Marrow
Sign in Create account

Agent memory for every AI.

Marrow Core keeps the context your apps and agents need as durable memory. Conversations, documents, tool calls, traces, feedback, and application records become connected facts, preferences, decisions, relationships, timing, and corrections. Provenance and time stay attached so each workflow can retrieve the relevant slice and show what it used.

Memory model.

Marrow Core stores memory as three connected parts. Records preserve conversations, documents, tool calls, traces, feedback, and application records with provenance and time. Graph state connects facts, preferences, decisions, entities, relationships, timing, boundaries, and corrections. Marrow Core returns query results as context packets for use in a specific app, agent, or workflow.

When an app or agent needs context, Marrow Core can make the relevant documents, records, conversations, memories, and workflow activity available from your server. The hosted path accepts a public URL or supported file, processes it, and returns the useful context through /v1/query with status, supporting excerpts, citations, warnings, and an insufficient-evidence state.

Records

Conversations, documents, tool calls, traces, feedback, and application records, preserved with provenance and time.

Graph state

Facts, preferences, decisions, entities, relationships, timing, boundaries, and corrections connected in the knowledge graph.

Context packets

The relevant slice for the agent or app, scoped to the task and recipient.

Memory benchmarks

Marrow reaches 93.8% on LongMemEval-S, ahead of full-context and leading memory systems in published results. On LoCoMo, Marrow reaches 89.1% across multi-session recall and reasoning, shown with published results from the same systems.

LongMemEval-S

93.8%

Long-term memory accuracy

Published LongMemEval-S results Benchmark Comparison source

LongMemEval-S

Accuracy
0 100
  1. Marrow 93.8%
  2. Full context 92%
  3. Honcho 90.4%
  4. Supermemory 84.6%
  5. Zep 71.2%