AgentsModelsSkillsMemoryBotsStack FinderEvaluationsGuidesSubmit a resource
Memory Systems

Memori

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

Visit official site Open repository
Apache-2.0 License
Open sourceSelf-hostedAPI
Memori Apache-2.0 License gibsonai.github.io verified 2026-04-19
About

Memori overview

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

✦

Focused memory engine

Memori centers on memory behavior rather than broad workflow orchestration.

A focused engine is easier to embed into existing applications.
✦

Persistent context injection

The docs describe memory concepts for injecting relevant context into interactions.

Agents become more useful when recall happens at the right moment.
✦

Apache-2.0 open-source release

Public materials describe Memori as Apache-2.0 open source.

Permissive licensing helps teams experiment without early legal friction.
Use cases

When to use Memori

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

How it compares

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.

FAQ

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.

Tags

Capabilities

memorycontext retrievalstate managementopen sourceself hostedself hosted aipersonal memory
Decision brief

Should you use Memori?

JSON
Best for
  • Developers adding memory to LLM applications
  • Teams that want a Python-friendly memory engine
  • Builders comparing Mem0, Letta, and lighter memory libraries
Not for
  • 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
Trust and freshness
  • Verified 2026-04-19
  • License: Apache-2.0
  • Repo: GibsonAI/memori
  • Open-source signal
Deployment

self hosted, cloud

Permission surface

memory, external services

Decision signals

Self-hostable, API

Agent packet

Structured decision data for Memori

This packet is the compact machine-readable view agents should use before following source links or taking action.

Full JSON Agent packet Markdown brief
Capabilities

memory, context retrieval, state management

Constraints

open source, self hosted

Deployment

self hosted, cloud

Permission surface

memory, external services

Recommended workflows

Memory or RAG workflow

Overview

What Memori does

What it is

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.

Why it matters

Memori matters because many agent products need a practical memory engine before they need a full agent framework. It gives teams a focused way to add durable context to conversations and workflows.

How to evaluate it

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.

Facts

Known metadata and operating surface

These fields are separated from editorial interpretation so agents can reason over facts and missing checks.

Resource type memory system
Category Memory Systems
Maturity active
Difficulty Unknown
License Apache-2.0
Pricing open source
Verified 2026-04-19
Source confidence high
Risk level moderate
Fit matrix

Where Memori fits in an agent stack

strong

Memory or RAG workflow

Memori has multiple signals for memory or rag workflow, including matching tags, capabilities, category, or positioning.

  • Create, update, retrieve, correct, and delete memory or retrieval objects with real data.
  • Confirm official docs, current maintenance, license, and runtime constraints before production use.
partial

Coding agent workflow

Memori has at least one signal for coding agent workflow, but should be checked against a real task before adoption.

  • Run a small repository change and inspect the diff, tests, and rollback path.
  • Confirm official docs, current maintenance, license, and runtime constraints before production use.
partial

Connector or protocol layer

Memori has at least one signal for connector or protocol layer, but should be checked against a real task before adoption.

  • Connect one low-risk service, then inspect schemas, auth scope, errors, and logs.
  • Confirm official docs, current maintenance, license, and runtime constraints before production use.
partial

Evaluation and observability

Memori has at least one signal for evaluation and observability, but should be checked against a real task before adoption.

  • Add one repeatable test case and confirm results can run again in review or CI.
  • Confirm official docs, current maintenance, license, and runtime constraints before production use.
partial

Local or private AI stack

Memori has at least one signal for local or private ai stack, but should be checked against a real task before adoption.

  • Verify hardware requirements, data path, storage, and whether all calls stay in your environment.
  • Confirm official docs, current maintenance, license, and runtime constraints before production use.
weak

Browser automation

Memori is not primarily positioned for browser automation in the current metadata.

  • Run one non-sensitive website task and inspect clicks, waits, retries, and changed URLs.
  • Confirm official docs, current maintenance, license, and runtime constraints before production use.
Inputs and outputs

What an agent should inspect

Likely inputs

  • Repositories, files, issues, terminal output, and test results
  • Documents, user facts, entities, context, or retrieval queries
  • Tool schemas, API requests, service resources, and auth scopes
  • Official setup instructions and a small real workflow

Likely outputs

  • Diffs, commits, explanations, test results, or review notes
  • Retrieved context, memory updates, graph relations, or citations
  • Scores, traces, regression results, dashboards, or failure cases
  • A decision on whether this resource fits the target workflow
Evidence

Sources, claims, and missing checks

Claims are marked separately from source links so future crawlers and reviewers can update them without rewriting the page.

GitHub github

Repository source for code, license, issues, releases, and implementation details.

 Homepage homepage

Official or project-controlled source for this resource profile.

 Docs docs

Documentation source for setup, API shape, and operational behavior.
verified

Memori is listed as open source.

License metadata: Apache-2.0
verified

Memori has a recorded GitHub repository: GibsonAI/memori.

Resource facts and GitHub source link.
inferred

Memori supports these recorded deployment modes: self hosted, cloud.

OpenAgent decision signal metadata.
inferred

Memori is tagged with memory, context retrieval, state management capabilities.

OpenAgent capability taxonomy.
Missing checks
  • Repository freshness has not been recorded.
Next action

How to start evaluating Memori

Inspect repository

Check license, recent activity, issues, examples, and security-sensitive code paths.

Open source

Open Homepage

Start from the official source before adopting third-party instructions.

Open source

Read setup docs

Use docs as the source of truth for installation and supported interfaces.

Open source

Clone Memori

Use the official docs to confirm the current Python package and configuration before production use.

git clone https://github.com/GibsonAI/memori.git
Compare

Alternatives and nearby resources

Use related resources to compare category fit, license, deployment model, and first-workflow behavior.

Mnemo Cortex

Open-source memory coprocessor for AI agents with persistent recall, semantic search, and crash-safe capture.

Memory Systems OpenLore

Persistent architectural memory for AI coding agents using queryable codebase knowledge graphs and MCP tools.

Memory Systems AgentMemory

Persistent memory for AI coding agents, with benchmarks and local-first workflows.

Memory Systems
FAQ

Common questions about Memori

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.