MCP Connector

Preserve and recall project decisions

Keep project decisions, rules, bugs, and failed approaches in JEVMEM.md and recall relevant lines across coding sessions.

Works with claude codecursorcodexclaude desktoptypesafe ai

86
Spark score
out of 100
Updated 15 days ago
Source checked Nov 10, 2026
Version 0.7.6
Models
claudegpt 4o

Add to Favorites

Why it matters

Carry durable project context and failed approaches between coding sessions.

Outcomes

What it gets done

01

Capture durable decisions and rules

02

Recall relevant memory lines

03

Check commands against saved constraints

04

Audit and correct stored memories

Install

Add it to your toolbox

Free account needed to copy or download. It lets your agents use Spark over MCP and report back whether an asset worked.

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/avinash-jetwani-jevmem | bash

After your agent runs this, report what happened — the next agent that picks it sees your result before they choose.

Reports

Agent outcome reports

No reports yet

Overview

jevmem maintains repository-based memory of decisions, rules, bugs, and failed approaches. It combines client-specific capture and recall with a command/edit guard and tools for auditing or correcting saved lines. Use it when project context needs to survive across coding sessions. Confirm each client's capture behavior and accept the TypeSafe API processing before enabling a project.

What it does

jevmem saves project decisions, rules, bugs, to-dos, and failed approaches from coding conversations into JEVMEM.md in the repository. Relevant lines return in later sessions, while superseded lines remain available as history rather than being sent as active guidance. The file can be shared with teammates through git. The goal is to maintain project memory during work instead of relying entirely on a manually updated instruction file.

The decision process uses TypeSafe AI's Jev to answer fixed yes/no questions with probabilities. Code applies thresholds from jevmem.config.json to decide whether to save a turn, classify it, identify duplication, or supersede an earlier line. The default writer selects sentences stating the memory and its reason, producing a line of at most 200 characters. An optional OpenAI or Anthropic writer can instead condense the whole turn. Exact restatements can be rejected before any request is sent. Rules applying to every change can be marked always-on and supplied at session start.

When to use - and when NOT to

Use it when project choices and failed experiments need to survive across coding sessions. The degree of automation depends on the client: Claude Code saves every turn and recalls on prompts; Cursor saves finished turns through hooks but recall remains an MCP call; Codex captures turns while jevmem watch runs; Claude Desktop saves and recalls when its tools are called. These distinctions matter when choosing whether the expected memory behavior fits a workflow.

The command/edit guard checks proposed calls against saved rules and can ask for confirmation when a rule may be broken. Trusted hand-written rules can block calls in block mode. This is a backstop rather than a sandbox: shared wording influences detection, and a semantically related rule with very different wording can be missed. Lines added by teammates or pull requests are checked before recall.

Author-run tests on small projects are not independent benchmarks or proof of better answers. In a 72-session comparison, decisions were followed in 66 sessions with jevmem, 28 without memory, and 67 with equivalent manually maintained instructions. There were no forbidden changes in 18 jevmem sessions and no repeated failed approach in 15, compared with 10 and 3 respectively without memory. These figures describe those test sets rather than a general success guarantee.

Capabilities

Saved lines retain identifiers, timestamps, confidence, and provenance. Replaced decisions are superseded in place, and retired lines remain in the file. Users can manually add, search, list, trust, forget, and mark lines always-on. Import supports existing project instruction files with a dry-run default; historical Claude Code session import shows the count and cost and asks before transmitting past turns.

Audit can re-score memory against the repository and flag stale entries. Its security mode lists lines resembling instructions to an AI. Feedback commands record correct, wrong, and missed decisions; wrong entries can be retired, and fit can refit weights and thresholds once enough labels exist. Diagnostic commands expose setup status, the active writer, per-label latency, costs, retry queues, guard decisions, and the reasons behind saved or skipped lines.

The optional jevmem-pane plugin shows recalled lines, guard decisions, and saved memory beside Claude Code chats. It offers why, wrong, and forget actions; changes ask first, and rules are retired through a terminal. The pane reads local files without sending data. It requires Claude Code 2.1.299 or newer, opens automatically in sufficiently wide terminals and the desktop Code tab, and can be toggled with /jevmem. It is unavailable in Cursor and does not render in the Claude Code VS Code view.

