mirror of
https://github.com/trustgraph-ai/trustgraph.git
synced 2026-04-25 00:16:23 +02:00
849987f0e6
Introduce an agent orchestrator service that supports three execution patterns (ReAct, plan-then-execute, supervisor) with LLM-based meta-routing to select the appropriate pattern and task type per request. Update the agent schema to support orchestration fields (correlation, sub-agents, plan steps) and remove legacy response fields (answer, thought, observation). |
||
|---|---|---|
| .. | ||
| trustgraph | ||
| pyproject.toml | ||
| README.md | ||