Modules
In-flight conversation buffer keyed by session_id.
Port for talking to a Gralkor backend from Elixir.
In-memory twin of Gralkor.Client for tests.
Production Gralkor.Client implementation. In-process — no HTTP — talks
to graphiti via Gralkor.GraphitiPool (Pythonx-backed) and to the LLM via
req_llm (Elixir-side, used by Gralkor.Distill and Gralkor.Interpret).
Configuration for the embedded Gralkor runtime.
Render a list of conversation turns into an episode body suitable for ingesting into the knowledge graph.
Format graphiti edge data into the canonical fact strings the LLM sees.
Per-group Graphiti instance cache, plus the gateway for graphiti operations.
Filter retrieved graph facts down to those relevant to the conversation, using the configured LLM.
Canonical message shape that Gralkor expects at its port boundary.
PythonX runtime owner for the embedded Gralkor stack.
Orchestrate one recall call: search the graph, interpret the hits against
the buffered conversation, wrap the result in a <gralkor-memory> block.