Skip to main content

Self-hostable personal intelligence engine. One pip install. One SQLite file. One MCP server.

Project description

OpenAugi

Your augmented knowledge base for Agentic work.

Human Context for Agents

You've become the bottleneck.

Your notes are scattered. Your AI can't reach them. Every conversation starts from zero.

Claude and ChatGPT memory keep you stuck in a weird bubble.

You've built years of thinking in Obsidian, Google, ChatGPT — ideas, decisions, threads you've followed and dropped. But when you talk to your agent, none of that context exists. You repeat yourself. You lose threads. The AI that's supposed to help you think doesn't know what you've been thinking about.

OpenAugi fixes this. It turns your personal data vault turned into a knowledge graph that agents can search, traverse, and understand — semantically, by keyword, by tag, by time. One SQLite file. One MCP server. Everything stays on your machine.

Status: Alpha. Evolving. This is a working tool, not a polished product. Expect rough edges. MIT licensed.


Quick Start

# Install from source (PyPI coming soon)
git clone https://github.com/bitsofchris/openaugi.git
cd openaugi && python3 -m venv .venv

# Pick your embedding model
.venv/bin/pip install -e ".[local]"    # free, no API key
# or: .venv/bin/pip install -e ".[openai]"  # better quality, needs API key

# Configure and run
.venv/bin/openaugi init    # one-time: vault path, embedding model, API key
.venv/bin/openaugi up      # sync vault + start MCP server + watch for changes

Then register with Claude and start asking questions about your notes.


What It Actually Does

Obsidian Vault --> split --> extract --> embed --> SQLite --> MCP Server --> Claude

Ingest: Splits your vault by headings, extracts tags and links, builds a graph of blocks and links in SQLite. Embeds everything for semantic search. Watches for changes and re-ingests automatically.

Query: Claude gets MCP tools to search (semantic + keyword), traverse your knowledge graph, fetch full context, and understand how your ideas connect. It can also write notes back to your vault.

Run: One command (openaugi up) does everything — ingest, file watcher, MCP server. Runs as a background service if you want.


Why This Exists

Most "AI + notes" tools are cloud services that want your data. Or they're RAG demos that chunk your files and call it a day.

OpenAugi is different:

  • Your data stays yours. One SQLite file on your machine. No cloud. No account.
  • Graph, not chunks. Tags, links, and documents are first-class nodes. Claude can follow connections, not just match keywords.
  • Time-aware. Your notes have history. OpenAugi preserves it — recently created, hub velocity, threads you dropped.
  • Composable. MCP tools that Claude calls directly. No middle layer, no wrapper app.

This started as a personal tool to make Claude useful with a large Obsidian vault. It works well enough that it might be useful to others.


Values

  • Privacy as foundation — your data stays on your machine
  • Open by default — MIT licensed, all code public
  • Augment, stay human — amplify your thinking, don't replace it
  • Composable ecosystem — building blocks that work together

Documentation

  • Getting Started — full install guide, CLI reference, MCP tools, Claude registration
  • Architecture — data model, processing layers, module map, design decisions
  • MCP Server — tool reference and tuning
  • Remote Access — Cloudflare Tunnel setup for Claude mobile

Development

.venv/bin/pip install -e ".[dev]"
./scripts/check.sh          # lint + types + tests

See ARCHITECTURE.md for the full system map.


License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

openaugi-0.1.0.tar.gz (90.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

openaugi-0.1.0-py3-none-any.whl (59.5 kB view details)

Uploaded Python 3

File details

Details for the file openaugi-0.1.0.tar.gz.

File metadata

  • Download URL: openaugi-0.1.0.tar.gz
  • Upload date:
  • Size: 90.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for openaugi-0.1.0.tar.gz
Algorithm Hash digest
SHA256 7fa15c8fa08ff9574981b73b29696d2d7de34ba0c712e7a83cea04037018948f
MD5 0a2061ec2213b20390267816ed327529
BLAKE2b-256 47ca366e6c1b6296a2d2355ccf3fde2dd02a51494a58ed7bf4f01c6b080e5bd2

See more details on using hashes here.

Provenance

The following attestation bundles were made for openaugi-0.1.0.tar.gz:

Publisher: publish.yml on bitsofchris/openaugi

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file openaugi-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: openaugi-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 59.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for openaugi-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 8e0034bbfac86a9a10cd8019e816a3a52eb8fa1170f8667389ea292634d7bd87
MD5 a8ae22d32bad2e24c3a9b7f896d8939d
BLAKE2b-256 29c36a5070cec894b44b6b194fb5369825df1ebcbe6df4de03ec29ed1cb34b4b

See more details on using hashes here.

Provenance

The following attestation bundles were made for openaugi-0.1.0-py3-none-any.whl:

Publisher: publish.yml on bitsofchris/openaugi

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page