Memory that knows where it came from.
Durable, scoped, explainable memory for coding agents. Every returned fact keeps its boundary, history, and recall rationale attached.
Drag the network. Watch recall explain itself.
This is not a diagram. Move the stations, pan the field, inspect any node, or replay the complete route from prompt to returned context.
The agent receives the current answer with its repository boundary and recall rationale intact.
trace: available
ARRIVED
When a fact changes platforms, its old route stays visible.
The destination board is only the entrance.
Open the dashboard to inspect memories, timelines, recall rationale, graph relationships, audit events, workspaces, and system health.
Enter the seeded dashboardFree is the main line.
Direct answers. No fog.
Do I need an API key?Open +
Not for memory. Optional chat and synthesis use the LLM provider you select.
Where does my memory live?Open +
The local core stores memory in SQLite on your machine. You can inspect, back up, and operate it yourself.
Which agents work with Engraphis?Open +
Engraphis provides 29 MCP tools for supported coding-agent clients, plus a REST API and Python library.
Is the dashboard demo connected to a backend?Open +
No. The interactive website demo uses seeded sample data and runs only in the browser tab.