Search Packages

vecs

Postgres/pgvector Python Client

pgserver

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

yourmemory

Agentic AI memory with Ebbinghaus forgetting curve decay. +16pp better recall than Mem0 on LoCoMo.

ogham-mcp

Shared memory MCP server — persistent, searchable, cross-client Claude, Opencode

vektori

Memory that remembers the story not just the facts. Three layer sentence graph for AI agents -> Facts, Episodes, raw Sentences. One DB. Zero config.

markcrawl

Fast Python web crawler for RAG and AI ingestion. Extracts clean Markdown from any site for LLMs and vector stores.

precis-mcp

MCP server giving LLM agents a seven-verb API over papers, documents, code, state, patents, and cached web/Wolfram/YouTube tool calls

brevia

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

genesys-memory

Open-source causal graph memory for AI agents. 89.9% on LoCoMo. MCP server with ACT-R scoring, spreading activation, and active forgetting.

palaia

Palaia — Local, crash-safe memory for AI agents. Semantic vector search (fastembed/OpenAI/Ollama). SQLite + sqlite-vec or PostgreSQL + pgvector. MCP server for Claude Desktop & Cursor. Multi-agent. Auto-capture.

gnosis-mcp

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

sifts

Simple full text & vector search engine Python library

snipara-mcp

MCP server for Snipara - Context optimization and Agent infrastructure for LLMs

cocosearch

Local-first hybrid semantic code search tool. Indexes codebases into PostgreSQL with pgvector embeddings via Ollama, combines vector similarity + keyword search with RRF fusion. Supports 30+ languages. Features CLI, MCP server, WEB dashboard and interactive REPL.

vector-inspector

A comprehensive desktop application for visualizing, querying, and managing vector database data

attestor

Auditable memory for agent teams. Self-hosted, deterministic retrieval, no LLM in the critical path. Python + MCP + Docker.

memwright

Production-grade memory infrastructure for multi-agent systems. Namespace isolation, RBAC, provenance, ranked retrieval.

pgserver-search

Embedded Postgres with pg_trgm + pgvector bundled — search-focused fork of pgserver

llama-index-tools-instanode

LlamaIndex tools for instanode.dev — provision Postgres + webhooks from LlamaIndex agents

crewai-instanode-tools

CrewAI tools for instanode.dev — provision Postgres + webhooks from CrewAI agents

langchain-instanode

LangChain tools for instanode.dev — let LangChain agents provision ephemeral Postgres + webhooks

raglite

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

memharness

Framework-agnostic memory infrastructure for AI agents

embedbase

Open-source API & SDK to integrate your data and easily hook them up to LLMs.