OmO
Oh My OpenAgentv4.7.5

Agent-Model Matching

Each agent's prompt is tuned for a model family. Where to swap models safely, where not to, and the substitution cheat sheet.

OmO assigns each agent a model that matches its working style. A model isn't only "smarter" or "dumber" — it interprets prompts differently. Sisyphus's ~1,100-line orchestration prompt and Hephaestus's principle-driven deep-work prompt are not interchangeable; the family matters.

This page is the substitution reference: when the native model isn't available, which models keep the agent's character, and which ones quietly break it.

Two prompt styles

StyleBest fitWhat it likes
Mechanics-drivenClaude family, Kimi K2.5/2.6, GLM 5/5.1Long detailed checklists, templates, step-by-step procedures. More rules = more compliance.
Principle-drivenGPT-5.4 and GPT-5.5Concise principles, XML structure, explicit decision criteria. More rules = more contradiction surface = drift.

Agents with dual prompts (Prometheus, Atlas) auto-detect the model family at runtime via isGptModel() and switch prompts. The rest expect one family.

Family alternatives

Claude family — communicative, instruction-following

Used by: Sisyphus, Atlas, Sisyphus-Junior, Metis (Claude path), Prometheus (Claude path), unspecified-low, unspecified-high.

PriorityModelProviders
1claude-opus-4-7 (max)anthropic, github-copilot, opencode, vercel
2claude-sonnet-4-6same
3kimi-k2.5 / kimi-k2.6 — recommended alternativeopencode-go, kimi-for-coding, moonshotai, opencode, vercel
4glm-5 / glm-5.1 — acceptable alternativeopencode-go, zai-coding-plan, opencode, vercel
5big-pickle (GLM 4.6)opencode

Kimi K2.5/2.6 outperforms GLM under Sisyphus's nested todo+delegation prompts. Use Kimi whenever both are available.

GPT family — principle-driven, autonomous

Used by: Hephaestus, Oracle, Momus, deep, ultrabrain, quick, Prometheus (GPT path), Atlas (GPT path).

PriorityModelProviders
1gpt-5.5 / gpt-5.4 (pro / xhigh / high / medium)openai, github-copilot, opencode, vercel
2gpt-5.3-codexsame
3DeepSeek (deepseek-v3.2, deepseek-chat-v3.1) — limited alternativeopenrouter/deepseek (add via fallback_models)
4MiniMax — strongly discouraged outside utility chainsopencode-go, opencode, openrouter/minimax

DeepSeek keeps GPT's autonomous exploration character. MiniMax loses coherence on multi-step deep work — use it only for grep-style utility agents (Explore, Librarian, quick), never for Hephaestus/Oracle.

Gemini family — visual, different reasoning style

Used by: visual-engineering, artistry, Oracle (visual fallback), Multimodal-Looker.

PriorityModelProviders
1gemini-3.1-pro (high)google, github-copilot, opencode, vercel
2gemini-3-flashsame
3Qwen (qwen3.6-plus, qwen3.5-plus) — alternativeopencode-go, openrouter/qwen

GLM and Kimi are not Gemini substitutes for visual work. Use Qwen.

Substitution cheat sheet

If you lose…Swap to (in order)Avoid
Claude Opus / SonnetKimi K2.5/K2.6 → GLM 5 → Big PickleOlder GPT models
GPT-5.4 / 5.5GPT-5.3 Codex → DeepSeek v3.2MiniMax (except utility work)
Gemini 3.1 ProQwen 3.6-plus / 3.5-plusClaude / Kimi (wrong reasoning style)
Grok Code Fast 1 (Explore)GPT-5.4 Mini Fast → MiniMax M2.7 Highspeed → Claude HaikuOpus (cost waste)

Safe vs dangerous overrides

Safe — same personality type:

  • Sisyphus: Opus → Sonnet, Kimi K2.5/2.6, GLM 5.
  • Prometheus: Opus → GPT-5.5 (auto-switches to the GPT prompt).
  • Atlas: Claude Sonnet 4.6 → Kimi K2.5, GPT-5.5 (auto-switches).

Dangerous — personality mismatch:

  • Sisyphus → older GPT: still a bad fit. Only GPT-5.4 and GPT-5.5 have dedicated Sisyphus prompt paths.
  • Hephaestus → Claude: built for Codex-style autonomy; Claude does not replicate it.
  • Hephaestus → MiniMax: loses coherence on multi-step deep work. Never.
  • Oracle → MiniMax: same — Oracle needs sustained reasoning.
  • Explore / Librarian → Opus: massive cost waste. They need speed, not intelligence.
  • visual-engineering → Kimi / GLM: wrong reasoning style. Use Qwen if Gemini is unavailable.

How the runtime resolves a model

The pipeline (from src/shared/model-resolution-pipeline.ts):

  1. Override — UI-selected or explicit user config.
  2. Category default — when the agent has a category set.
  3. User fallback_models — your configured chain, tried before the hardcoded one.
  4. Provider fallback chain — built-in from src/shared/model-requirements.ts.
  5. System default — OpenCode's configured default.

Variants and reasoningEffort are normalized to model-supported values, so cross-provider overrides degrade gracefully instead of failing hard.

Run bunx oh-my-openagent doctor --verbose to see effective model resolution for your config, and bunx oh-my-openagent refresh-model-capabilities to refresh the local models.dev cache.

OpenCode Go + OpenAI Plus/Pro — best $/coverage

~$30/month. Beats direct Anthropic + OpenAI + Google (~$60+/month) on both cost and coverage.

  • Hephaestus runs on GPT-5.5 (ChatGPT Plus path).
  • Sisyphus/Atlas run on Kimi K2.6 (OpenCode Go path) — Claude-like with no Anthropic subscription needed.
  • visual-engineering falls back to Qwen 3.6-plus when Gemini isn't connected.

All-native — highest quality

Anthropic + OpenAI + Google. Default Sisyphus on Opus, Hephaestus on GPT-5.5, visual-engineering on Gemini 3.1 Pro. Highest cost.

OpenCode Go only — budget

Kimi K2.6 + GLM-5.1 + Qwen + MiniMax. Cheapest full-stack path. Hephaestus does not activate (it requires GPT). Trade-off: no autonomous deep work.

Source Notes

Mirrors upstream docs/guide/agent-model-matching.md. Authoritative fallback chains live in src/shared/model-requirements.ts. The dispatch logic that picks a category over a model is in Orchestration.

On this page