jevmem
llms.txt136 starsChanged 39 days agoMITView on GitHub
jevmem saves the decisions, rules and failed approaches from your Claude Code chats to JEVMEM.md in your repo, and brings the relevant ones back next session. jevmem needs a TypeSafe API key: message text is sent to TypeSafe to be scored, with common secrets scrubbed first.
Files
# jevmem > jevmem saves the decisions, rules and failed approaches from your Claude Code chats to JEVMEM.md in your repo, and brings the relevant ones back next session. jevmem needs a TypeSafe API key: message text is sent to TypeSafe to be scored, with common secrets scrubbed first. ## Docs - [What is jevmem?](https://avinash-jetwani.github.io/jevmem/index.md): what it does, what was measured, how to install it, which tools it works with - [How do I make Claude Code remember project decisions across sessions?](https://avinash-jetwani.github.io/jevmem/claude-code-memory.md): why a file, how jevmem keeps it, and CLAUDE.md, auto memory and jevmem side by side - [How does jevmem compare with CLAUDE.md, Claude Code's auto memory and other memory tools?](https://avinash-jetwani.github.io/jevmem/compare.md): how each saves, where it stores, what it works with, whether it needs a key, its licence - [What is Jev used for in coding agents, and how does jevmem use it?](https://avinash-jetwani.github.io/jevmem/jev.md): the three places jevmem calls Jev, and why Jev and not an LLM - [Can Claude Code check commands against my project's rules before they run?](https://avinash-jetwani.github.io/jevmem/guard.md): the guard, how it reads a command, its modes and its limits - [Can I see what jevmem recalled and saved, beside my Claude Code chat?](https://avinash-jetwani.github.io/jevmem/pane.md): the side pane (0.7.5), what each block shows, the buttons, where it shows, what was measured - [How do I install jevmem?](https://avinash-jetwani.github.io/jevmem/install.md): the four steps, the other install paths, upgrading - [How do I use jevmem in Cursor?](https://avinash-jetwani.github.io/jevmem/cursor.md): the jevmem plugin for Cursor (0.7.6: the hooks, the MCP server and the rule in every window, nothing written into a project; from the Marketplace once listed, from the repository's folder now) or `jevmem init --tool cursor` (one command writes the hooks, the launcher, the MCP config and the rule; one toggle in the Cursor app turns that server on), saving automatic since 0.7.4 and what was measured, recall over MCP - [How do I use jevmem in Codex?](https://avinash-jetwani.github.io/jevmem/codex.md): setup, `jevmem watch`, the MCP config - [How do I use jevmem in Claude Desktop?](https://avinash-jetwani.github.io/jevmem/claude-desktop.md): setup and the MCP config - [What leaves my machine?](https://avinash-jetwani.github.io/jevmem/privacy.md): what is sent to TypeSafe, what is scrubbed, what is stored, how to delete it - [Does jevmem need a key, what does it cost, and what are its limits?](https://avinash-jetwani.github.io/jevmem/faq.md): key, cost, local models, teams through git, every known limit ## Results - [Does jevmem work?](https://avinash-jetwani.github.io/jevmem/results.md): every measured result, with its method and its limits - [The results files](https://github.com/Avinash-jetwani/jevmem/tree/main/results): the file behind each number, in the repository ## Optional - [What changed in each version of jevmem?](https://avinash-jetwani.github.io/jevmem/whats-new.md): each release's features with their measurements, and every version with its date - [Every page in one file](https://avinash-jetwani.github.io/jevmem/llms-full.txt) - [The repository](https://github.com/Avinash-jetwani/jevmem): source, README, CHANGELOG, MIT licence
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.