Settings¶
Hive's Settings view is a single scrolling page of sections. Workspace-scoped
config (runtimes, MCP servers) is written back to hive.config.toml; connection
settings persist to a settings.json in the app data dir; the theme is stored
locally per device.

Identity¶
Your display name (the (@handle, device) pair Hive signs envelopes with)
and the current device name.
Workspace¶
The workspace root path (drives the Diff canvas + git integration), the current git branch / dirty count, and an Open in editor shortcut.
Team sync¶
Everything needed to share a workspace, editable at runtime (applied within a
few seconds, no restart). Teams are normally created/joined from the left
rail (the + button generates the room, key, and a shareable code for you);
this section is the manual/advanced surface and the relay configuration:
- Relay URL — peers on the same relay + room converge. Blank = local-only.
- Relay access token — needed only for a gated/paid hosted relay; leave blank for a relay you host yourself (the open default). Sent as a bearer on every relay request; never echoed back.
- Room + Workspace key (under Advanced) — the room id and the shared
passphrase → end-to-end encryption; the relay sees only ciphertext (status
shows
🔒 encrypted).
See Self-hosting a relay, the small-team deployment guide, and the pricing tiers.
Account (GitHub)¶
Sign in with GitHub (OAuth device flow) to get a stable identity across all your
devices and to invite teammates by @handle. The same GitHub account on your
laptop and desktop resolves to one member, two devices. See
Identity & devices. Official builds ship with the
OAuth App client id baked in; forks can paste their own.
Check for updates also lives here. The auto-updater is scaffolded and activates at public launch (for signed builds); on current unsigned dists it's inert.
Danger zone — Reset local data¶
The bottom of the Account tab has a Danger zone with "Reset local data": it wipes this device's chats, identity, keys, settings, and workspaces, then relaunches Hive fresh. It's the supported way to start over — uninstalling leaves data behind. See Reset local data for the per-OS data directories.
Providers, Models & Agents¶
LLM access is organized as a hierarchy:
- Providers —
anthropic,openAI,openRouter,ollama,custom, plus theclaudeCLI and subprocess agents (pi/aider). Each provider holds its own API key and optional base URL (so multiple providers can have distinct keys, including any generic OpenAI-compatible endpoint). - Models (runtimes) — a model on a provider (id + capability flags).
- Agents — reusable personas (name + model/runtime + role + instructions) you can attach to any chat.
The default runtime is the claude CLI — no API key needed, it uses your
Claude subscription. See Configuring a runtime.
Agent file access¶
Controls how agents are allowed to touch files — and this differs per agent type (Claude Code is not the only agent that edits files):
claudepermission mode —Read-only(default; proposes edits but blocks writes),Accept edits(can write files), orBypass all(also runs shell commands). Injected as--permission-modeinto theclaudeCLI, which runs headless and can't show an interactive prompt.- aider / pi gate via their own flags.
- API/MCP-backed agents gate via built-in-tool consent + per-tool MCP trust (see Tools, consent & trust).
MCP servers¶
Install / enable / remove Model Context Protocol servers. An installed server
stays inert until you enable it — enabling is what launches the command or
opens the connection. Two transports: stdio (Hive spawns the binary) and
http. See MCP servers.
Appearance¶
- Mode —
Auto(follows your OS light/dark setting, any platform),Light, orDark. - Theme — the accent family: pollen (the honey-gold default), studio (neutral graphite), harbor (ocean blue), or meadow (green). Each has a light and a dark variant; the mode picks which.
Notes¶
- New chats are auto-titled from the opening exchange using the chat's primary runtime — no setting required.
- Workspace config round-trips through the TOML encoder, so hand-edited and
GUI-edited
hive.config.tomlfiles stay compatible (comments aren't preserved). Seehive.config.tomlreference.