Bring your own engine
Detailed GlinkBot custom engines guidance.
Two zero-code ways to run GlinkBot bots on an engine the app doesn't ship.
Both live in ~/.glinkbot/config.json under "instances"; restart the app
after editing (instance entries are read at boot).
Provider icons
Each instance shows its driver's mark. An OpenAI-compatible server shows the
mark of whoever runs it, read from the host in its address: api.deepseek.com
shows DeepSeek, <resource>.openai.azure.com Microsoft Azure,
dashscope-intl.aliyuncs.com or <workspace>.<region>.maas.aliyuncs.com Qwen,
openrouter.ai OpenRouter, and so on
(the list is SERVER_HOSTS in server/provider-icon.ts). A server without a
mark of its own, such as Groq, Together, Ollama or LM Studio, keeps the default.
An icon stored on the instance still wins: add
"icon": { "kind": "preset", "preset": "azure" } alongside driver and
displayName. The presets are OpenAI, Anthropic, Google Gemini, Microsoft
Azure, Amazon Bedrock (AWS), xAI, DeepSeek, Meta, Mistral AI, Qwen, Moonshot
AI, Cohere and OpenRouter. Custom images saved before v0.1.102 keep rendering;
the app never fetches remote icon URLs.
Any ACP agent (a CLI you spawn)
If an agent CLI speaks ACP over stdio —
fx acp, a Zed-style agent server, your own wrapper — point a customAcp
instance at it:
{
"instances": {
"my-agent": {
"driver": "customAcp",
"displayName": "My Agent",
"environment": { "MY_AGENT_TOKEN": "…" },
"config": { "cli": "my-agent acp" }
}
}
}
config.cliis the whole command, args included ("npx -y some-agent acp"works). You can also set it from the app: Settings → Engines → Set CLI… on the instance's row. An instance without a command shows up with exactly that hint instead of failing at first message.- Sign in first. The driver has no auth flow of its own — run the CLI once in a terminal and log in there; GlinkBot spawns it with your login intact.
- Choose models per bot. Open the bot's model picker and use Refresh models to load the models advertised by the agent. Select a model and, when offered, its thinking level. Bot defaults and individual conversation overrides are saved independently. Agent default leaves the native session's model unchanged. An agent that does not advertise models still has this option.
- Choices come from the agent. Discovery starts a temporary ACP session without sending a prompt. Only confirmed, model-specific thinking options are shown; a failed refresh keeps the last successful catalog. ZCode, CodeBuddy, Qoder and other custom ACP engines use the same mechanism.
environmentis passed to the CLI child. Foreign provider keys (XAI_API_KEY, OPENAI_COMPAT_API_KEY, …) are deliberately stripped so a custom CLI can never bill against another engine's login.- Permissions ride ACP's own
session/request_permission— if your agent asks, the request becomes a normal approval card in chat. - Multiple instances are fine — one per agent.
Example: Mistral Vibe
Mistral Vibe ships an ACP entry
point, vibe-acp, so it runs as a custom ACP engine with your Mistral account's
own sign-in, not a Mistral API key saved in GlinkBot.
-
Install it:
uv tool install mistral-vibe(orpipx install mistral-vibe). This putsvibeandvibe-acpin~/.local/bin. -
Sign in once from a terminal: run
vibe --setupand sign in with your Mistral account (Vibe offers a browser sign-in through Mistral AI Studio, or an API key). Vibe uses the first credential it finds in the shell environment,~/.vibe/.env, or the OS keyring, andvibe-acpuses it too. -
Add the instance and restart GlinkBot:
{ "instances": { "mistral-vibe": { "driver": "customAcp", "displayName": "Mistral Vibe", "icon": { "kind": "preset", "preset": "mistral" }, "config": { "cli": "/home/you/.local/bin/vibe-acp" } } } }Use the full path when
~/.local/binis not on the app'sPATH(a desktop app started from the dock often doesn't have it). -
Pick Mistral Vibe for a bot. Its model menu shows Agent default, which runs the model Vibe itself uses by default.
GlinkBot never passes its own MISTRAL_API_KEY to the CLI, so turns use the
Vibe sign-in from step 2. Without it, the chat shows Missing API key for mistral provider: sign in again from a terminal (step 2).
Example: Command Code
Command Code has an ACP mode, cmd acp, so it runs as
a custom ACP engine with your own Command Code sign-in. (Checked with
command-code 1.88.2.)
