multi-model-research
Multi-Model Research Agent
Implements Karpathy's LLM Council pattern for superior research through parallel queries, peer review, and chairman synthesis.
Architecture
Geoffrey/Claude (Native Council Member):
- Routes simple vs complex queries
- Calls external API orchestrator (
research.py) - Provides my own research response
- Conducts peer review phase
- Requests GPT-5.1 synthesis (chairman)
- Saves final report to Obsidian
Python External API Orchestrator:
- Fetches responses from GPT-5.1, Gemini 3.0 Pro, Perplexity Sonar, Grok 4.1
- Returns JSON with all external responses
- I handle all orchestration and synthesis
More from krishagel/geoffrey
morning-briefing
Generate comprehensive morning briefing with calendar, tasks, tickets, news, and weather. Saves to Obsidian, sends email with audio podcast attached.
144google-workspace
Unified Google Workspace integration for managing email, calendar, files, and communication across multiple accounts
32local-tts
Local text-to-speech using MLX and Kokoro model
25omnifocus-manager
Manage OmniFocus tasks, projects, and inbox with proper tagging and organization
24personal-strategic-planning
Annual strategic review and goal-setting interview for personal life/work domains with quarterly progress check-ins
22browser-control
Full browser control for authenticated web interactions using Playwright scripts
21