Subconscious

How to use goose with Subconscious

Let your AI do the setup. Paste this into Claude Code, Cursor, ChatGPT or any assistant.

Set up goose to use Subconscious as its model provider.

Subconscious is an inference API for agents. It serves open models through OpenAI- and Anthropic-compatible endpoints, billed per token.
- OpenAI-compatible base URL: https://api.subconscious.dev/v1
- Anthropic-compatible base URL: https://api.subconscious.dev
- Model: subconscious/glm-5.3-marathon
- API key: read it from the SUBCONSCIOUS_API_KEY environment variable. Never commit the key or paste it into project files. If it is not set, ask me to create one at https://platform.subconscious.dev.

Follow these steps. Run commands and edit files yourself. For any step in a settings screen, tell me exactly what to click and what to enter.

1. Install the goose CLI
The desktop app works too: add the provider under Settings, Models, Configure providers.
```bash
curl -fsSL https://github.com/aaif-goose/goose/releases/download/stable/download_cli.sh | bash
```

2. Create a Subconscious API key
Sign in at https://platform.subconscious.dev, create an API key, and export it so the tool can read it.
```bash
export SUBCONSCIOUS_API_KEY="your_key"
```

3. Add Subconscious as a custom provider
goose's docs give custom providers the full chat completions URL. context_limit tells goose when to compact; 5,000,000 matches what the Subconscious CLI uses.
```json
{
  "name": "subconscious",
  "engine": "openai",
  "display_name": "Subconscious",
  "api_key_env": "SUBCONSCIOUS_API_KEY",
  "base_url": "https://api.subconscious.dev/v1/chat/completions",
  "models": [{ "name": "subconscious/glm-5.3-marathon", "context_limit": 5000000 }],
  "supports_streaming": true,
  "requires_auth": true
}
```

4. Start a session
Pass the provider name for one session, or pick it as the default in goose configure.
```bash
goose session start --provider subconscious
```

Full guide: https://www.subconscious.dev/agents/agent-harnesses/goose.md

When you are done, confirm the tool is using subconscious/glm-5.3-marathon, then summarize what you changed.

To use goose with Subconscious, add a custom OpenAI-compatible provider: run goose configure and choose Add A Custom Provider, or create ~/.config/goose/custom_providers/subconscious.json pointing at Subconscious with the model subconscious/glm-5.3-marathon. Then start a session with --provider subconscious.

Get an API keyRead the API docs

Last verified against the goose docs on

Before you start

  • A Subconscious account and API key

goose docs · Source on GitHub

Set up goose

  1. Step 1: Install the goose CLI

    The desktop app works too: add the provider under Settings, Models, Configure providers.

    Terminal
    curl -fsSL https://github.com/aaif-goose/goose/releases/download/stable/download_cli.sh | bash

  2. Step 2: Create a Subconscious API key

    Sign in at https://platform.subconscious.dev, create an API key, and export it so the tool can read it.

    Terminal
    export SUBCONSCIOUS_API_KEY="your_key"

  3. Step 3: Add Subconscious as a custom provider

    goose's docs give custom providers the full chat completions URL. context_limit tells goose when to compact; 5,000,000 matches what the Subconscious CLI uses.

    ~/.config/goose/custom_providers/subconscious.json
    {
  "name": "subconscious",
  "engine": "openai",
  "display_name": "Subconscious",
  "api_key_env": "SUBCONSCIOUS_API_KEY",
  "base_url": "https://api.subconscious.dev/v1/chat/completions",
  "models": [{ "name": "subconscious/glm-5.3-marathon", "context_limit": 5000000 }],
  "supports_streaming": true,
  "requires_auth": true
}

  4. Step 4: Start a session

    Pass the provider name for one session, or pick it as the default in goose configure.

    Terminal
    goose session start --provider subconscious

Why run goose on Subconscious

Context that keeps going
The OrangeLine runtime compresses the parts of context that stopped mattering, on the GPU, while the run continues. That gives a 5M+ token context window with no stop-and-compact pause.
Long sessions stay fast
2x faster task completion on long tasks than standard open-model inference, especially past 200k tokens of context.
Lower cost on long tasks
50% to 80% lower cost on long tasks, because the runtime processes far fewer tokens. Cached input bills at a steep discount, and agentic coding sees cache hit rates above 95%.
Your data stays yours
Prompts, inputs and outputs are not recorded, and nothing you send is used to train a model.

Connection details

For any client that takes a custom OpenAI- or Anthropic-compatible endpoint.

OpenAI-compatible base URL
https://api.subconscious.dev/v1
Anthropic-compatible base URL
https://api.subconscious.dev
API key
From subc login or the Subconscious dashboard
Model
subconscious/glm-5.3-marathon
Multimodal, high-throughput model
subconscious/deepseek-v4.1-flash-marathon

Full reference in the Subconscious API docs.

Questions

Is goose still a Block project?
goose started at Block and now lives under the Agentic AI Foundation at the Linux Foundation, in the aaif-goose GitHub organization.
Which Subconscious model should I use with goose?
Start with subconscious/glm-5.3-marathon, an open frontier coding model built for long agent runs. subconscious/deepseek-v4.1-flash-marathon is a cheaper, high-throughput alternative that also takes image input. Use the full model ID, including the subconscious/ prefix.
Is goose on Subconscious OpenAI- or Anthropic-compatible?
This guide connects goose through the OpenAI-compatible Subconscious API. Subconscious serves both formats: OpenAI Chat Completions at https://api.subconscious.dev/v1 and Anthropic Messages at https://api.subconscious.dev.
How is goose usage on Subconscious billed?
Per token by default, with no commitment. Heavy users can switch to a monthly token plan: a fixed price for a large daily token allowance shared across your team.

More agent harnesses

See all