Results for “daemon”

Smart Tree: not just a tree, a philosophy. A context-aware, AI-crafted replacement for 20+ tools with MEM8 quantum compr

Model Context Protocol servers for the official Robinhood Crypto Trading API — the credentialed brokerage API at trading

Local MCP daemon that compresses your codebase before sending it to Claude 41-89% token reduction

This MCP server provides tools for listing and retrieving content from different knowledge bases.

The missing integration layer for AI agents. Let them call any OpenAPI / MCP / GraphQL / custom js functions in secure e

Local semantic search over your Claude Code session + shell history, exposed to Claude Code as an MCP search_history too

Local MCP broker that exposes one compact MCP entry for MCP clients while routing to many configured upstream servers.

Extremely fast hybrid code search for agents.

苹果 MCP 工具 ✅

MCP Docs Vector - Documentation vectorization and search via MCP

The most comprehensive code intelligence MCP server for AI coding agents. 40+ tools, 30+ languages, 9 agent integrations

mnemos

@swapnanil

Semantic codebase search + persistent working memory for AI code editors. Local, zero-config, MCP. No API key.

Local cognitive infrastructure for AI coding agents — semantic memory, repository intelligence, and MCP tools to reduce

MCP server and local sync package for Cosmos. Connects agents, iMessage, browser history, calendar, Claude Desktop, and

Email MCP server with full IMAP + SMTP support — read, search, send, manage, and organize email from any AI assistant vi

Load MCP servers on-demand instead of keeping them in context permanently. Zero token overhead when not in use. Start se

The leading, most token-efficient MCP server for documentation exploration and retrieval via structured section indexing

Enhanced MCP server for browser automation with improved element selection, tab management, and token optimization

daimonos

Self-hosted multi-channel notification gateway (Docker + Redis queue): token-auth API fans one message out to ntfy, Tele

Embedded, local-first agent memory. No server, no daemon, no mandatory cloud key.

NEXO Brain — Shared brain for AI agents. Persistent memory, semantic RAG, natural forgetting, metacognitive guard, trust

An open registry for discovering, verifying, and trusting AI agents.

Email, SMS & phone-call infrastructure for AI agents — send and receive real email and text messages, and place agent-dr

MCP server that lets Claude Code pause mid-task and ask a human a question via Slack — then resume once you reply.

The shell around your coding agent: a neuro-symbolic code graph with calibrated trust, via MCP.

Substrate-based context compaction for Claude Code. Inspectable signal weights, local-only, MCP-ready. Alternative to /c

MCP server giving LLM agents a seven-verb API over papers, documents, code, state, patents, and cached web/Wolfram/YouTu

Local, evidence-linked project memory and cited context compiler for coding agents - 98.71% less estimated repeated cont

stackchan-remote-mcp

Persistent Project Context for xAI Grok — IANA-registered .faf format · MCP server on a URL

A local-first AI secretary that gathers your scattered work context into private memory you and your AI agents can query

FCoP is a minimal protocol that lets multiple AI agents — running in Cursor, Claude Code, plain shells, CI runners — col

Single-file memory layer for AI agents, sub mili-second RAG on Apple Silicon. Metal Optimized On-Device. No Server. No A

MCP server that lets any llm (i.e. Claude Desktop) delegate tasks to a local Hermes Agent — cron jobs, web search, emai

Control Wemo smart home devices through AI assistants using natural language.

Alcove is an MCP server that gives AI coding agents on-demand access to your private project docs — BM25 + vector hybrid

Persistent memory for AI coding agents

📜 An MCP server for conversation history search and retrieval in Claude Code

Todo and task management

The Mind Palace for AI Agents - HIPAA-hardened Cognitive Architecture with on-device LLM (prism-coder:7b), Hebbian learn

MCP server for Performance Co-Pilot metrics

Minimal, auth-secured MCP server for real browser access. ~500 lines. Token auth, Chrome Extension MV3, accessibility tr

Self-improving context & memory for Claude Code and OpenAI Codex. One canonical knowledge store injected only when relev