127 tagged embeddings, measured the same way as everything else here.
Browse within: LLM 32local-first 18code-search 16knowledge-graph 16model-context-protocol 16agent-memory 15hybrid-search 15chromadb 14mcp-server 14knowledge-base 12bm25 9cli 8cursor 8ai-memory 7
MCP server Cursor
One of 2 in mcp.json
Gives the agent up-to-date documentation and code examples for libraries and frameworks, fetched on demand so answers are not stuck at the model's training cutoff. Runs locally from the @upstash/context7-mcp npm package.
MCP server Claude CodeCodexCursor +2
A semantic search engine for files and code. Runs locally from the vexor Python package. Needs 3 environment variables to run.
MCP server Claude CodeCodexCursor +2
MCP server "velesdb-memory" as configured in cyberlife-coder/VelesDB. Launched with https://github.com/cyberlife-coder/VelesDB/releases/download/velesdb-memory-v0.9.
MCP server Claude CodeCodexCursor +2
MCP server "pensyve" as configured in major7apps/pensyve. Launched with pensyve-mcp --stdio.
MCP server Claude CodeCodexCursor +2
Local semantic search over Obsidian vaults via Smart Connections embeddings. Multi-vault, private. Runs locally from the smart-connections-mcp npm package. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
A deterministic, high-precision code intelligence MCP server. Runs locally from the code-memory Python package. Needs 2 environment variables to run.
MCP server Claude CodeCodexCursor +2
MCP server "conversationalanalysisengine" as configured in MVPandey/CAE. Runs locally from the ConversationalAnalysisEngine Python package.
MCP server Claude CodeCodexCursor +2
MCP server "cortex" as configured in gambletan/cortex. Runs in Docker (ghcr.io/gambletan/cortex:v1.8.0).
MCP server Claude CodeCodexCursor +2
Generic markdown vault MCP with hybrid search. Runs locally from the markdown-vault-mcp Python package. Needs 89 environment variables to run.
MCP server Claude CodeCodexCursor +2
Semantic code graph for AI-assisted code understanding via tree-sitter and MCP. Runs locally from the rpg-encoder npm package.
MCP server Claude CodeCodexCursor +2
MCP server "fortemi" as configured in Fortemi/fortemi. Runs ./mcp-server/index.js with node. Needs 2 environment variables to run.
MCP server Claude CodeCodexCursor +2
MCP server "connapse" as configured in Destrayon/Connapse. Runs in Docker (ghcr.io/destrayon/connapse:v0.3.2).
MCP server Claude CodeCodexCursor +2
MCP server for Midas — local-first, source-traceable agent memory with no LLM at ingest. Runs locally from the midas-memory-mcp Python package. Needs 4 environment variables to run.
MCP server Claude CodeCodexCursor +2
Intelligent MCP tool routing — reduce context bloat by serving only relevant tools. Runs locally from the smartmcp-router Python package.
MCP server Claude CodeCodexCursor +2
MCP server that gives AI coding agents accurate NXOpen .NET API knowledge via hybrid retrieval. Runs locally from the nxopen-mcp Python package.
MCP server Claude CodeCodexCursor +2
One of 2 in .mcp.json
Locus — local-first hybrid code search MCP (transitional id @sylphx/coderag-mcp; brand @sylphx/locus). Runs locally from the @sylphx/coderag-mcp npm package. Needs 3 environment variables to run.
MCP server Claude CodeCodexCursor +2
Pull Deep Memory from across your Claude Code Sessions — when you need it. Runs locally from the claude-find npm package.
MCP server Claude CodeCodexCursor +2
Obsidian MCP server: semantic search, knowledge graph, and vault editing. No plugin required. Runs locally from the obsidian-brain npm package. Needs 15 environment variables to run.
MCP server Claude CodeCodexCursor +2
One of 2 in .mcp.json
MCP server "agent-relay", hosted remotely at localhost, as configured in TsukumoHQ/trovex.
MCP server Claude CodeCodexCursor +2
Local-first persistent memory for AI agents — SQLite + local embeddings, MCP-native, no cloud. Runs locally from the @hbarefoot/engram npm package.
MCP server Claude CodeCodexCursor +2
MCP server "palace-rs" as configured in AncientiCe/palace-rs. Launched with https://github.com/AncientiCe/palace-rs/releases/download/v0.9.1/palace-0.9.1.mc.
MCP server Claude CodeCodexCursor +2
MCP server enabling AI agents to efficiently search and understand PDF documents. Runs locally from the paper-intelligence Python package.
MCP server Claude CodeCodexCursor +2
MCP server "mnemotree" as configured in kurcontko/mnemotree. Runs locally from the mnemotree Python package.
MCP server Claude CodeCodexCursor +2
Trustworthy retrieval for an AI agent's own memory — verdict, confidence and provenance per hit, or an explicit abstention. Runs locally from the recall-rag Python package. Needs 3 environment variables to run.