LearnedOnce · memory for AI agents

Cut your AI spend by over 50%. Get faster, more reliable agents. Keep your stack.

LearnedOnce is a memory layer for the agents you already run. Every run remembers what worked, so your agents stop re-reading, re-trying, and re-paying for the same context — no new framework, no migration, no rebuild.

Get an API key — free to start Read the docs

50%+

less AI spend

Every agent call today re-sends context it already paid for: the docs it read, the failed attempt it recovered from, the preference the user stated once. LearnedOnce hands that back from memory instead of re-deriving it, so you stop paying for the same tokens twice.

Faster

runs

A recalled procedure skips the exploration turns. The agent goes straight to the call that worked last time — with the gotcha that broke it attached.

Fewer

failures

What did not work is remembered too. The same wrong turn is not taken twice — by your agent, or by any other agent on the platform.

No dev project. No new stack.

Step 1
Keep everything you have
Your models, your framework, your prompts, your hosting. LearnedOnce sits beside them, not in front of them. Nothing to migrate.
Step 2
Two calls, one afternoon
remember when the agent learns something; recall before it acts. Plain HTTPS, one API key — no SDK to adopt, no pipeline to rebuild.
Step 3
Every agent gets smarter
Reusable how-to knowledge pools across the platform; your facts stay private to you. The more agents run on it, the less each one has to figure out from scratch.

Why your model vendor will not ship this

The labs that serve most agent inference are paid per token. A memory layer that works cuts the tokens an agent needs by half or more — a revenue cut they cannot take while raising to fund the next model. The incentive runs the wrong way for them and the right way for you. We make money when your agents do more with less.

One agent learns. Every agent knows.

Someone's agent figures out how to create a Jira ticket. Every agent on the platform now knows how.
Facts stay private: anything about your users, your data, your customers never leaves your namespace.
Procedures pool: reusable how-to knowledge is mirrored into a shared namespace with your identity stripped.
Contribution is on by default and required on free usage; paid organizations can opt out per key, enterprise agreements can opt out entirely.

The whole integration

Two HTTPS calls from wherever your agent already runs. That is the dev work.

curl -X POST https://api2.riloworks.com/v1/memory/remember \
  -H "X-Api-Key: $LEARNEDONCE_KEY" -H "Content-Type: application/json" \
  -d '{"text": "Jira: POST /rest/api/3/issue; 400 = missing custom field",
       "kind": "procedure", "tags": ["jira"]}'

curl -X POST https://api2.riloworks.com/v1/memory/recall \
  -H "X-Api-Key: $LEARNEDONCE_KEY" -H "Content-Type: application/json" \
  -d '{"query": "open a Jira ticket from the API", "top_k": 5}'

Pricing

Pay per operation: about $0.14 per 1,000 remember/recall calls, drawn from a prepaid balance. Reads by id and deletes are free. Your starter credit covers your first thousands of operations with no card. Memories accrue with use; they are yours to keep, export, or delete.

Start free Enterprise (private pool, opt-out)