Long-running agents deserve better inference.

Use agent harnesses with Subconscious

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

Set up the agent harness I use to run on 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.

Work out which of these tools I am using: check my project and installed tools, or ask me. Then fetch its setup guide and follow it. Each guide is Markdown and lists every command and config file.

Agent harnesses:
- Hermes Agent: https://www.subconscious.dev/integrations/agent-harnesses/hermes.md
- OpenClaw: https://www.subconscious.dev/integrations/agent-harnesses/openclaw.md
- goose: https://www.subconscious.dev/integrations/agent-harnesses/goose.md
- Nori: https://www.subconscious.dev/integrations/agent-harnesses/nori.md
- Coder: https://www.subconscious.dev/integrations/agent-harnesses/coder.md
- Kodus: https://www.subconscious.dev/integrations/agent-harnesses/kodus.md

If you cannot fetch URLs, point the tool at the OpenAI-compatible base URL with the model above, or ask me for the guide.

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

Point an agent harness, from a self-hosted personal assistant to a managed cloud session runner, at Subconscious for long-running sessions that stay fast and cheap as context grows.

Nori

Runs coding agents in isolated cloud sessions from Slack, the web, schedules or webhooks.

Setup guide