OmO
Oh My OpenAgentv4.7.5

Librarian

Multi-repo analysis and documentation lookup. Evidence-based answers, never opinions.

Librarian retrieves. Multi-repo analysis, doc lookup, OSS implementation examples — answers grounded in what the codebase and library docs actually say, not what the model "thinks." Speed-first, intentionally cheap.

Default model

FieldValue
Defaultopenai/gpt-5.4-mini-fast
StyleUtility — speed over depth

Runtime fallback chain

gpt-5.4-mini-fastopencode-go/qwen3.5-plusvercel/minimax-m2.7-highspeedopencode-go\|vercel/minimax-m2.7anthropic\|opencode\|vercel/claude-haiku-4-5openai\|opencode\|vercel/gpt-5.4-nano.

Tool restrictions

Read-only. Blocked: write, edit, task, call_omo_agent. Retrieval lane only.

When to invoke

  • Ask @librarian how this is implemented — why does the behavior keep changing?
  • Cross-repo pattern lookup ("how does FastAPI handle X?").
  • Documentation grounding before a decision.

What it doesn't do

  • Run on Opus — massive cost waste. Substitution rules in Agent-Model Matching explicitly call this out.
  • Synthesize opinions — retrieval, not orchestration.

Source Notes

Aligned with upstream docs/reference/features.md#core-agents and src/shared/model-requirements.ts.

On this page