Memorable

Memorable launched a memory layer that stores how an agent completed a task and replays the procedure when a similar task returns, with storage kept on the user's side and consent enforced fail-closed. The tool offers four onboarding routes — an npx memorable-cli install for coding agents including Claude Code, Codex, Cursor, Devin and Antigravity; a dashboard connector for custom agents; a Claude connector for claude.ai, Cowork and Claude desktop; and a POST /v1/extract API for servers without Node. In two independent runs against the same tasks without memory, Memorable cut agent turns by 19% at an injected size of roughly 293 tokens, versus 0% turn reduction for a 15,593-token skill, with every run passing.

Memorable An agent finishes a task; Memorable stores how it was done and replays it when a similar task returns. Storage stays on your side and consent is fail-closed. Pick your route Four ways in. Each one ends with this machine signed in and recording. Nothing below asks an agent to open a browser. A coding agent on a repo Claude Code, Codex, Cursor, Devin, Antigravity. npx memorable-cli Picks the agent, asks whether to make a page for this project, opens one tab, you press Approve. Hooks and consent are written for you. Your own agent Browser, voice, smart home, research, ops. memorable.sh/dash, Environments, Connect Pick the card, Save, Copy prompt. The key is already in it. Paste it into the agent that builds your project; it adds recall, replay and record. No terminal claude.ai, Cowork, Claude desktop. memorable.sh/dash, Connect, Create a connector Add the link under Connectors in Claude. It searches memorables before it plans and records when it finishes. A server with no Node A backend that runs agents. memorable.sh/dash, Account, New key for an agent POST /v1/extract with the key. Store the draft on your side. Quickstart Two minutes. Signing in links this machine to your workspace; the default backend is a standalone local store, and on a machine running gbrain you can point it at your own database with memorable init gbrain afterwards. connect this machine no node or npm on this machine store a procedure, then find it For agents Telling a coding agent "use memorable" is enough. Every step is a plain CLI call it can run itself. The drop-in file lives on AGENTS.md . one line Measured Against the same tasks run without memory, on two independent runs. Recall vs no recall agent turns -19%, replicated pass rate every run passed injected size ~293 tokens vs a 15,593-token skill: 0% turns Extraction API One endpoint converts a tool-call trace into a procedure. Full reference on the API page. POST /v1/extract BASE=https://memorable-\ extraction-api.memorable.workers.dev curl $BASE/v1/extract \ -H "Authorization: Bearer \ $MEMORABLE API KEY" \ -H "Content-Type: \ application/json" \ -d '{ "session id": "run-183", "task description": "rotate the TLS cert", "harness": "my-orchestrator", "tool calls": {"name": "shell", "input": {"command": "certbot renew"}, "result": {"ok": true}} }' Response · 200 { "draft": { "title": "Rotate the TLS cert", "schema version": "1.0.0", "steps": { "seq": 1, "action": "shell", "activity class": "execute", "command": "certbot renew", "repeat count": 1 } , "postconditions": "final command exited successfully: certbot renew" , "embedding": , "embedding model": "" }, "request id": "82886df0-..." }