Solomon AIA knowledge graph you own
Connects Gmail, Calendar, and meeting notes into an Obsidian-compatible Markdown vault of people, projects, decisions, and commitments — every claim traceable to its source.
Local-first AI coworker
An assistant that remembers your work.
The local-first AI layer of Solomon AI. It turns your email, calendar, and meetings into a knowledge graph you own — and is built to work across Eigenn, Cadense, and Conduitt to draft, prep, and act on what matters, privately on your machine.
§What it does
One working memory
Context that compounds, instead of retrieval that starts cold.
Most AI tools rebuild context on demand by re-reading transcripts. Solomon AI Assistant keeps long-lived memory instead — relationships are explicit, inspectable, and editable by you. It's built to connect with the rest of Solomon AI, so that memory can reach past your inbox into the customers, invoices, and conversations your team already works in.
Live notes that stay current
Give a note an objective and it updates itself on a schedule or when new emails and events match — track a deal, a person, or a competitor without rebuilding the summary.
Local-first by design
Everything is plain Markdown on your machine. Inspect, edit, back up, or delete it anytime. No proprietary format, no hosted lock-in.
§Built to act
Acts, with your approval
Drafts, briefs, and real artifacts — from context it already has.
Solomon AI keeps your finance work in one place. The Assistant is the AI built to act across it — reading your vault, and connecting to your platforms, to produce work, not just answers. Every action is reviewable before it runs.
Meeting prep & email drafts
Pulls past decisions, open questions, and threads into a crisp brief or a grounded email draft — including PDF decks generated from your ongoing context.
Designed to work across Solomon AI
Designed to connect to Eigenn (modeling), Cadense (payables), and Conduitt (customer comms) over the Model Context Protocol — so it can act on the same records your team uses, alongside Slack, Linear, GitHub, and your own tools.
Bring your own model
Run local models via Ollama or LM Studio, or hosted providers with your own key. Swap anytime — your data stays in your vault.
§Download
Open source · yours to run
Download it. Own your data. Keep your keys.
A desktop app for macOS, Windows, and Linux. Open source under Apache-2.0, runs on your machine, works with the model and tools you choose, and updates itself after install.