Semantic search across Sui documentation and knowledge sources, powered by kapa.ai
Two-tier memory: hot cache (0ms) + semantic search. Self-organizing.
Two-layer memory MCP server for AI agents with 37 tools, RAG, graphs, wiki, auth
Enhanced MCP server-memory with ZeroDB cloud persistence and semantic vector search. Drop-in replacement for @modelcontextprotocol/server-memory that stores your knowledge graph in the cloud instead o
Universal code development MCP server — search, analyze, navigate, review any codebase. 29 tools, semantic search, AST parsing, security scanning, dead code detection, complexity heatmaps, DB schema p
Your second brain, in every AI you use — a local MCP server for your Obsidian vault (or any markdown folder). Allowlist-gated, capped, disclosed, audited.
Expose your Quickchat AI agent as an MCP server, giving AI apps real-time access to its knowledge base and conversational capabilities.
Hosted MCP knowledge base: businesses forward emails and docs; buyers query them over MCP.
Deterministic, namespace-isolated document retrieval with a CLI and MCP server.
Local screen and activity knowledge graph, served as context to computer-use agents.
Zero-overhead local persistent memory & MCP server for AI assistants (Cursor, Claude, VS Code). Single SQLite file, hybrid search & active dashboard.
An MCP server for your documents: npx @devilsdev/rag-mcp-server ./docs indexes a folder offline and serves search_documents and check_answer over stdio.
AI employee operating system — persistent memory, task management, and multi-agent coordination for Claude Code.
Multi-tenant hybrid RAG & evidence verification MCP server enforcing PostgreSQL RLS.
Persistent memory MCP server for Claude Code, Cursor, and GitHub Copilot.
Persistent 5-level hierarchical memory for AI agents. SQLite-backed, lazy-loaded.
A sourced learning map your AI places you on: finds gaps you can't name, teaches step by step.
Embed a customizable AI chatbot on any website. Knowledge-base RAG, tier-aware rate limits, white-la
Persistent, searchable context storage across Claude Code sessions using SQLite FTS5, with AI session summaries, checkpoint recovery and a web dashboard.
Persistent memory for AI agents, one account across four sites, plus a partner program.
Local workspace memory: indexes Markdown, CSV and session logs into a vector store with hybrid search, cross-session memory and knowledge graph visualization.
MCP server for semantic search and write actions across Apple Mail, Messages, Calendar, and Contacts. Speaks stdio (local) or bearer-token-authenticated Streamable HTTP (LAN / Tailscale).
One user-owned memory shared across AI assistants: recall, spaces, and confirmed references.
MCP server that gives coding agents persistent project understanding via a knowledge graph
Sub-5ms topological 4D associative memory coprocessor for LLMs and multi-agent swarms.
MCP Memory Server with Neo4j backend
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 i
Autonomous multi-source deep research with DuckDuckGo search (zero API keys), parallel scrapers, markdown cleaning, synthesis with citations, fact-checking, and persistent memory.
Project-scoped memory layer for Claude Code, Codex, Hermes, MCP, and dashboards
Shared, persistent memory for any AI agent. Agents recall what your workspace established — instructions, decisions, facts, preferences, active working threads, and grounded PDF/DOCX/CSV/web documents
Persistent memory for Claude Code and Pi with native Skills integration, automatic capture, failure learning, and project scoping
Self-learning vector database for Node.js: native HNSW vector search, ONNX embeddings, GNN, attention, SONA routing and an MCP server for agents.
DeepSeek Harness bundle that launches the compound-memory stdio MCP server, mounts the bundled compound-memory skill, and injects a short once-per-session usage reminder.
Certified SEC EDGAR fact memory for AI agents with zero hallucination and filing provenance.
SQLite-backed MCP server for persistent memory, full-text retrieval, and graph traversal.
InfoLang semantic memory MCP — investigate, memorize, and recall compressed agent context.
पूरी डायरेक्टरी
RAG, ग्राफ़ और एजेंट की लॉन्ग-टर्म मेमोरी। 2,654 सर्वर, सबसे ज़्यादा इस्तेमाल वाले पहले। हर एक पब्लिशर का पेज खोलता है।