-
Install it:
npm install -g command-code. This putscmdon yourPATH; on Windows the command iscmdc, becausecmdis the Windows command prompt. -
Sign in once from a terminal: run
cmd login(cmdc loginon Windows). On a server without a browser, create an API key in Command Code Studio instead and put it in the instance'senvironmentasCOMMAND_CODE_API_KEY; GlinkBot passes it to the CLI. -
Add the instance and restart GlinkBot:
{ "instances": { "command-code": { "driver": "customAcp", "displayName": "Command Code", "config": { "cli": "cmd acp" } } } }Use
"cmdc acp"on Windows, and the full path when the npm global folder is not on the app'sPATH:which cmdon macOS or Linux, orwhere.exe cmdcon Windows. -
Pick Command Code for a bot. Its model menu shows Agent default, which runs Command Code's own default model; Refresh models lists the models it advertises once you're signed in.
Without a sign-in the chat shows Not authenticated. Run `cmd login` in a terminal first.: sign in from a terminal (step 2). A wrong
COMMAND_CODE_API_KEY shows 401 error: Invalid 'Authorization' header or token.
Any OpenAI-compatible endpoint (no process at all)
The built-in openai-compat driver supports multiple instances, so a local
vLLM/LM Studio/Ollama-openai endpoint or any hosted compatible API is one
entry:
{
"instances": {
"my-endpoint": {
"driver": "openai-compat",
"displayName": "My Endpoint",
"environment": { "MY_ENDPOINT_KEY": "sk-…" },
"config": {
"url": "http://127.0.0.1:1234/v1",
"apiKeyEnv": "MY_ENDPOINT_KEY",
"model": "my-model"
}
}
}
}
apiKeyEnvnames whichenvironmentvalue carries the key, so several instances can hold different keys without colliding.- The driver lists the endpoint's
/modelswhen it can and keeps yourmodelas a custom option either way. - OpenAI-compatible instances support structured tools and image input. With a model that accepts both, the harness can mount the approved host, Local VM, VPS or built-in browser tools and return their screenshots to the model. The existing platform, computer-selection and approval checks still apply.
- Set
config.toolstofalsefor a model without tool support. Image support also depends on the chosen model; the driver cannot add vision to a text-only model. See tool verification for scope and tests.
Example: Alibaba Cloud Model Studio (Qwen)
Use the openai-compat instance above with your Model Studio API key and a
model ID enabled for your account. Set config.url to the base URL from
your Model Studio workspace, including /compatible-mode/v1:
| Region | Base URL |
|---|---|
| Beijing | https://<workspace-id>.cn-beijing.maas.aliyuncs.com/compatible-mode/v1 |
| Virginia | https://<workspace-id>.us-east-1.maas.aliyuncs.com/compatible-mode/v1 |
| Singapore | https://<workspace-id>.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1 |
| Tokyo | https://<workspace-id>.ap-northeast-1.maas.aliyuncs.com/compatible-mode/v1 |
Replace <workspace-id> with your workspace ID. The API key must come from
the same region as the endpoint; a mismatch can return HTTP 401 even when
the key is valid. The older dashscope.aliyuncs.com and
dashscope-intl.aliyuncs.com addresses still work. Both address formats show
the Qwen mark; the mark identifies the service, not the selected model's
capabilities or account access.
See Alibaba Cloud's OpenAI-compatible API guide for current addresses, model availability and region requirements.
Example: GLM through Z.ai or Zhipu BigModel
Use the openai-compat instance above with a general API key from your
chosen service. Set config.url to its OpenAI-compatible base URL:
| Service | Base URL |
|---|---|
| Z.ai (international) | https://api.z.ai/api/paas/v4 |
| Zhipu BigModel (mainland China) | https://open.bigmodel.cn/api/paas/v4 |
Set environment.MY_ENDPOINT_KEY to that service's API key and keep
config.apiKeyEnv as MY_ENDPOINT_KEY. Set config.model to an exact model
ID available to your account, such as glm-5.3. The driver appends
/chat/completions to the base URL and attempts /models discovery; a
manually configured model stays selectable if discovery is unavailable.
Both services document this general API setup and their current model IDs in their OpenAI compatibility guides. See the Z.ai guide and the Zhipu BigModel guide.
Notes
config.jsonis written with mode 0600; values inenvironmentare stored as plaintext in that file. Prefer keys scoped to the one engine.- A typo'd
driveror invalidconfignever breaks the app: the instance shows as unavailable with the reason, and the rest of the fleet loads.
GlinkBot documentation, reviewed for the 0.0.4 codebase. Public download availability can differ. Licenses and acknowledgments.