OB-1 Owner's Manual
The multi-model coding agent for your terminal.
Why OB1?
OB1 is a terminal-based coding agent—like Claude Code, but with multi-model access and self-optimizing workflows. You bring your own API keys (or use ours), pick the best model for each task, and let OB1 handle the rest.
The short version: if you're locked into a single model provider, hitting context limits, or manually repeating the same workflows, OB1 fixes that.
- 01Multi-Model
- Claude, GPT, Gemini, Grok + 300 more.
/modelto switch. No vendor lock-in. - 02Self-Optimizing
- Learns from your sessions. Run
/inboxfor suggested skills and workflow improvements. - 03Session Forking
- Fork any conversation to explore alternatives. Rewind to any point. Share via link.
- 04CC Compatible
- Migrate from Claude Code with
/migrate. AGENTS.md, skills, and commands carry over.
Get Started
Install OB1 with a single command and you'll be up and running in minutes.
Using OB1
Essentials
Models & Execution
Sessions
Input & Navigation
Integrations
Tools & Subagents
Skills & Commands
Agents & Models
Quality & Extensions
Configuration
Agent Tasks
Delegate coding work to OB1 from the Console dashboard — describe the task, pick a repo, and the agent works in the background.
Agent Tasks is in beta. Interested in early access? Reach out to team@openblocklabs.com.
Pricing
Support
For help with OB1, join our Discord community or email team@openblocklabs.com.
To report bugs, use /bug in OB1—it automatically includes your session context.
Supported platforms: macOS, Linux, Windows (WSL recommended).