AgentsModelsSkillsMemoryEvaluationsGuidesSubmit a resource

Memory Systems profile

Memori

Open-source memory engine for LLM apps and agents that need persistent context injection.

Memori is an open-source memory engine from GibsonAI for giving LLM applications and agents persistent memory, context injection, and configurable recall behavior.

Best for Developers adding memory to LLM applications
First test Run a repeated-session recall test and check what the system stores, retrieves, updates, scopes, and forgets.
Open repository Read docs View sources
Decision signals
Open sourceSelf-hostedAPI
Tags
memorycontext retrievalstate managementopen sourceself hostedself hosted aipersonal memory

Memory profile

What does Memori remember?

Memory profiles should explain what is remembered, how recall works, how memory is scoped, and how users can inspect, update, or delete durable context.

Memori is an open-source memory engine from GibsonAI for giving LLM applications and agents persistent memory, context injection, and configurable recall behavior.

Memori is an open memory-system resource to evaluate by what it stores, how recall works, how memory is scoped, and whether users or teams can inspect, correct, export, or delete durable context.

Fit check

Where this memory layer helps

Good fit if

  • Developers adding memory to LLM applications
  • Teams that want a Python-friendly memory engine
  • Builders comparing Mem0, Letta, and lighter memory libraries

Not a fit if

  • Users who want a fully managed consumer product with no setup work
  • Teams that cannot review the linked source, license, and operational requirements before adoption

Memory safety

What to inspect before storing user context

Memory object

User facts, task history, documents, graph entities, preferences, or workflow state.

You cannot evaluate memory without naming what is stored.
Recall behavior

Search, retrieval, ranking, graph traversal, summaries, or context injection.

Useful memory must surface the right context at the right time.
Control

Scope, deletion, export, consent, logs, and stale-memory correction.

Bad memory can be worse than no memory.

First test

How to evaluate it before committing

Run a repeated-session recall test and check what the system stores, retrieves, updates, scopes, and forgets.

Keep the first test small enough that you can inspect the source, understand the permissions, and compare the result with nearby OpenAgent resources.

Workflows

Best memory workflows to test

Conversational memory

Remember preferences and prior facts across user conversations.

Agent task context

Inject previous task details when an agent resumes work.

Memory library evaluation

Compare a focused memory engine against heavier agent platforms.

Compare

Compare by memory object and control

Memori is a lighter memory layer vs full agent platforms

Use Memori when you want memory inside an existing app rather than adopting a whole agent runtime.

Resource Category License Stars
Cognee Memory Systems Apache-2.0 n/a
Graphiti Memory Systems Apache-2.0 n/a
Letta Memory Systems Apache-2.0 n/a

FAQ

Memory adoption questions

What should I check before using Memori?

Test Memori with repeated sessions. Add facts, update them, ask for recall, inspect retrieval behavior, and verify deletion or scoping controls before storing sensitive user or project memory.

Is Memori open source?

Memori is listed with Apache-2.0 based on the official source links in this profile. Re-check the repository, model card, or docs before production use.

Who should evaluate Memori?

Memori is most worth evaluating for developers adding memory to LLM applications.

Related

More memory systems to compare