316 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。
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。
Human Assistance for AI Assistants
Claude Code skill that removes signs of AI-generated writing from text
Humanizer 的汉化版本，Claude Code Skills，旨在消除文本中 AI 生成的痕迹。
Open-source AI agent orchestration platform — self-hosted mission control for autonomous multi-agent systems. Visual DAG
Human-as-a-Service MCP server for AI agents. When your agent needs a real human (accept ToS, create accounts, verify ide
Agenda Intelligence — product runtime + evidence-discipline layer for strategic-intelligence agents. One core service la
enrichr-mcp-server
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
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
NEXO Brain — Shared brain for AI agents. Persistent memory, semantic RAG, natural forgetting, metacognitive guard, trust
Email, SMS & phone-call infrastructure for AI agents — send and receive real email and text messages, and place agent-dr
Time estimation MCP server for AI agents: PERT, COCOMO II, Monte Carlo, sprint forecasting, token-to-time mapping, cost
Claude skill that strips AI writing patterns from Malaysian BM text. 32 BM patterns + Indonesian intrusion detection + 2
Claude Code plugin that replaces native tools with token-efficient precision equivalents. 75 MCP tools, 11 specialized a
Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption
MDA Open Spec — a Markdown superset for agent-facing documents. One .mda source compiles to drop-in SKILL.md, AGENTS.md,
去AI味 skill for Codex: a compact Chinese AI writing humanizer for AI味清理, template sentence shells, and fake engagement en
Callcenter.JS AI Voice Agent VOIP Connector, MCP + CLI
A local Apple Documentation crawler and MCP server. Written in Swift.
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
🔏 Trust verification for AI agents — Ed25519 stamps, trust scoring (0-100), x402 micropayments, 14 MCP tools. Free tier
Stillpoint is an open source MCP server that delivers short, welfare oriented messages to AI models for their own benefi
Zero Knowledge Cloud Drive for Humans and Agents
Advanced cognitive reasoning MCP server — DAG thought graph, 10 strategies, metacognition, self-critique, knowledge inte
MCP server that provides LLM with tools for interacting with Starknet
Metatron is a self-hosted system that captures a codebase's real implementation decisions — preferred patterns, rejected
mcp-occams-razor
Decentralized AI-to-AI communication — Let Claude Code, Codex, and OpenCode talk to each other. Local, LAN, or across th
TensorZero is an open-source LLMOps platform that unifies an LLM gateway, observability, evaluation, optimization, and e
A specialized Claude Code workspace for creating long-form, SEO-optimized blog content for any business. This system hel
MCP server + TypeScript client + CLI for Tradallo's verified record protocol, query cryptographically-verified human + a
Precomputed reasoning cache for AI infrastructure decisions — 220K+ pages tracking the open-source AI ecosystem
IGA for AI agents. IETF AIMS-compliant identity, credential governance & MCP proxy. SPIFFE · RFC 7591 · AuthZEN · CIBA.
A content-addressable protocol for universal food data
Professional skills for Claude AI — 167 skills across 17 professions. Save 8-10 hours per week. PM stands for Profession
On-chain civil registry for AI agents — birth certificates, identity, and lineage tracking on Ethereum
Your agents forget. Neotoma makes them remember.
Claude Code skill for recursive research up to PhD level across any domain. Source tiering, WDM + Munger inversion for a
[NeurIPS 2024] ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution
Turn any web page into traceable, citable evidence for AI agents.