by sslugic
Local, private memory for coding agents: facts, skills and tasks that persist across sessions.
npm:@iamem/amem · local package2.6k/wkpublished 8 d ago
Embeddings and similarity search.
Local, private memory for coding agents: facts, skills and tasks that persist across sessions.
Semantic code search MCP server for AI coding agents (opencode, Claude, Cursor). Local embeddings, no API keys.
Local MCP server that gives coding agents (Claude Code, Codex) cheaper, sharper tools than their built-in search. Windows.
Local-first context engine for AI coding agents. Pre-indexes your codebase into a dependency graph and feeds any MCP agent only the code that matters, so it stops rediscovering your repo before every change. Fable-5-level results from Opus 5 on SWE-bench
Workspace-local reference CLI/MCP server for semantic IWSDK search using externally hosted corpus/model warmup artifacts
Convert a web page URL to clean Markdown for LLM context. Local, no external API calls.
Agent memory MCP server with 4-type cognitive memory, hybrid search, and TTL-based forgetting.
Open-source retrieval for agentic RAG: local document search, exact citations, OCR, CLI, MCP, and TypeScript.
Local-first AI memory with knowledge graphs and hybrid search. 17+ AI tools via MCP. Free.
Deterministic security layer your AI can't be. 644 rules, 39 tools, CLI + doctor + host audit.
Search a folder of documents and check answers against them. Offline: no API key or database.
Persistent, searchable memory for Cursor AI — You control what your AI remembers.
MCP server for code intelligence — 146 tools for symbol search, call graph, semantic search, route tracing, community detection, LSP bridge, secret detection, conversation search, and Hono framework intelligence
A Model Context Protocol (MCP) server for Obsidian vault management via SSE transport, with optional pgvector-backed semantic search
MCP Server for AIVault — search, sync, and manage your AI conversations from any agent. Connects to your AIVault instance via HTTP API.
Local-first project memory with legacy MCP and 2026 discovery compatibility.
Universal persistent memory layer and context manager for AI agents, Claude, Cursor, and LLMs via Model Context Protocol (MCP)
Open-source Ask AI for your docs, with an MCP server for agents: cited answers on your own model key, from one static index built with your site. No vendor, no vector database. Starlight, Docusaurus and VitePress plugins, Next.js, or one script tag.
Semantic codebase search engine with embedding-based ranking and MCP server
Sciverse MCP server — metadata search across papers, patents, authors and sources, paper semantic retrieval and document content reading.