Who it is forA developer returning to a bug or feature in a repository after days or weeks, when a new agent session has no memory of the earlier attempts.
The problemA new session often starts without the failed attempts, design rationale, and pitfalls established in earlier work, so the agent repeats old mistakes.
The outcomeThe agent starts with the small set of saved engineering lessons relevant to the current task and reaches useful investigation sooner.
What you need first
- Node.js 20+ (Node.js 24 LTS recommended)
- At least one supported coding agent installed, such as Codex, Claude Code, or Cursor
- A normal interactive terminal for setup, or a caller-provided API key for stdin setup
- Network access for MemoraX search and writeback
- On Linux, /usr/bin/secret-tool from libsecret and an available Secret Service for guest credentials
Steps
- Run
npm install -g @memorax/memorax-codeto install the package. - Run
memorax-code setupin a normal terminal for guest mode, ormemorax-code setup --existing-accountif you have a MemoraX account. - Restart or refresh your coding agent so the managed plugin and Hooks load.
- Open the project, start a new session, and send one prompt.
- Run
memorax-code statusandmemorax-cli statusfrom the project directory; a Hook that has run should change to hook-runtime=observed.
Prompt for your agent
In the <project path> repository, use the MemoraX Code skill to recall prior engineering lessons about <task area> before you edit anything. List each lesson you retrieved and state which one you will apply first. Verify that the list comes from the memory search result, not from your own assumptions.
Caveat. Search and writeback need network access, and Linux guest credentials depend on libsecret and a running Secret Service session.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page