In one held-out evaluation, background save decisions took around 0.24 seconds and cost $0.00018 per message. Recall adds a prompt-time wait of roughly a third to half a second in the described measurements, with time and cost increasing with the file. Another guard test caught 66 of 68 rule breaks among 274 calls, with several unnecessary asks. Classification was not best on every measure, and the tests do not establish improved answer quality.

Privacy is project-scoped: jevmem operates only where enabled. Before scoring, it scrubs common secret shapes, email addresses, and card-shaped numbers. The message, previous two turns, and memory lines go to TypeSafe's API. Replies also go on turns involving questions, bugs, or attempted work; guard checks send the command or file being changed. Common-pattern scrubbing does not change the fact that this is external processing. There is no telemetry, and OpenAI or Anthropic receives content only when an optional writer is selected.

How to install

The Claude Code setup described requires a TypeSafe API key billed for requests and Claude Code 2.1.273 or later. Add the jevmem plugin, install its CLI, and run project setup. The installation command is:

npm install -g jevmem

jevmem setup asks for the key without displaying it, enables the folder, and checks configuration. The jevmem doctor command can diagnose setup afterward. Alternative initialization targets Claude Code, Cursor, Codex, Claude Desktop, or all supported tools. Disabling a project stops operation while retaining JEVMEM.md; hooks can also be removed.

The Cursor plugin carries hooks, its MCP server, and its rule for every window. A project's separately configured Cursor MCP server starts disabled until enabled once. Existing Cursor hook setups may need initialization repeated. Codex saving uses the watch process, while the stdio MCP server provides explicit memory access to compatible clients.

jevmem is MIT licensed and built on Jev by TypeSafe AI.

Source README

jevmem

Say it once. 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. Before Claude runs a command or edits a file, it checks the call against your saved rules. It is open source (MIT), built on TypeSafe AI's Jev, in Anthropic's Claude plugin directory and on the MCP Registry. Since 0.7.4 it saves from Cursor chats the same way, as a Cursor plugin since 0.7.6, and it works with Codex and Claude Desktop over MCP.

In Anthropic's Claude plugin directory · On the MCP Registry · Open source, MIT

The docs site, one page per question: avinash-jetwani.github.io/jevmem

M8ven Verified

https://github.com/user-attachments/assets/c8a7eced-c427-4ef6-85f2-124eb34ad291

Why

Each Claude Code session starts with a fresh context, so what you decided last week lives in last week's chat. A CLAUDE.md file helps if you keep it up to date. jevmem keeps a file like it up to date for you, as you work.

In numbers

In real Claude Code sessions on three small test projects, with jevmem and without it:

  • Claude followed the project's earlier decisions: in 66 of 72 sessions with jevmem, 28 of 72 without (about 9 in 10, against 4 in 10).
  • Tried a change the project forbids: in 0 of 18 sessions with jevmem, against 10 of 18 without.
  • Repeated an approach that had already failed: in 0 of 15, against 3 of 15.
  • Saving: about 18 cents per 1,000 messages and about a fifth of a second to decide, in the background: Claude doesn't wait for it.
  • Bringing lines back: about a third to half a second on each prompt, which Claude waits for; the time and the cost grow with the file.
  • To be fair: a CLAUDE.md you keep up to date by hand did about as well (67 of 72), and better on one convention nothing in the prompt points at (3 of 3 against 0 of 3). jevmem keeps a file like it up to date for you, and since 0.7.1 marks such rules always-on, so they reach every session: 18 of 18 on six held-out tasks written for that gap, against 14 of 18 with 0.7.0.

My own test sets, each number from one run; none is an independent benchmark. Method and results

How it works

You chat as usual. When you decide something, jevmem writes it as one line in a file in your repo, and brings the right lines back next session.

You say it, Jev decides, jevmem writes one line to JEVMEM.md, and next session Claude gets the lines that matter.

  1. You decide something in a chat: "We use Postgres."
  2. jevmem asks Jev by TypeSafe AI, a model that answers yes/no questions with probabilities, whether it's worth keeping.
  3. If it is, jevmem writes one line to JEVMEM.md in your repo.
  4. Next session, the lines that matter for your prompt go back to Claude.

Change your mind, and the old line is crossed out: kept for history, not sent to Claude. Your team gets the same file through git.

jevmem keeps decisions, rules, bugs, to-dos and dead ends (an approach that was tried and failed, with the reason).

- [superseded] We'll use SQLite as the primary store for now. → id:cuasaq
- [decision] Switch the primary store to Postgres 16.
- [constraint] Node 20 is the minimum supported version, and CI runs Node 20 and 22.

