OpenCompanyBrain

A local knowledge workspace for people and AI assistants.

Keep documents, source references, decisions and their revisions under your control. Connect compatible assistants through MCP. Choose a local model or an optional remote provider for tasks that need generation.

0.1.0-alpha — early development. The feature matrix distinguishes working components from experiments and planned extensions. This is not a hosted service.

Local demo workspace. All displayed content is synthetic.

Quick start

Use Python 3.11 or newer and a virtual environment. The alpha passes CI on Windows, macOS and Linux with Python 3.11 and 3.13, including clean wheel installation and synthetic CLI/MCP checks. Optional integrations have their own requirements; see the verification record for evidence and limits. From this checkout:

python -m venv .venv
# Activate .venv using the command for your shell.
python -m pip install -e .
python -m opencompanybrain --home ./brain-data plan
python -m opencompanybrain --home ./brain-data init
python -m opencompanybrain --home ./brain-data doctor
python -m opencompanybrain --home ./brain-data demo
python -m opencompanybrain --home ./brain-data serve

Open http://127.0.0.1:8877. The demo uses synthetic material. Choose a data directory outside the checkout for a lasting installation. A model account or API key should not be needed to inspect the local workspace and try the demo.

For AI-assisted installation, start with AGENTS.md, project-manifest.json and the installation guide. Run the installed CLI's --help before configuring additional commands.

Related MCP server: context-atlas

What the project is for

• Map explicitly selected sources rather than uploading a computer's contents.

• Keep source provenance and distinguish extracted, generated and curated knowledge.

• Prepare document changes with review, or publish validated changes automatically according to each source's policy.

• Retrieve a bounded, attributable context package through MCP.

• Add conversion, graph and operational integrations as optional components.

The last four areas are being assembled during the alpha. See the feature matrix for the implementation status and roadmap for the wider scope.

Local by choice

The application and its data directory run on your machine. Selecting a cloud model or remote database makes the relevant transfer an explicit configuration decision. Local installation alone does not make a remote model private or offline. See security and configuration.

Documentation

• Install and verify

• Configuration and data

• Optional database sources

• Local document and media extraction

• Optional telemetry and release staging

• Connect an assistant through MCP

• Source and document lifecycle

• CLI reference

• Feature status

• Verification record

• Publication gate

• Roadmap

• Guida in italiano

• Contribute · Changes · MIT license

Screenshots are generated from synthetic demo data. A screenshot demonstrates a particular view, not completion of every roadmap item.