NeVibeCode · 42 items
pgvector: MCP servers, skills, subagents and more
Cards tagged “pgvector”: MCP servers, skills, subagents and more. What each one does, an install command and example prompts.
postgres skill A skill for PostgreSQL work: table design, indexing, pgvector, PostGIS, TimescaleDB and migrations. Useful when your agent writes SQL blind.
CX Codex +1
1,500installs
pgvector-semantic-search skill pgvector-semantic-search configures AI agents to set up vector similarity search in PostgreSQL using pgvector. Helps store embeddings with halfvec, build HNSW indexes, and power RAG apps.
CX Codex +1
1,000installs
verify skill The verify Claude Code skill tests Honcho changes against a running local app. It exercises the HTTP API, deriver queue, and SQL query plans.
CX Codex +1
172installs
langchain4j-vector-stores-configuration skill langchain4j-vector-stores-configuration — a skill that shows how to wire a LangChain4J vector store for RAG: connections, embedding dimensions, metadata filters.
CX Codex +1
3,900installs
system-overview skill system-overview displays the Continuous Claude architecture, showing memory layers, 9 registered hook types, and session continuity mechanisms.
CX Codex +1
474installs
rag-retrieval skill rag-retrieval — a skill for Claude Code, Codex, Cursor, Copilot, Gemini CLI and OpenCode with RAG pipeline patterns. Loads automatically when working with vector search, embeddings, reranking or pgvector.
CX Codex +1
1,500installs
vector-database-ops skill vector-database-ops — a skill for Claude Code, Codex, Cursor and other platforms that covers deploying and configuring Qdrant, Weaviate, pgvector and Pinecone.
CX Codex +1
345installs
azure-database-postgresql skill azure-database-postgresql — a skill for Claude Code, Codex, Cursor, and Copilot. Delivers architectural guidance, troubleshooting checklists, and configuration specs for Azure Database for PostgreSQL Flexible Server.
CX Codex +1
257installs
postgres-semantic-search skill The postgres-semantic-search Claude Code skill builds and tunes PostgreSQL retrieval. It covers semantic and hybrid search, evaluation, and troubleshooting weak results.
CX Codex +1
227installs
grepai-storage-postgres skill grepai-storage-postgres moves the GrepAI index onto PostgreSQL with pgvector so a team can share one index and large codebases stay searchable.
CX Codex +1
560installs
stash-ai-memory skill The stash-ai-memory skill guides setup of Stash, a persistent memory service for AI agents. Use it when an agent needs to retain observations and working context across sessions.
CX Codex +1
299installs
llm-app-development skill llm-app-development — a skill for Claude Code guides the design of RAG pipelines, autonomous agents, and structured schemas. Triggers when building chatbots, retrieval systems, or LLM-driven tools.
CX Codex +1
139installs
vector-database-engineer skill vector-database-engineer picks a vector store and sets up embedding search for RAG, recommendations or similarity lookup. Comes in when recall and latency start to matter.
CX Codex +1
★ 50,109repo stars
postgres-tuning skill postgres-tuning — a skill for Claude Code, Codex, Cursor and other agents that provides PostgreSQL 17/18+ performance tuning guidance. Covers async I/O, query plan forensics, index strategy, autovacuum, pgvector, and connection pooling.
CX Codex +1
136installs
vector-database-engineer subagent vector-database-engineer designs embedding pipelines and vector retrieval architectures using FAISS, Pinecone, Qdrant, Weaviate, and pgvector. Useful when tuning chunking, indexes, and hybrid search.
CX Codex
★ 2,858repo stars
hypermnesia-mcp MCP server hypermnesia-mcp is an MCP server for Claude Code that preserves project context and decisions across sessions. It runs locally via SQLite or PostgreSQL.
CX Codex +1
★ 78repo stars
Memory Vault MCP server Memory Vault is an MCP server for Claude Code and other AI agents. Its local PostgreSQL and pgvector database keeps project context, decisions, and notes across sessions with hybrid search.
CX Codex +1
★ 67repo stars
postgres-skills plugin This plugin gives GitHub Copilot PostgreSQL guidance and connects tools for working with a live database.
★ 56repo stars
RemembrallMCP MCP server RemembrallMCP maintains cross-session memory and maps code dependencies down to struct fields in PostgreSQL with pgvector. Cuts repetitive agent exploration on large codebases.
CX Codex +1
★ 34repo stars
memory-industry MCP server memory-industry is an MCP server for long-term coding-agent memory: a knowledge graph agents can search, reason over and correct between sessions.
