Pgvector Python Packages

pgserver

Pip-installable, embedded-like postgres server for your python app

vecs

Postgres/pgvector Python Client

embedded-postgres

PostgreSQL server binaries as a pip-installable wheel (Linux x86_64/aarch64, macOS, Windows) with a small Python layer to init, start and stop it

aindy-runtime

Self-hosted runtime for AI agents and workflows. Durable execution, capability-gated tools, human approval gates, and a memory system that accumulates. Runs survive restarts and resume where they stopped. Mount your domain logic as a plugin package or drive it over the HTTP SDK

mengram-ai

Human-like memory for AI agents — semantic, episodic & procedural. Experience-driven procedures that learn from failures. Free API, Python & JS SDKs, LangChain, CrewAI & OpenClaw integrations.

garage-rag

A utility for reading in the corpus of your life...

geolens

Self-hosted geospatial data catalog with semantic search (pgvector), OGC/STAC APIs, and map builder. Built on FastAPI, PostGIS, React, and MapLibre.

geolens-mcp

Self-hosted geospatial data catalog with semantic search (pgvector), OGC/STAC APIs, and map builder. Built on FastAPI, PostGIS, React, and MapLibre.

deutsches-ki-toolkit

Deutschsprachige KI-Infrastruktur für Dokumente, Datenschutz, Suche und RAG: deutsche PII-Erkennung mit Prüfsummen, Komposita-Zerlegung, strukturtreues Chunking, hybrides Retrieval und RAG mit geprüften Quellenangaben. Live-Demo im Browser.

geolens-cli

Self-hosted geospatial data catalog with semantic search (pgvector), OGC/STAC APIs, and map builder. Built on FastAPI, PostGIS, React, and MapLibre.

brevia

Extensible API and framework to build your Retrieval Augmented Generation (RAG) and Information Extraction (IE) applications with LLMs

edgeproc-core

Decides which partition a vector belongs in when a vector index is split across tenants, users, or time windows: three routing strategies plus result merge-back, one runtime dependency (pydantic), no index of its own. 243 tests, 98% coverage.

gnosis-mcp

Zero-config MCP server for searchable documentation (SQLite default, PostgreSQL optional)

contex-python

An MCP-native context bus that pushes updates to agents that subscribe to data using natural language.

alice-memory

Open-source, local-first memory for AI agents. An MCP server that keeps facts, decisions and open loops in one SQLite file on your machine. MIT, public alpha.

bgts-context-engine

Deterministic code-graph context engine for AI coding agents - PostgreSQL + Apache AGE + pgvector, MCP & REST, no LLM in the loop.

sifts

Simple full text & vector search engine Python library

embedflow

Zero downtime embedding upgrades

hermes-memory-pgvector

Postgres + pgvector memory provider plugin for hermes-agent. Multi-agent storage layer with per-minion themes, async writer, no LLM in the memory hot path.

undertow-llm

Provider-agnostic LLM observability & reliability SDK — semantic caching, retries, rate limiting, and real-time dashboard via a single @track() decorator.

pseudolife-mcp

Persistent long-term memory for Agents — an MCP server with an associative memory bank, a canonical-fact cortex, sleep-like dream consolidation, and a web console. Not quite alive.

raglite

🥤 RAGLite is a Python toolkit for Retrieval-Augmented Generation (RAG) with DuckDB or PostgreSQL

serviette

Universal RAG tool

voyd

Ranking is not permission. Your vector index is still serving documents you deleted. Admission control for RAG retrieval: a read path that cannot return an expired, revoked, or forgotten fact.