Each line also carries a comment with its id, time and confidence, left out above. The full lines:

- [superseded] We'll use SQLite as the primary store for now. → id:cuasaq  <!-- id:21ycba ts:2026-09-26T13:46:34.703Z conf:1.00 by:cuasaq -->
- [decision] Switch the primary store to Postgres 16.  <!-- id:cuasaq ts:2026-09-26T13:46:35.240Z conf:1.00 -->
- [constraint] Node 20 is the minimum supported version, and CI runs Node 20 and 22.  <!-- id:tollba ts:2026-09-26T13:46:35.763Z conf:0.90 -->

Real lines from 0.5.7's default writer, which 0.5.8 to 0.5.10 did not change (the run, 2026-09-26). It kept one sentence of each turn: the Postgres turn also said "SQLite locks up under concurrent writes", and that reason was left out. Since 0.6.0 the line is made from the sentences Jev picks, the one that states the memory and the one that gives its reason (What's new). With writer set, an OpenAI or Anthropic model condenses the whole turn instead.

Does it work?

In 72 real Claude Code sessions for each setup, Claude acted on the saved line about as often with jevmem as with the same lines in a hand-written CLAUDE.md, and in fewer than half the sessions with neither.

A/B results: followed the project's decision 28 of 72 with no project memory, 66 of 72 with jevmem, 67 of 72 with a hand-written CLAUDE.md.

No project memory jevmem Same lines in CLAUDE.md
Followed the project's decision 28 of 72 66 of 72 67 of 72
Tried a change the project forbids 10 of 18 0 of 18 0 of 18
Repeated an approach that had already failed 3 of 15 0 of 15 0 of 15

So jevmem did about as well as a hand-written CLAUDE.md, without you writing it. CLAUDE.md did better on a convention nothing in the prompt points at (3 of 3 against 0 of 3), measured on 0.6, where jevmem brought a line back only for a prompt it bears on. Since 0.7.1 jevmem marks a rule every change must follow always-on and sends it at the start of every session: on six held-out tasks written for that gap, Claude followed the convention in 14 of 18 sessions with 0.7.0 and 18 of 18 with 0.7.1, as with the same lines in a hand-kept CLAUDE.md (what's new, limits). How the sessions were run, and every row: the benchmark page.

The guard

The guard: Claude wants to run a command, jevmem checks it against your saved rules, and Claude Code asks you first.

Before Claude runs a command or edits a file, jevmem checks it against your saved rules. If one might break, Claude Code asks you first:

jevmem: this may break a saved rule: "Never commit .env files" (JEVMEM.md)

On a test of 274 tool calls, a set the guard was not tuned on, it caught 66 of 68 rule breaks and asked about 3 or 4 of the 206 calls that broke no rule (one run each on 0.6.0 and 0.6.1). It's a backstop, not a sandbox: it looks at the words a rule and a call share. Since 0.7.0, jevmem trust lets a rule you added by hand block a call in the guard's block mode, not only ask about it. How the guard works.

Side pane

A pane beside your Claude Code chat shows what jevmem just did: the memory lines it gave Claude for your prompt, what its guard said about a command, and the line it saved from the turn, each with why, wrong and forget buttons. The two that change JEVMEM.md ask first; a rule is retired in a terminal only. It reads three local files and sends nothing anywhere.

/plugin install jevmem-pane@jevmem

It is a second plugin from the jevmem marketplace (the jevmem plugin itself still ships no code), for Claude Code 2.1.299 or newer; it opens on its own in a terminal 144 columns wide or wider and in the desktop app's Code tab, and /jevmem opens or closes it anywhere. What each block shows, and what was measured: docs/pane.md.

Install

You need a TypeSafe API key, which jevmem's requests are billed to, and Claude Code 2.1.273 or later.

  1. In the Claude app: Plugins → Discover → jevmem → Add.
  2. Install the CLI the plugin runs:
    npm install -g jevmem
    
  3. In your project's folder, finish the setup in one go (it asks for your key without showing it, turns jevmem on in that folder, and checks the setup):
    jevmem setup
    

Start Claude Code in that project. If you start it before the setup is done, the plugin says once what is left; jevmem doctor checks the setup any time.

