KnowledgeMay 13, 2026·2 min read

Memori — Agent-Native Memory Infrastructure

Memori is an Apache-2.0 memory layer that captures what agents do (not just say) and plugs into existing stacks via Python/Node SDKs and a cloud option.

AI Open Source
AI Open Source · Community
Agent ready

Ready-to-run agent install

This asset can be installed after the agent chooses its runtime, checks the plan, and runs the matching command.

Native · 96/100Policy: allow
Agent surface
Any MCP/CLI agent
Kind
Knowledge
Install
Single
Trust
Trust: Established
Entrypoint
Asset
Direct install command
npx -y tokrepo@latest install 7fcb5dcd-8666-5767-a3af-208f83343287 --target codex

Run after dry-run confirms the install plan.

Intro

Memori is an Apache-2.0 memory layer that captures what agents do (not just say) and plugs into existing stacks via Python/Node SDKs and a cloud option.

Best for: teams building long-running agents that need durable memory and audit-friendly traces

Works with: Python and Node runtimes, existing agent frameworks, self-hosted or cloud storage backends

Setup time: 8-15 minutes

Key facts (verified)

  • GitHub: 14399 stars · 2050 forks · pushed 2026-05-12.
  • License: Apache-2.0 · owner avatar + repo URL verified via GitHub API.
  • README-verified entrypoint: pip install memori.

Main

  • Treat memory as infrastructure: log durable actions and outcomes, not just chat transcripts, so you can replay decisions later.

  • Start by capturing one narrow signal (tool calls, file writes, or task outcomes), then expand once you can query and summarize it reliably.

  • When debugging agents, memory traces help you answer “what happened” with timestamps and artifacts instead of vibes.

Source-backed notes

  • README tagline emphasizes memory from what agents do, not just what they say.
  • README links both PyPI (memori) and npm (@memorilabs/memori) packages.
  • Repo license file is Apache License 2.0.

FAQ

  • Is it framework-specific?: No—README describes it as framework and datastore agnostic.
  • Is there a hosted option?: Yes—README links to Memori Cloud documentation.
  • Do I have to store private data?: No. You control what events are captured and where they are stored.
🙏

Source & Thanks

Source: https://github.com/MemoriLabs/Memori > License: Apache-2.0 > GitHub stars: 14399 · forks: 2050

Discussion

Sign in to join the discussion.
No comments yet. Be the first to share your thoughts.

Related Assets

Awesome Agent Memory — Long-Term Context Index

Awesome Agent Memory curates systems, benchmarks, and papers on long-term context for LLMs/MLLMs—use it to compare approaches and pick tools to try.

Knowledge
AI Open Source

Memorix — Cross-Agent Memory Control Plane

AVIDS2/memorix is a local-first cross-agent memory layer (MCP + CLI/TUI); verified 443★ with stdio `memorix serve` and an HTTP dashboard mode.

Knowledge
Agent Toolkit

Awesome-Memory-for-Agents — Paper List + Taxonomy

Awesome-Memory-for-Agents is a paper list and taxonomy for agent memory, splitting short vs long-term memory and mapping to 3 application scenarios.

Knowledge
AI Open Source

Statewave — Memory Runtime for AI Agents (API + SDKs)

Statewave is a self-hostable memory runtime: ingest episodes, compile memories, do semantic search, and build token-bounded context bundles via REST.

Knowledge
AI Open Source
◈Home🔍Search👤Me