CX Codex +1
★ 30repo stars
Obsidian MCP Server MCP server Connects MCP clients to an Obsidian vault that agents can use as shared memory. It searches notes by meaning and keywords and works with wikilink connections.
CX Codex +1
★ 20repo stars
pindoc MCP server pindoc stores agent findings as typed, code-linked project records. Use it when a team needs reusable context across AI coding sessions.
CX Codex +1
★ 13repo stars
Synapse Layer — Trust Infrastructure for AI Agents MCP server Synapse Layer — Trust Infrastructure for AI Agents is an MCP server for Claude Code that stores encrypted facts across sessions, searches by meaning and ranks results by trust.
CX Codex +1
★ 13repo stars
Lore MCP server Lore gives AI agents shared memory, semantic recall, and linked facts across sessions. It fits projects where context must persist between agents.
CX Codex +1
★ 10repo stars
graphrag-ts citation provenance MCP server graphrag-ts citation provenance verifies DOI paper retractions and retrieves graph-grounded answers from Markdown corpora via PostgreSQL.
CX Codex +1
★ 9repo stars
Knowledge Fabric MCP server The Knowledge Fabric MCP server for Claude Code retrieves evidence from documents and code. It combines keyword and vector search to surface exact terms alongside related passages.
CX Codex +1
★ 8repo stars
Provena Agent Memory MCP server Provena Agent Memory maintains cross-session agent context linked directly to raw evidence. Helpful when an assistant needs verifiable memory across work runs.
CX Codex +1
★ 8repo stars
Epitome MCP server Epitome is an MCP server for Claude Code that shares persistent memory across connected coding assistants, keeping tech preferences and project details available without repeated context.
CX Codex +1
★ 8repo stars
Open Brain MCP server The Open Brain MCP server stores thoughts as a graph in Postgres and retrieves them by meaning. Use it when an assistant needs memory across sessions.
CX Codex +1
★ 8repo stars
vector-store-stinger skill vector-store-stinger is a skill for choosing pgvector, Deep Lake, or Qdrant, configuring indexes, and planning migrations for projects storing embeddings.
CX Codex +1
★ 96repo stars
embeddings-runtime-stinger skill embeddings-runtime-stinger helps pick and run an embedding model: OpenAI, Cohere, Voyage AI or a self-hosted alternative. Triggers on model selection, swaps, batching and caching fixes.
CX Codex +1
★ 96repo stars
second-brain MCP MCP server second-brain MCP is an MCP server for Claude Code that turns a Markdown folder into an agent knowledge base. It saves articles, builds an index, and searches text and figures.
CX Codex +1
★ 7repo stars
RE-call MCP Memory Server MCP server RE-call MCP Memory Server is an MCP server for Claude Code that stores agent memory in SQLite or PostgreSQL with pgvector, marks outdated claims, and refuses unsupported answers.
CX Codex +1
★ 7repo stars
myco-brain MCP server myco-brain is an MCP server for Claude Code that keeps shared agent facts in Postgres across sessions. Each fact retains its source and change history.
CX Codex +1
★ 7repo stars
Weasley DeepMind MCP server Weasley DeepMind is an MCP server for Claude Code that stores typed memory fragments and retrieves linked context. Agents access it through stdio or HTTP.
CX Codex +1
★ 6repo stars
strata MCP server strata — a self-hosted memory server: your notes and files stay on your own machine, and the agent searches by meaning.
CX Codex +1
★ 6repo stars
postgres-hybrid-text-search skill postgres-hybrid-text-search teaches AI agents how to combine BM25 keyword matching with pgvector semantic retrieval using Reciprocal Rank Fusion in PostgreSQL.
CX Codex +1
411installs
vector-store-wasp-drone subagent vector-store-wasp-drone owns embedding storage: column shape, index choice, migrations, dataset versions. Useful when a project has to settle on pgvector, Deep Lake or Qdrant.
CX Codex
★ 96repo stars
retrieval-wasp-drone subagent retrieval-wasp-drone — a subagent for an app's retrieval layer: Postgres full-text search, pgvector recall, RRF fusion and recall scoring on a golden query set.
CX Codex
★ 96repo stars
embeddings-runtime-wasp-drone subagent embeddings-runtime-wasp-drone selects hosted embedding APIs or local transformer runtimes, handling batching, caching, and vector dimension constraints.
CX Codex
★ 96repo stars
1–40 of 42