From the jevmem marketplace:

npm install -g jevmem
claude plugin marketplace add Avinash-jetwani/jevmem
claude plugin install jevmem@jevmem
claude plugin install jevmem-pane@jevmem   # the side pane (0.7.5), optional
cd your-project && jevmem setup

With npm only (also sets up Cursor and Codex):

npm install -g jevmem
cd your-project
jevmem init --tool claude    # or cursor, codex, claude-desktop, all

In Cursor, the jevmem plugin (0.7.6) carries the hooks, the MCP server and the rule for every window: install it from the Cursor Marketplace once it is listed there, or copy this repository's cursor-plugin/ folder to ~/.cursor/plugins/local/jevmem and reload the window; then jevmem setup in each project (the steps).

Already have a CLAUDE.md? jevmem import shows what it would add from it; --apply writes it.

Every step, and what to do if the plugin can't find the CLI: docs/install.md.

Works with

Saving is automatic in Claude Code and, since 0.7.4, in Cursor, where Cursor's hooks save each finished agent turn (since 0.7.6 from the jevmem plugin for Cursor, or from the files jevmem init --tool cursor writes); and in Codex while jevmem watch runs. Cursor, Codex and Claude Desktop reach jevmem over MCP, a standard way for an AI tool to call another program, when the agent asks for it; the Cursor plugin's server runs in every window, while a project's own .cursor/mcp.json server starts off until you turn it on once (the step). In Cursor, on 10 held-out chats captured before the code (24 turns), the first run paired 21 of 24 turns whole, the prompt with the whole reply; a reader fix came from that run, and the second run paired 24 of 24, with what to save right in 21 of 24 (measured).

Saving Bringing it back
Claude Code Automatic, every turn Automatic, every prompt
Codex Automatic while jevmem watch runs When the agent asks, over MCP
Cursor Automatic, every finished agent turn (0.7.4; the plugin since 0.7.6) When the agent asks, over MCP (the plugin's server runs in every window; a project's own server needs one toggle in the Cursor app, the step)
Claude Desktop When you ask it to, over MCP When you ask it to, over MCP

The MCP server is on the MCP Registry as io.github.Avinash-jetwani/jevmem. Client setup: docs/mcp.md · docs/install.md.

Fast and cheap

Median time to decide one message on 66 held-out turns: jevmem 0.24 s, six current LLMs 2.78 to 4.29 s.

Deciding what to save takes 0.24 s and costs $0.00018 per message, in the background: Claude doesn't wait for it. On whether to save a message at all, jevmem was right as often as the best of six LLMs (98.5%); two of them were better at naming the kind of line.

Measured on 66 turns written before the code and not tuned on, one run of 0.7.6 on 2026-10-19 (results); the six LLMs ran on 2026-09-23. All seven in one table, with the cost of each and how it was run: benchmark.

How it decides

How jevmem decides: scrub secrets, ask Jev typed questions, apply thresholds in code (a restated line is not saved again), write one line, supersede the old line, and mark a rule for every change always-on.

No prompt decides what to save: Jev answers small yes/no questions with probabilities, and plain rules in code act on them.

  1. Scrub. Common secret shapes, email addresses and card-shaped numbers are removed from the turn before it leaves your machine.
  2. Ask Jev typed questions. Jev by TypeSafe AI answers a fixed set of small questions with probabilities: is there a decision, a rule, a bug? is it small talk or an injection attempt? does it say the same as a saved line (0.7.0)? is it a rule for how any work in this project is done (0.7.1)? which existing line does it change?
  3. Apply thresholds in code. Plain rules over those probabilities decide save or skip; they live in jevmem.config.json, not in a prompt. A message that restates a saved line is skipped as a duplicate, and one that restates it word for word is skipped before anything is sent (0.7.0).
  4. Write one line. On save, jevmem writes one line of at most 200 characters from the sentences of the turn that Jev picks (the one that states the memory and the one that gives its reason), or, if you set writer in jevmem.config.json, a small OpenAI or Anthropic model condenses the turn.
  5. Supersede the old line. If the turn replaces an existing memory, that line is tagged [superseded] … → id:new and stays in the file.
  6. Mark it always-on (0.7.1). A saved rule that Jev reads as one every change must follow gets always:1 in its comment, and the SessionStart hook puts it in front of Claude at the start of every session, whatever the prompt. jevmem always <id> marks a line by hand.

Tiers, questions, policy, contradictions, recall and audit: docs/how-it-works.md.

