Vector Search

MCP server for true local semantic search over Obsidian vaults using Smart Connections embeddings — multi-vault, block-level retrieval, no cloud calls

MCP server for Kaval: before an AI agent acts, verify the facts the action depends on — ALLOW, REVIEW, or BLOCK, with a signed receipt.

MCP server & CLI: codebase index + cache for Claude Code, Cursor, OpenAI Codex, Google Antigravity/Gemini. Model Context Protocol tools (codetree_read, codetree_search, …), hooks on Claude, rules on other IDEs. Token savings, SQLite index, symbol search,

Persistent learning memory for AI coding agents. Memory that compounds.

AINative ZeroDB Memory MCP Server - 18 tools for agent memory: 9 memory + 5 write-back (Slack, Gmail, Calendar, GitHub, Notion) + 4 plan artifacts (persistent plans/PRDs across sessions with diff history). Auto-context middleware. Production-ready for Cla

Sciverse MCP server — exposes academic paper retrieval (search_papers / semantic_search / read_content) to MCP-compatible coding agents (Claude Code, Cursor, Codex CLI, Windsurf, ...).

A code indexing system accessible via MCP (Model Context Protocol)

AiFP Cognitive Memory — persistent memory MCP server for AI assistants. Chinese-first retrieval with causal chains, Hebbian associations and graph diffusion. 记忆感知系统

Multi-model consensus: 2-6 frontier LLMs answer, an independent judge synthesises one answer.

MCP server for Scrivener - Read, write, analyze, and search manuscripts with semantic search, character/plot tracking, writing analysis, and content enhancement. Works with Claude, ChatGPT, and other AI assistants.

AI memory system for coding agents. Local-first MCP runtime with connectors (Google Drive, GitHub, Slack, Notion), knowledge graphs, decay scoring, and multi-tier deployment. Free locally, paid Cloud for sync and teams.

Zero-config Postgres MCP server with auto-provisioning. Drop-in replacement for @modelcontextprotocol/server-postgres — no DATABASE_URL needed. Auto-provisions a managed PostgreSQL instance with pgvector on first run.

Context integrity infrastructure for AI agents and retrieval systems. Score, explain, and wrap candidate context before it reaches the model.

Ask questions about your own notes and get answers that cite their sources — then get told when a source changed underneath a conclusion. Local-first CLI + MCP server, zero runtime dependencies.

Cognitive architecture for persistent AI agent memory. Knowledge graph with learning retrieval, ACT-R decay, and spreading activation. Markdown-native, local-first, zero cloud. MCP server + CLI.

Persistent intelligence infrastructure for agentic development

Code intelligence for AI coding assistants — AST-level semantic code search with keyword boost. Index your codebase, search by meaning, keep everything local.

DocBrain MCP server — query your documentation from Claude Code, Cursor, and any MCP-compatible editor

Local RAG MCP Server - Enhanced with hybrid search, memory management, and code file support (fork of shinpr/mcp-local-rag)

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 of local JSONL files.