autoresearchclaw-integration-architecture-decisions
Confirmed integration design for AutoResearchClaw into Oracle: (1) Dedicated researchclaw container on oracle-network, NOT inside oracle-hermes, to isolate LLM-generated experiment code execution. (2) MCP Server invocation pattern (~10 tools) chosen over CLI or ACP because it fits the oracle-* native tooling architecture and returns structured JSON tool responses. (3) Hybrid LLM config: Opus 4.6 for the 8 critical reasoning stages (hypothesis gen, paper writing, peer review), GPT-4o-mini or Gemini Flash for the 15 routine stages — AutoResearchClaw natively supports primary+fallback model config.
Related
- 2026-04-04-oracle-001-self-architecture-analysis
- oracle
- docker
- autoresearchclaw-integrated-as-mcp-server-not-cli-or-acp
- hermes
- hybrid-opus-haiku-for-researchclaw-stay-anthropic
- oracle-researchclaw-mcp-server-over-cli-or-acp
- researchclaw-hybrid-llm-opus-haiku-stage-split
- researchclaw-gate-stages-need-dedicated-mcp-tools
- researchclaw-integration-approved-design-decisions
- haiku-45-preferred-over-gpt4o-mini-for-routine-stages-anthro
- autoresearchclaw-hybrid-llm-routing-opus-haiku
- researchclaw-integration-architecture-decisions
- oracle-researchclaw-integration-architecture-decisions
- hybrid-llm-model-pattern-opus-haiku-pipeline-stages
- researchclaw-integration-decisions-container-mcp-hybrid-llm