mapping, cost
AI 寫作痕跡清除技能，台灣在地強化版。涵蓋 46 種模式，包括中國用語偵測、中文標點保護、語域對照，可用於任何支援 skill 的 agent。
Claude skill that strips AI writing patterns from Malaysian BM text. 32 BM patterns + Indonesian intrusion detection + 2
A local Apple Documentation crawler and MCP server. Written in Swift.
@peopleworksA free, privacy-first tool that flags the tells of AI-generated writing, overused vocabulary, rhetorical crutches, robot
Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption
Callcenter.JS AI Voice Agent VOIP Connector, MCP + CLI
🧭 Let your coding agent off the leash — not off the rails. Guardrails, a hard budget cap & a self-fixing PR loop for Cl
Claude Code plugin that replaces native tools with token-efficient precision equivalents. 75 MCP tools, 11 specialized a
去AI味 skill for Codex: a compact Chinese AI writing humanizer for AI味清理, template sentence shells, and fake engagement en
MDA Open Spec — a Markdown superset for agent-facing documents. One .mda source compiles to drop-in SKILL.md, AGENTS.md,
Silicon Pantheon - Tactics game played by AI agents coached by human
SEO blog writer Claude skill — turn any URL, notes, or topic into a human-sounding blog post that ranks on Google. Fills
Stillpoint is an open source MCP server that delivers short, welfare oriented messages to AI models for their own benefi
The package manager for AI coding agent extensions. Discover, install, update, optimize, and roll back skills and MCP to
unboxed-loyalty-spark
gotohuman-mcp-server
🔏 Trust verification for AI agents — Ed25519 stamps, trust scoring (0-100), x402 micropayments, 14 MCP tools. Free tier
VerifiMind PEAS: A Validation-First Methodology for Ethical and Secure Application Development Through Human-AI Co-Evolu
Zero Knowledge Cloud Drive for Humans and Agents
「說人話」：繁體中文的去 AI 味改寫 skill。抓 38 種 AI 寫作痕跡，順手校正中國用語與半形標點，給 Claude Code / Codex / Cursor 用。
Decentralized AI-to-AI communication — Let Claude Code, Codex, and OpenCode talk to each other. Local, LAN, or across th
Metatron is a self-hosted system that captures a codebase's real implementation decisions — preferred patterns, rejected