Metadata-Version: 2.4
Name: openaugi
Version: 0.1.0
Summary: Self-hostable personal intelligence engine. One pip install. One SQLite file. One MCP server.
Project-URL: Homepage, https://github.com/bitsofchris/openaugi
Project-URL: Repository, https://github.com/bitsofchris/openaugi
Project-URL: Issues, https://github.com/bitsofchris/openaugi/issues
Author-email: Chris <chris@openaugi.com>
License-Expression: MIT
License-File: LICENSE
Keywords: knowledge-graph,mcp,obsidian,personal-knowledge,sqlite
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.12
Requires-Dist: mcp>=1.0
Requires-Dist: numpy>=1.26
Requires-Dist: openai>=1.0
Requires-Dist: pydantic>=2.6
Requires-Dist: rich>=13
Requires-Dist: sqlite-vec>=0.1.6
Requires-Dist: tiktoken>=0.7
Requires-Dist: typer>=0.12
Requires-Dist: watchdog>=4.0
Provides-Extra: all
Requires-Dist: httpx>=0.27; extra == 'all'
Requires-Dist: openai>=1.0; extra == 'all'
Requires-Dist: sentence-transformers>=3.0; extra == 'all'
Provides-Extra: dev
Requires-Dist: pre-commit>=4.0; extra == 'dev'
Requires-Dist: pyright>=1.1; extra == 'dev'
Requires-Dist: pytest-cov>=5.0; extra == 'dev'
Requires-Dist: pytest>=8.0; extra == 'dev'
Requires-Dist: ruff>=0.4; extra == 'dev'
Provides-Extra: local
Requires-Dist: sentence-transformers>=3.0; extra == 'local'
Provides-Extra: ollama
Requires-Dist: httpx>=0.27; extra == 'ollama'
Provides-Extra: openai
Provides-Extra: remote
Requires-Dist: cryptography>=42; extra == 'remote'
Requires-Dist: httpx>=0.27; extra == 'remote'
Requires-Dist: pyjwt>=2.8; extra == 'remote'
Description-Content-Type: text/markdown

# 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.](LICENSE)

---

## Quick Start

```bash
# 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](docs/GETTING_STARTED.md#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](docs/GETTING_STARTED.md)** — full install guide, CLI reference, MCP tools, Claude registration
- **[Architecture](ARCHITECTURE.md)** — data model, processing layers, module map, design decisions
- **[MCP Server](docs/MCP_SERVER.md)** — tool reference and tuning
- **[Remote Access](docs/local.docs/REMOTE_ACCESS.md)** — Cloudflare Tunnel setup for Claude mobile

---

## Development

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

See [ARCHITECTURE.md](ARCHITECTURE.md) for the full system map.

---

## License

MIT