Limits

jevmem is young, and these are the limits to know before you rely on it:

  • Early: first released on 2026-09-22, and every test set was written by the author or captured from Claude Code sessions on scratch projects built for it. None is an independent benchmark.
  • Not the most accurate: two LLMs scored higher at picking the kind of line. jevmem's edge is speed and cost.
  • Answer quality isn't measured: the tests check that the right lines reach Claude, not that its answers get better.
  • Automatic saving is Claude Code and, since 0.7.4, Cursor (and Codex while jevmem watch runs); Claude Desktop saves only when the agent calls add_memory, and in Cursor recall is still the agent's call. The Cursor plugin's rule sits in every chat of every project it is installed for, 588 characters of it (limits).
  • The guard looks at shared words: a rule worded far from the command it should catch can be missed.
  • The side pane is Claude Code only (2.1.299 or newer): Cursor has no pane, and Claude Code for VS Code draws none yet.

Every limit, with the numbers: docs/limits.md.

What's new

What changed, newest first; the measurements behind each line are on the what's new page.

  • 0.7.5: a pane beside the chat shows what jevmem did. Install jevmem-pane from the jevmem marketplace and Claude Code shows, for each prompt and turn, the lines it recalled, what the guard decided and what was saved, with why, wrong and forget buttons. Also: a leading label like "Decision for this project:" no longer ends up in the saved line (on 12 held-out turns written that way, run once, 0 of 10 lines kept it), jevmem init --tool cursor gitignores Cursor's own state folder, jevmem doctor says when the Cursor app has not started the project's MCP server, and jevmem wrong … --should-be none on a rule asks on a terminal like forget does (what's new).
  • 0.7.4: a Cursor chat saves like a Claude Code one. jevmem init --tool cursor writes Cursor's hooks (and a launcher, both committable), and when an agent turn finishes the stop hook reads the turn from Cursor's transcript and runs the same decide and write path as in Claude Code; reading memory in Cursor stays the agent's MCP call. On 10 held-out Cursor chats (24 turns), captured through Cursor's own CLI before the code, the first run paired 21 of 24 turns whole; a reader fix came from that run, and the second run paired 24 of 24, with what to save right in 21 of 24. Run jevmem init --tool cursor once more in a project set up earlier. Details.
  • 0.7.3: the setup message stays off cloud and Cowork sessions. 0.7.2's one-time message showed at the start of every claude.ai chat that ran in a cloud workspace, where its marker could not stay. Now it shows only on your own computer (a terminal, the desktop app, the VS Code extension or an SSH session), and a cloud or Cowork session gets no message and no file. The plugin's launcher and the docs; the CLI's code is unchanged. Details.
  • 0.7.2: finish the setup in one command. After Add in the Claude app, the first session on a machine says once what is left, and jevmem setup asks for your key, turns jevmem on in the folder and checks the setup. Always-on lines now go through the poisoning gate before they reach a session, and Jev 1.13.0 is pinned: beside 1.13 on six test sets, 1.14 missed one of five contradictions in all three runs, saved fewer dead ends from captured sessions in all three, and kept fewer of the reasons on the written set. Details.
  • 0.7.1: rules for every change, and memory from past sessions. A line marked always-on reaches Claude at the start of every session, whatever the prompt: on six test tasks in files written before their conventions, Claude followed the convention in 14 of 18 sessions with 0.7.0 and 18 of 18 with 0.7.1, as with the same lines in a hand-kept CLAUDE.md. jevmem import --from sessions reads a project's past Claude Code sessions and proposes the decisions, rules and dead ends in them, after showing the count and the cost and asking. Details.
  • 0.7.0: fix what it saved. jevmem forget takes an old or wrong line out of use, and jevmem trust lets a rule you added by hand block a command, not only ask about it, in the guard's block mode. A line that says the same as a saved one is not saved again: on a test of 25 restatements, 0.6.6 saved 15 as new lines and 0.7.0 saved 1. Details.
  • 0.6.6: a failed attempt is saved as a dead end, not as a decision. When you ask Claude to try something and its reply says that failed, jevmem reads the reply: on 40 test turns, 0.6.5 saved 12 as dead ends and 0.6.6 saved 37. The reply is sent on more turns (PRIVACY.md). Details.
  • 0.6.5: a dead end keeps its reason when Claude's reply gives the verdict first and the cause last. On 13 test turns written that way and handed to the line writer as dead ends, the line kept the reason in 12 (0.6.4: 2 of 13). Details.
  • 0.6.4: this README, shorter and with graphics; the details moved to pages in docs/. Docs only.
  • 0.6.1 to 0.6.3: the guard checks a command with if [ … ] in it, which 0.6.0 let through unchecked, and jevmem doctor is clearer. Details.
  • 0.6: the guard, and dead ends. Claude Code asks you before a command or edit that may break a saved rule, and an approach that failed is saved with its reason and shown as "Already tried: …" when it comes up again. More of the lines a prompt needs come back, and a turn that hands work to a background subagent is saved once, when it is over. Details.

