| TL;DR: Memorable records the tool calls an agent made to run a task, reuses that workflow on similar tasks instead of re-deriving through reasoning from scratch. –60% tool calls, –40% latency.

https://youtu.be/3m9I1zHSMPk

Memorable turns agent reasoning into a graph search problem.

1. We capture your agents' traces and store them as a lightweight graph.
2. When a similar prompt arrives, we extrapolate a workflow with a graph search.
3. We inject a short pointer (50 to 100 tokens) into the prompt.

So the agent runs deterministically instead of re-deriving a plan every. single. time.

Forget tokenmaxxing.

We're graph-first and anti-text so you SAVE time, tokens, and money.

• –60% tool calls and –40% latency on QM's benchmarks
• –20% turns in Gbrain bench, ran GStack’s /investigate skill with –98% tokens

Do your agents need procedural memory?

• Memorable is for anyone running agents that do the same work more than once.
• We've built for coding, support, ops, research, company brain, and browser/computer-use agents.
• If you find yourself repeatedly having to correct or guide your agents, they need procedural memory!

Imagine a world where your agents don’t reason.

• Most agent memory layers store facts using text: preferences, docs, past chats, while Memorable stores procedures: the steps an agent takes to achieve an outcome.
• We are able to encode this graphically using nodes and edges, making it incredibly agent-friendly and token-efficient, allowing most agents to skip the preliminary planning step altogether.

Try Memorable, your agent will onboard you!

npx memorable-cli
curl -fsSL https://memorable.sh/install.sh | sh

• Compatible with Claude Code, Codex, Cursor, and Claude Cowork

• You can try it out live in QM and Gbrain (thanks @Joshua France &

  @Garry Tan!)

• Procedures live encrypted in your own cloud, or run entirely local.

Memorable Team

• Nikhil Krishnaswamy [Stanford CS]: created an iOS MCP interning at AGI Inc, research published in COLM and IEEE
• Advaiyt Sane [Carnegie Mellon CS]: built dev tools at Nvidia that create 50k AV tests a month

We are looking for design partners!

• Would love to chat with teams deploying agents at volume (high tool-call or token spend, repeated workflows) willing to pilot as design partners.
• Open to custom harness and framework integrations for your interesting use cases

Email info@memorable.sh and we'll spend a day solving your memory problems with you, plus:

• LIFETIME of Memorable Pro FREE
• Reach out to us about anything agent memory-related, whether or not you use Memorable :)

and grab a slot: cal.com/team/memorable/30

website | docs | try memorable

Let's build something Memorable!