Skip to main content

​
Memorose

Memorose turns raw agent traffic into memory that compounds. It ingests events, consolidates facts and procedures, previews semantic updates or forgetting before execution, projects shared organizational knowledge, tracks goals and tasks, and keeps the whole runtime operable through a real dashboard and Raft-backed deployment model.

Start with Quickstart

Log in, create a stream, ingest an event, retrieve memory.

Read the API

Inspect the stream-first HTTP surface.

Understand the Model

L0-L3 hierarchy, domains, and runtime pipeline.

​
Runtime Map

1

L0 — Raw Events

Text, image, audio, video, and JSON enter as stream-scoped events.
2

L1 — Stable Memory

Facts, preferences, procedural traces, and grounded summaries.
3

L2 — Insights

Themes, graph-linked clusters, and shared organization knowledge.
4

L3 — Goals and Tasks

Milestones, dependencies, progress, execution state, and sedimented outcomes.

​
API Snapshot

POST /v1/users/:uid/streams/:sid/retrieve
Request fields: query, graph_depth, org_id, agent_id, image / audio / video
This docs set follows the real server model implemented in memorose-server, not the older CRUD-style memory API.

​
Three Core Surfaces

Memory Runtime

Streams, layered memory, hybrid retrieval, semantic update flows, and active forgetting.

Execution Layer

Task trees, ready queues, milestones, dependencies, and result sedimentation.

Operations Surface

Dashboard auth, cluster control, organization knowledge, and runtime inspection.

​
Stream-First HTTP Surface

The current API is scoped by user_id and stream_id, then connected to tasks, graph edges, organization knowledge, and cluster operations.
  • /events for raw ingest
  • /retrieve for hybrid recall
  • /memories/semantic/preview and /memories/semantic/execute for semantic update and forgetting workflows
  • /tasks/tree and /tasks/ready for L3 execution state
  • /organizations/:org_id/knowledge for shared knowledge

​
Follow the Runtime Flow

1

Ingest events into a stream

Everything starts as L0 input attached to a concrete user and stream timeline.
2

Consolidate into durable memory

Facts and procedural traces become stable memory units instead of remaining raw traffic forever.
3

Retrieve with more than one signal

Hybrid retrieval combines vector search, text search, graph depth, time filters, and shared organization knowledge.
4

Review memory changes and track execution

Semantic update / forget previews plus L3 goals, milestones, dependencies, and completion summaries turn memory into an execution surface rather than a passive archive.

​
Choose By Job

Build

I need to wire ingest and retrieval into an agent.Start with Quickstart, REST API, and Hybrid Search.

Operate

I need to inspect memory, tasks, knowledge, and cluster health.Go through Dashboard, Organization Knowledge, and Distributed Deployment.

Reason

I need the model before I design wrappers or product behavior.Read Architecture, Memory Hierarchy, Memory Domains, and Forgetting Strategies.

​
Start Here

Quickstart

Log in, create a stream, ingest an event, retrieve memory. Use the real v1 routes with the current auth and response model.

Architecture

Understand L0-L3, domains, and the runtime pipeline. Read the model before you build wrappers around the wrong abstraction.

Tasks

See how goals and execution state are exposed in L3. Task trees and ready queues are part of the product, not an internal detail.

Organization Knowledge

Inspect the shared memory layer for one org_id. Use it when personal memory needs to evolve into reusable organizational knowledge.