# AI use cases for Jevmem (Avinash-jetwani/jevmem)

Repo: [Avinash-jetwani/jevmem](https://github.com/Avinash-jetwani/jevmem) | Use cases: 4 | Page: https://dedupedai.com/use-cases/avinash-jetwani-jevmem/

jevmem is an open source TypeScript tool that saves decisions, rules and failed approaches from Claude Code, Cursor and Codex chats to a JEVMEM.md file in your repo and brings the relevant lines back in later sessions.

This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL.

- Stop Claude Code from repeating past decisions and dead ends: https://dedupedai.com/use-cases/avinash-jetwani-jevmem/stop-claude-repeating-past-decisions/
- Move an existing CLAUDE.md into JEVMEM.md lines: https://dedupedai.com/use-cases/avinash-jetwani-jevmem/turn-existing-claude-md-into-jevmem/
- Share project decisions with your team through git: https://dedupedai.com/use-cases/avinash-jetwani-jevmem/share-project-memory-with-team-through-git/
- Use one project memory across Cursor and Codex: https://dedupedai.com/use-cases/avinash-jetwani-jevmem/same-project-memory-in-cursor-and-codex/

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

Repo: [Avinash-jetwani/jevmem](https://github.com/Avinash-jetwani/jevmem) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README

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

**Who it is for:** A 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 problem:** Each 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 outcome:** Decisions, 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.

### 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 to paste into your agent

```text
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.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/avinash-jetwani-jevmem/stop-claude-repeating-past-decisions/

## How to move an existing CLAUDE.md into JEVMEM.md lines with Jevmem

Repo: [Avinash-jetwani/jevmem](https://github.com/Avinash-jetwani/jevmem) | Difficulty: Beginner | Time: 15 minutes | Basis: From the README

Preview and apply the rules from a hand-written CLAUDE.md as Jevmem memory lines.

**Who it is for:** A developer who already keeps a CLAUDE.md by hand and wants its rules kept up to date automatically.

**The problem:** A hand-written CLAUDE.md goes stale as the project changes, and rewriting it by hand takes effort.

**The outcome:** The rules from CLAUDE.md are listed first, then added to JEVMEM.md, so future rules are saved as you work.

### Steps

1. Run `npm install -g jevmem` if the CLI is not installed yet.
2. In the project folder, run `jevmem import` to see what it would add from CLAUDE.md.
3. Run `jevmem import --apply` to write those lines to JEVMEM.md. (inferred, check the README)
4. Check JEVMEM.md in your editor and remove any line that no longer applies.

### Prompt to paste into your agent

```text
In the jevmem repo at <project-folder>, run `jevmem import` and report the lines it would add from CLAUDE.md. Expected output: a list of candidate lines and no file changes. Verify that after running `jevmem import --apply`, JEVMEM.md contains those lines.
```

### Caveat

The README says a hand-kept CLAUDE.md did about as well as Jevmem on the author's tests, so the gain is mainly that the file updates itself.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/avinash-jetwani-jevmem/turn-existing-claude-md-into-jevmem/

## How to share project decisions with your team through git with Jevmem

Repo: [Avinash-jetwani/jevmem](https://github.com/Avinash-jetwani/jevmem) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Commit JEVMEM.md so every teammate's agent gets the same saved decisions and rules.

**Who it is for:** A tech lead or team member whose colleagues each run Claude Code on the same repo and keep getting different answers.

**The problem:** Decisions made in one person's chat stay in that chat, so teammates' agents do not know them.

**The outcome:** JEVMEM.md is versioned in the repo, and each teammate's Claude Code session reads the same saved lines after a pull.

### Steps

1. Run `jevmem setup` in the project folder once.
2. Commit JEVMEM.md with your other project files.
3. Ask teammates to run `npm install -g jevmem` and `jevmem setup` in their own clone.
4. Pull the repo so each teammate has the current JEVMEM.md before starting a session.

### Prompt to paste into your agent

```text
In the jevmem-enabled repo at <project-folder>, confirm that JEVMEM.md is tracked by git with `git ls-files JEVMEM.md`. Expected output: the file name printed once. Verify after a teammate pulls that their Claude Code session receives the saved lines on their next prompt.
```

### Caveat

Each teammate still needs their own TypeSafe API key and the Jevmem CLI installed, because requests are billed to the key.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/avinash-jetwani-jevmem/share-project-memory-with-team-through-git/

## How to use one project memory across Cursor and Codex with Jevmem

Repo: [Avinash-jetwani/jevmem](https://github.com/Avinash-jetwani/jevmem) | Difficulty: Advanced | Time: 45 minutes | Basis: From the README

Point Cursor or Codex at the same JEVMEM.md so the agent reads the same saved lines.

**Who it is for:** A developer who switches between Claude Code, Cursor and Codex on the same project and wants each agent to know the same decisions.

**The problem:** Each tool starts without the decisions made in the others, so the agent in one editor can contradict a choice made in another.

**The outcome:** Cursor saves finished agent turns automatically and Codex saves while watch runs, with both reading the shared JEVMEM.md over MCP when asked.

### Steps

1. Run `npm install -g jevmem` if the CLI is not installed yet.
2. In the project folder, run `jevmem init --tool cursor` for Cursor or `jevmem init --tool codex` for Codex. (inferred, check the README)
3. For Codex, run `jevmem watch` in the project folder while you work.
4. In Cursor, install the Jevmem plugin from the Cursor Marketplace once it is listed there, then run `jevmem setup` in each project.

### Prompt to paste into your agent

```text
In the repo at <project-folder>, run `jevmem init --tool codex` and then confirm that jevmem watch starts without errors. Expected output: a running watch process and no setup errors. Verify that a decision made in a Codex chat appears as a line in JEVMEM.md.
```

### Caveat

In Cursor and Codex the agent must ask for Jevmem over MCP to read memory, and a project's own Cursor MCP server starts off until it is turned on once in the Cursor app.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/avinash-jetwani-jevmem/same-project-memory-in-cursor-and-codex/