Knowledge Management Python Packages

basic-memory

AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https://discord.gg/tyvKNccgqN

atlas-mind

Self-hostable, git-native knowledge base & AI memory (MCP) — your notes stay plain Markdown files in your own git repo. Pure-stdlib Python, no database. AGPL-3.0.

kluris

Turn AI agents into team SMEs. Kluris builds a shared, human-curated knowledge brain (decisions, constraints, incidents, tribal knowledge) as markdown in a git repo. Queryable via slash commands from Claude Code, Codex, Cursor, Windsurf, Cline, Gemini CLI.

bkmr

Knowledge Management for Humans and Agents

ain-state-compiler

AIN State Compiler is a local-first enterprise AI state compiler that continuously transforms Slack, Jira, and Gmail logs into executable, conflict-resolved operational state. Built with Python and SQLite.

research-hub-pipeline

AI-operable research workspace for Zotero, Obsidian, and NotebookLM. Use any two, or all three, through CLI, MCP, REST, and dashboard.

obsidiantools

Obsidian tools - a Python package for analysing an Obsidian.md vault

innate-ai

Self-growing procedural knowledge layer for AI agents. Rust MCP server + CLI — recall relevant knowledge before tasks, record outcomes after, distill experience into reusable insights. Works with Claude Code, Codex, opencode.

uni-db

Uni is a modern, embedded database that combines property graph (OpenCypher), vector search, and columnar storage (Lance) into a single, cohesive engine. It is designed for applications requiring local, fast, and multimodal data access, backed by object storage (S3/GCS) durability.

uni-db-onnx

Uni is a modern, embedded database that combines property graph (OpenCypher), vector search, and columnar storage (Lance) into a single, cohesive engine. It is designed for applications requiring local, fast, and multimodal data access, backed by object storage (S3/GCS) durability.

mcp-logseq

MCP server to interact with LogSeq via its Local HTTP API - enabling AI assistants like Claude to seamlessly read, write, and manage your LogSeq graph.

cruxhive-mcp

One knowledge base, every AI tool. Human-approved, versioned, local. MIT.

create-vivary

Typed memory, search, and gates for AI-agent workspaces. Scaffold plain-Markdown project memory, state, skills, and review gates in one command.

athenaeum

Open source knowledge management pipeline — passive recall, append-only intake, tiered compilation, configurable schemas

memtomem

Markdown-first, long-term memory infrastructure for AI agents. Hybrid BM25 + semantic search across markdown/code files via MCP.

keephive

A knowledge sidecar for Claude Code. It captures what you learn, verifies it stays true, and surfaces it when relevant.

vivary-tropo

Typed memory, search, and gates for AI-agent workspaces. Scaffold plain-Markdown project memory, state, skills, and review gates in one command.

memorius

Memorius is a self-contained, agent-agnostic memory system that gives LLMs and AI agents persistent, searchable memory with a hierarchical knowledge organization. Drop-in with multi-backend vector storage, pluggable embeddings, built-in MCP + REST servers, and auto-detecting agent hooks for 7 different AI coding agents.

socratic-knowledge

RAG (Retrieval-Augmented Generation) with semantic search and embeddings

uni-db-onnx-cuda

Uni is a modern, embedded database that combines property graph (OpenCypher), vector search, and columnar storage (Lance) into a single, cohesive engine. It is designed for applications requiring local, fast, and multimodal data access, backed by object storage (S3/GCS) durability.

uni-db-cuda

Uni is a modern, embedded database that combines property graph (OpenCypher), vector search, and columnar storage (Lance) into a single, cohesive engine. It is designed for applications requiring local, fast, and multimodal data access, backed by object storage (S3/GCS) durability.

uni-db-metal

Uni is a modern, embedded database that combines property graph (OpenCypher), vector search, and columnar storage (Lance) into a single, cohesive engine. It is designed for applications requiring local, fast, and multimodal data access, backed by object storage (S3/GCS) durability.

trw-mcp

MCP server for AI coding agents — persistent engineering memory, knowledge compounding, and spec-driven development workflows. Part of TRW Framework.

myco

The living armor an AI agent inhabits: eternal devouring, eternal evolution, eternal amplification.