# Korvo

> Korvo is a local-first private research workspace that organises documents, plans analysis, cites sources, and preserves a traceable decision record — all on your machine.

Korvo is a local-first desktop application built by Snab Limited (trading as Korvo, Company No. 16006744, England & Wales). It runs on macOS, with Windows and Linux in alpha, and gives knowledge workers a private workspace for turning scattered documents into traceable, cited decisions. No account is required to download and start using the free Explorer tier.

## What It Is

Korvo positions itself as a "decision engine" rather than a chatbot or generic AI workspace. Users drop in PDFs, spreadsheets, notes, and transcripts; Korvo indexes them locally using its on-device embedding engine (Korvo Embed), plans the analysis, executes grounded synthesis with inline citations, and preserves the full decision record — including the plan, evidence, model details, revisions, and unresolved questions — for later inspection. The core workflow is: **Capture → Structure → Plan → Execute → Preserve**.

## Local-First Architecture and Privacy Model

Korvo's privacy design is structural rather than policy-only:

- **Files, notes, the local SQLite index, plans, and decision history reside strictly on the user's device.** Korvo states it never holds workspace data on its servers.
- **BYOK (Bring Your Own Key):** Users connect OpenAI, Anthropic, or Google directly with their own API keys. Prompts and selected context go to that provider under the user's own agreement; Korvo does not proxy, inspect, or log them.
- **100% on-device option:** Connect Ollama for full offline operation — no prompt, project context, or document data leaves the machine.
- **Korvo Embed**, the on-device embedding engine, is a 34 MB encoder with no HTTP client in its dependency tree, making it structurally incapable of sending documents to a network. It is verifiable in one command and enforced in CI.

## Key Capabilities

- **Plan Mode:** Korvo detects the goal, surfaces assumptions, flags missing context, and proposes analysis steps before any generation runs. Users approve the plan.
- **Grounded outputs with citations:** Every material claim links back to the specific source file, sheet, and cell range in the project.
- **Two-model critique pass (beta):** One model builds the case; a second critiques it. The revision and unresolved questions remain visible.
- **Decision history:** Conclusions, source links, model details, timestamps, and open questions are preserved together and exportable to PDF or Markdown.
- **MCP integration:** Users can connect the built-in Superhuman Mail preset or a custom MCP server. Chat models cannot autonomously execute MCP tools; mutating or unannotated tools require explicit confirmation.
- **Medha:** An on-device quality-measurement layer that tests retrieval with deterministic metrics (recall, MRR, nDCG) in under 10 ms per operation, with zero network calls.

## Target Audience

Korvo is built for professionals who need to show their work:

- **Investors** running due diligence across decks, financials, founder notes, and call transcripts.
- **Founders** turning board material, customer evidence, and strategy notes into plans with explicit assumptions.
- **Operators** synthesising multi-report context into actionable briefs.
- **Researchers** organising literature sets, comparing claims, and producing cited synthesis.

## Current Status

The product is in early access as of 2026. The two-model critique (Deliberation) remains in beta while real-project dogfood and blinded evaluation continue. Medha's synthetic baselines are available; human-labelled release evaluation is still in progress. Early-access delivery is targeted within seven days of purchase. An iPhone and iPad version is available via TestFlight request. Korvo Agents — starting with Google Calendar, Drive, and Korvo Workspace integration — are announced as coming next, with a private cloud execution model and visible run history.

## Features
- Local-first workspace — all files, notes, index, and decision history stored on device
- On-device semantic search via Korvo Embed (34 MB encoder, no network access)
- Plan Mode — goal detection, assumption surfacing, and analysis planning before generation
- Grounded outputs with inline citations linked to source file, sheet, and cell
- Two-model critique pass (beta) — one model builds, a second critiques
- Decision history with source links, model details, timestamps, and open questions
- Export to PDF and Markdown
- BYOK support for OpenAI, Anthropic, and Google
- Ollama integration for fully on-device, offline operation
- MCP server integration with manual tool execution and confirmation controls
- Medha on-device quality measurement (recall, MRR, nDCG) — zero network calls
- Korvo Embed licensing for third-party products
- Superhuman Mail MCP preset
- iPhone and iPad TestFlight access (alpha)
- Korvo Agents (coming soon) — Google Calendar and Drive integration

## Integrations
OpenAI, Anthropic, Google (Gemini), Ollama, Superhuman Mail, Google Calendar, Google Drive, MCP servers (custom), Zotero (planned), Mendeley (planned)

## Platforms
WINDOWS, MACOS, LINUX, ANDROID, IOS, WEB, API

## Pricing
Freemium — Free tier available with paid upgrades

## Links
- Website: https://www.korvo.xyz
- Documentation: https://www.korvo.xyz/faq
- EveryDev.ai: https://www.everydev.ai/tools/korvo