Frequently asked questions

A native desktop AI workspace that orchestrates a team of coding agents against your real project — a manager plans, workers build in parallel, and a critic reviews before anything reaches you. See How it works.

No. You bring your own models — API keys or the agent CLIs you already have. Koryphaios is the orchestration layer, not a reseller of inference.

The current registry exposes 94 provider adapters, including API-key connections (OpenAI, Google direct API, Google AI Studio, Vertex AI, Anthropic, xAI, Groq, OpenRouter, Azure, Bedrock, Mistral, and OpenAI-compatible endpoints) and subscription CLIs (Claude Code, Codex, Grok, Cursor, Devin, Cline, Antigravity). Authentication and model availability are checked live, so a listed adapter is not a promise that every account exposes every model. See Providers.

The backend and repository operations run locally. An API or CLI model sees the context you choose to send, and model sharing forwards the bounded model request through the host you joined. Koryphaios does not silently upload your repository to a Sylorlabs service. See model sharing.

The app itself runs locally, but the models don't — you need network access to reach a hosted provider. If you point Koryphaios at a local model (Ollama, LM Studio, llama.cpp), you can work fully offline.

Windows, macOS (Apple Silicon & Intel), and Linux (.deb, .rpm, AppImage). One note: the model-sharing sandbox can use kernel enforcement on Linux and macOS when the host supports it; on Windows it's a softer jail — details in The remote sandbox.

Sharing your own API keys is fine. Sharing a subscription(Claude, Copilot, ChatGPT plans) is account-sharing that several providers' terms forbid and enforce. The app flags this per provider and defaults subscriptions off. See Share your models.

Every AI change is captured as a ghost commit, so you can rewind the workspace to any earlier state. Combined with the critic gate and per-tool permissions, mistakes are recoverable. YOLO mode removes the confirmations if you want speed over caution.

Same core idea (wikilinks, backlinks, a graph) but native to the workspace and — the real difference — readable and writable by your agents. It now covers the features people miss most: live Markdown preview, math (KaTeX) and Mermaid diagrams, a Dataview-style query language, aliases, ghost nodes, callouts, a plugin API, a spatial canvas/whiteboard, and full-text search that stays fast at thousands of notes (the graph renders on a GPU-friendly canvas with no node cap). The honest gaps: a mature third-party plugin ecosystem and a native mobile app. See Notes.

Not yet as a shipping native app. The desktop UI (including notes) is touch-friendly and responsive down to phone widths. A packaged iOS/Android build is on the roadmap — it needs its own device testing and store pipeline, so we'd rather ship it right than ship it untested.

The app checks for updates and can install them in place; a banner appears when one is available, and the changelog lists what changed each release.

The desktop app is free to download and run — you only pay your own model providers. Grab it from the download page.