DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to stop Claude Code from repeating past decisions and dead ends with Jevmem

Save decisions, rules and failed approaches from Claude Code chats and reuse them next session.

Who it is forA developer working on a project across many Claude Code sessions who keeps re-explaining the stack, the rules and the approaches that already failed.

The problemEach Claude Code session starts with a fresh context, so decisions made last week live only in last week's chat and the agent may suggest an approach that already failed.

The outcomeDecisions, rules and failed approaches are written as lines in JEVMEM.md, and the relevant lines are sent back to Claude at the start of later prompts, with a guard that asks before a command that might break a saved rule.

What you need first

  • A TypeSafe API key from https://console.typesafe.ai/keys, which jevmem's requests are billed to
  • Claude Code 2.1.273 or later
  • npm, to install the jevmem CLI that the plugin runs
  • A project folder in a git repo, so JEVMEM.md can be committed and shared

Steps

  1. In the Claude app, open Plugins, then Discover, choose Jevmem, and click Add.
  2. Run npm install -g jevmem in a terminal.
  3. In your project folder, run jevmem setup and enter your TypeSafe key when asked.
  4. Start Claude Code in that project and work as usual; when you decide something, Jevmem writes one line to JEVMEM.md.
  5. Run jevmem doctor if the setup seems incomplete.

Prompt for your agent

In the jevmem repo's setup for <project-folder>, run the jevmem setup flow and confirm that JEVMEM.md exists in the project root. Expected output: a JEVMEM.md file with at least one line tagged as a decision, rule or dead end after a short test chat. Verify by running `jevmem doctor` and checking that it reports no missing setup steps.

Caveat. The accuracy figures in the README come from the author's own test sets, each from one run, and are not an independent benchmark.

Share: 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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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