> ## Documentation Index
> Fetch the complete documentation index at: https://docs.graphify.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Agent memory
> Explore remembered facts, their entities, and the source evidence behind them.
**Memory** makes recorded agent context inspectable in [Graphify Cloud](https://app.graphify.com). Facts are organized around the entities they describe, with source and grounding information alongside them.
## Explore remembered context
1. Open **Memory** and select a repository.
2. Search for a fact or entity, or choose an entity from the list.
3. Read its remembered facts and inspect the available source references, provenance, and graph anchors.
Use memory to recover context from earlier agent work, investigate why a fact was recorded, and connect it to the current code graph. Coverage and grounding metrics help explain how much recorded context has a corresponding graph anchor.
## Grounding and provenance
A remembered statement and an extracted code relationship are different kinds of evidence. Check where a fact came from and whether it is linked to a graph node. Source references and provenance are more useful than treating every stored fact as equally authoritative.
For current implementation details, follow the graph anchor or open [Graphs](/platform/graphs). Read [provenance labels](/concepts/provenance) when evaluating an inferred connection.
## Connect an agent
Use **Connect an agent**, or open the workspace's **MCP** page, to connect your coding assistant. See [Connect agents and integrations](/platform/connections).
An empty repository has no recorded memories yet. Connect an agent and use the workspace's memory capabilities before expecting facts to appear.
## Memory and learning
Memory stores contextual facts around entities. [Learning](/platform/learning) uses pull request feedback to adjust advisory reviews. Both are Cloud features, with separate purposes and controls.