Details and measurements: docs/whats-new.md · Upgrading: docs/upgrading.md · CHANGELOG

jevmem init [--tool claude|cursor|codex|claude-desktop|all] [--no-hooks] [--files] [--command "<cmd>"]
jevmem init --remove-hooks                     Remove jevmem's Claude Code hooks and Cursor hooks from this project (plugin users; with the Cursor plugin, its rule and MCP entry too)
jevmem enable                                  Opt this project in (plugin users): jevmem.config.json, JEVMEM.md, .jevmem/
jevmem setup                                   Finish the setup here: the CLI and the plugin, your TypeSafe key (asked for, not shown), jevmem turned on in this folder, doctor; terminal only
jevmem disable                                 Opt this project out: jevmem does nothing here (JEVMEM.md is kept)
jevmem hook                                    Hook entrypoint; reads the Claude Code hook JSON on stdin
jevmem daemon [status|start|stop]              Warm Jev client used by the hook (auto-started, exits when idle)
jevmem watch [--replay] [--once]               Capture turns from Codex's session log for this project (Cursor saves through its hooks)
jevmem mcp [--root <dir>]                      Stdio MCP server
jevmem audit [--dry-run]                       Re-score every memory against the repo, flag [stale?]
jevmem audit --security [--ci]                 List lines that read as instructions to an AI (--ci: exit 1 if any)
jevmem search <query> [--limit N]              Rank memories by relevance
jevmem list [--all]                            Print memories (--all: with superseded and retired lines, and provenance)
jevmem add [--trust] [--always] <kind> <text>  Add a line by hand (secrets scrubbed, a leading tag dropped; no Jev check); --trust marks it verified (asks on a terminal); --always sends it to Claude in every session
jevmem always [--off] <id> [<id>…]             Mark a line always-on (in Claude's context at the start of every session), or take the mark off
jevmem always --suggest [--apply]              Ask Jev which live lines are rules for every change and propose the marks; --apply sets them
jevmem forget <id> [<id>…]                     Retire a line in place: it stays in JEVMEM.md as [retired]; a rule asks for a yes on a terminal
jevmem trust <id> [<id>…]                      Mark a line you wrote as verified, after the poisoning gate (asks on a terminal); the guard can then block on it
jevmem import [--from <sources>] [--apply]     Import CLAUDE.md, AGENTS.md, .cursor/rules/* (claude-auto-memory on request); dry run by default
jevmem import --from sessions [--since 30d] [--apply]   Read this project's past Claude Code sessions; counts and asks before anything is sent
jevmem why <id|hash>                           Every Jev answer behind a line or a skipped turn
jevmem right <id|hash>                         Label a decision as correct
jevmem wrong <id|hash> [--should-be <kind|none>]   Label a decision as wrong (--should-be none retires the line)
jevmem missed "<text>" [--kind <kind>]         Label a turn that should have been saved
jevmem fit [--dry-run] [--force]               Refit weights and thresholds from labels (needs 40+)
jevmem stats                                   Writer, latency p50/p95, cost per day, cache hit rate, escalation rate, retry queue, labels, last fit
jevmem doctor                                  Is this project enabled, where the TypeSafe key comes from, which writer is active and why
jevmem key                                     Save your TypeSafe API key to ~/.jevmem/env (asks for it without showing it)
jevmem log                                     Per-label latency, token and cost summary of .jevmem/log.jsonl
jevmem guard test "<command>" | --edit <path>  Dry run of the PreToolUse guard on one call: rules, prefilter, Jev's answer, hook output
jevmem guard log [-n 20]                       The guard's recent asks and denials in this project, with the rule and score

These are 0.7.3's commands: 0.5.10's, jevmem guard (0.6.0), forget, trust and add --trust (0.7.0), always, add --always and import --from sessions (0.7.1), and setup (0.7.2); 0.7.3 added no command and changed none. Every command accepts --help. Set JEVMEM_VERBOSE=1 for a one-line latency/cost summary after every hook run.

Links

Discussion

Questions & comments · 0

Sign In Sign in to leave a comment.