> ## Documentation Index
> Fetch the complete documentation index at: https://docs.memorylake.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Memories
> How MemoryLake extracts, stores, retrieves, and maintains long-term memories — traces, conflicts, and management
## Overview
Memories are the heart of MemoryLake: structured, durable facts distilled from your conversations and documents. Unlike a chat log (noisy, unbounded) or a document chunk (raw text), a memory is an *extracted* statement worth keeping — deduplicated, searchable, traceable to its source, and checked for consistency.
## Where Memories Come From
Playground chats and agent sessions are analyzed automatically — durable facts are extracted, merged with what's already known, and stored. Transcripts stay transcripts; facts become memories.
Uploaded files are parsed and indexed; key content becomes retrievable memory alongside conversational facts.
Store a memory deliberately — via the API (`add memory`), agent tools (`memory_store`), or by telling the assistant "remember this".
Connected agents (OpenClaw and friends) report conversation turns in the background; the server decides what to store, update, or merge.
## What Makes a Memory Trustworthy
### Source Traces
Every memory keeps a trace back to its origin — the conversation turn or document it was extracted from. Open any memory in the console and check its **Source Trace** tab, or fetch it via the [trace API](/features/memorylake/api-reference/memories/get-memory-trace). When an assistant asserts something, you can always answer *"how do you know that?"*
### Conflict Detection
When a new memory contradicts an existing one — a moved deadline, a changed policy, a corrected fact — MemoryLake doesn't silently keep both or overwrite blindly. It raises a **conflict**:
1. The conflicting pair appears in the project's **Conflicts** tab
2. A reviewer (anyone with the resolve permission) picks what's true
3. Memory stays current, and the resolution is deliberate rather than accidental
Conflicts are also exposed via [API](/features/memorylake/api-reference/memories/list-memory-conflicts), and agent tools surface unresolved conflicts alongside retrieval results so assistants can flag uncertainty instead of asserting stale facts.
### Deduplication & Merging
Repeating yourself doesn't create ten copies of the same fact — extraction merges new information into existing memories where they overlap, and updates them when details change.
## Retrieving Memories
* **Console**: browse and search in the **Memories** page (workspace-wide) or a project's Memories tab — including a word-frequency visualization for a quick sense of what a project knows
* **Semantic search**: hybrid keyword + embedding retrieval, scoped to a project or workspace — the same engine behind the Playground, agent tools, and the [search API](/features/memorylake/api-reference/memories/search-memories)
* **Automatic recall**: connected assistants retrieve relevant memories before answering — you don't query anything by hand
## Managing Memories
### Browse & Inspect
The Memories views support search, filtering, pagination, and bulk selection. Click any memory for details: full content, metadata, and source trace.
### Edit
Open a memory and edit its content when a fact needs refinement. Edits take effect immediately in future retrieval.
### Forget (Delete)
Forgetting a memory is permanent — it is removed from all future retrieval for every connected assistant and API client.
Delete from the memory's action menu (or the [forget API](/features/memorylake/api-reference/memories/forget-memory)). This is also your "right to be forgotten" mechanism when building user-facing products.
## Individual and Organizational Memory
The same machinery serves two different kinds of knowledge:
| | Individual memory | Organizational memory |
| ------------- | ------------------------------------------ | ------------------------------------------------- |
| Belongs to | A person (across all their tools) | A team workspace |
| Examples | Preferences, personal facts, working style | Policies, decisions, domain facts, client history |
| Governance | Private to you | Roles + fine-grained permissions per action |
| Typical worry | "Will my tools remember me?" | "Will knowledge survive people leaving?" |
Both flow through extraction → trace → conflict-checking → retrieval; the difference is scope and governance. See the [Personal AI Memory](/scenarios/personal-ai-memory) and [Team Knowledge Base](/scenarios/team-knowledge-base) scenarios.
## Working with Memories Programmatically
```bash theme={null}
# Feed a conversation — facts are extracted from the messages you append
POST /api/v3/workspaces/{workspaceId}/memories/conversations
POST /api/v3/conversations/{conversationId}/messages
# Import documents into a project
POST /api/v3/workspaces/{workspaceId}/projects/{projectId}/memories/documents
# Search across documents and facts in one call
POST /api/v3/workspaces/{workspaceId}/memories/search
# Browse and manage extracted facts
GET /api/v3/workspaces/{workspaceId}/projects/{projectId}/memories/facts
POST /api/v3/workspaces/{workspaceId}/projects/{projectId}/memories/facts/{factId}/forget
# List / resolve conflicts
GET /api/v3/workspaces/{workspaceId}/projects/{projectId}/memories/conflicts
POST /api/v3/workspaces/{workspaceId}/projects/{projectId}/memories/conflicts/{conflictId}/resolve
```
All paths are relative to `https://app.memorylake.ai/openapi/memorylake`. Start with [Core Memory Operations](/features/memorylake/api-reference/core-memory/overview) for the end-to-end flow.
Earlier project-scoped `api/v1` and `api/v2` memory endpoints remain available for existing integrations and are documented under **Deprecated** in the API reference. New integrations should use the v3 paths above.
## Next Steps
Get better memories out of conversations, documents, and agents
Bring memory recall into your agents and apps
Manage memories programmatically