Skip to main content
DOSIA is ByteSpike’s own desktop client — a multi-model chat app with image/video generation, vision, MCP tool calling, and an agent loop. It speaks every protocol ByteSpike serves, so the same key reaches Claude, GPT-5, Gemini, DeepSeek, Doubao, Kimi, GLM, MiniMax, Seedream, Sora, Veo, Seedance — without per-vendor reconfiguration. Two ways to wire it up:
  • Personal mode — install DOSIA, paste your own sk-byts-... key, pick models. This page covers that path.
  • Enterprise mode — admin pre-provisions you via lark SSO, DOSIA auto-picks up the allowed model set, no manual key. See Employee onboarding for the enterprise flow.

Install

Download the latest dmg from github.com/leave1206/dosia-releases:
  • Apple Silicon (M1/M2/M3/M4): DOSIA-x.y.z-arm64.dmg
  • Intel: DOSIA-x.y.z.dmg
Drag DOSIA into /Applications, then launch.
First-launch may report “file is damaged” or “from an unidentified developer” — that’s macOS Gatekeeper blocking an un-notarized dmg, not a real issue. Fix:
xattr -cr /Applications/DOSIA.app
Then relaunch.

Personal mode setup

1

Get a ByteSpike key

console.bytespike.ai/keysCreate key. Pick the routing group based on what you want DOSIA to reach (claude-default for Claude, gemini-default for Gemini, or default to route everything). See Models for the group-vs-model map.
2

Open DOSIA Settings

Top menu: DOSIA → Settings (shortcut ⌘, on Mac).
3

Stay in Personal mode

Deploy Mode stays on Personal (the default). Enterprise mode is for SSO-managed accounts — see Employee onboarding if your admin gave you a backend URL.
4

Add ByteSpike as a provider

Settings → AI Models → Add Provider → “ByteSpike”.
FieldValue
Base URLhttps://llm.bytespike.ai
API keyyour sk-byts-...
ProtocolAnthropic Messages (or OpenAI Chat Completions — either works against the same key)
DOSIA will hit /v1/models against ByteSpike to fetch the list of models your key can actually reach. Wait a couple seconds for the dropdown to populate.
5

Pick a model + chat

Back in the main chat box, pick any model in the dropdown (“Claude Sonnet 4.6” / “GPT-5.5” / “Gemini 3.1 Pro” / etc.). Type a message, hit enter.

What works in DOSIA

FeatureBacked by
Text chatAll text models (Claude / GPT / Gemini / DeepSeek / Kimi / GLM / MiniMax / Doubao)
Vision (drag image into chat)DOSIA’s analyze_image MCP tool calls a vision model (Claude / GPT-5-4 / Gemini)
Image generation (“draw a …”)generate_image MCP tool routes to Nano Banana / Seedream / GPT-Image
Video generation (“generate a video of …”)generate_video MCP tool routes to Sora / Veo / Seedance
Agent (multi-step task)DOSIA’s agent loop calls tool_use / function calling across providers
MCP pluginsDOSIA bundles 9 official plugins (Lark, browser automation, meeting analysis, knowledge base, etc.) — see github.com/leave1206/dosia-plugins
For the routing model (how the agent decides which model handles which step), see DOSIA Agent mode. For the MCP bridge between DOSIA and the model side, see MCP integration.

Switching models

Each chat thread remembers the model it was opened with. Switch at the top of the chat box — the dropdown shows every model your key can reach. Image / video model picks happen inside the respective tool calls; you don’t need to set them per-thread.

Troubleshooting

SymptomCauseFix
”Failed to fetch models” after adding providerKey invalid or wrong groupCopy a fresh key from console; confirm group serves the models you expected
Model dropdown emptyKey has 0 allowed modelsCheck the key’s group_id in console; pick a non-empty group
Image / video tool button greyed outThe MCP plugin isn’t enabled in DOSIA settingsSettings → MCP → enable image-tools / video-tools
Vision drag-drop returns 400The chosen text model doesn’t support image inputSwitch the chat to claude-sonnet-4-6, gpt-5-4, or gemini-3-1-pro
”insufficient_balance”Key (or org wallet) is out of creditsTop up at console.bytespike.ai/billing
Slow first tokenCold start on a cross-protocol translation routeWarm with a small request first, or stick to a native protocol for hot path

Enterprise mode (lark SSO)

If your company runs DOSIA centrally: admin provisions the enterprise backend URL, DOSIA flips into Enterprise mode, lark SSO logs you in, the allowed model set syncs automatically — no per-user key. The full setup is in Employee onboarding. The admin side (granting employees, monitoring usage, configuring allowed groups) is documented in Admin operations.

Next

Employee onboarding

Enterprise / SSO path.

DOSIA Agent mode

How DOSIA’s agent loop picks models per step.

MCP integration

The bridge between DOSIA’s tool plugins and the model side.

Configure your client

Wire any other client (Claude Code / Codex / Cursor / SDK).