Automatic project memory for Claude Code. Also works with Cursor and Codex.
jevmem-launch-readme-v2.mp4
- Saves decisions, constraints, bugs and todos from your Claude Code chats into
JEVMEM.md, automatically. - When you change your mind, the old line is marked superseded, not deleted.
- Next session, the relevant lines are added to Claude's context.
- [decision] Use Postgres 16 for the primary store; SQLite locks under load <!-- id:k3d9xq ts:2026-09-22T10:14:02.113Z conf:0.93 -->
- [constraint] Node 20 is the floor; CI runs 20 and 22 <!-- id:p1m4zt ts:2026-09-22T10:20:41.907Z conf:0.88 -->
- [superseded] Use SQLite as the primary store → id:k3d9xq <!-- id:a8s2ww ts:2026-09-20T16:02:11.000Z conf:0.81 by:k3d9xq -->
npm install -g jevmem
export TYPESAFE_API_KEY=... # https://typesafe.ai (an OpenAI or Anthropic key is optional)
cd your-project
jevmem init --tool claudeinit creates JEVMEM.md, jevmem.config.json and a gitignored .jevmem/ folder, and registers two Claude Code hooks in .claude/settings.local.json, which it adds to .gitignore (details).
What is automatic and what depends on the agent:
| Tool | Setup | Capture | Recall |
|---|---|---|---|
| Claude Code | jevmem init --tool claude |
Automatic, every turn, via the Stop hook |
Automatic, every prompt, via UserPromptSubmit |
| Codex | jevmem init --tool codex |
Automatic while jevmem watch runs (it tails Codex's session log for this project and runs the same decide → write path); otherwise agent-initiated via MCP add_memory, prompted by an AGENTS.md section |
Agent-initiated: search_memory via MCP, prompted by AGENTS.md |
| Cursor | jevmem init --tool cursor |
Agent-initiated: a .cursor/rules/jevmem.mdc rule tells the agent to call MCP add_memory when you state a decision. Nothing is captured if it doesn't |
Agent-initiated: the rule tells it to call search_memory before non-trivial tasks |
| Claude Desktop | jevmem init --tool claude-desktop prints a config snippet to paste (one project per config, named with --root) |
Manual: ask it to call add_memory (no hook, no rule file) |
On request: search_memory |
MCP add_memory goes through the same gate as the hook. Client configs: docs/mcp.md.
- Scrub. Common secret shapes, email addresses and card-shaped numbers are removed from the turn before it leaves your machine.
- 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? which existing line does it change?
- Apply thresholds in code. Plain rules over those probabilities decide save or skip; they live in
jevmem.config.json, not in a prompt. - Write one line. On save, a small LLM (or a deterministic extract, with no LLM key) writes one line of at most 200 characters.
- Supersede the old line. If the turn replaces an existing memory, that line is tagged
[superseded] … → id:newand stays in the file.
Tiers, questions, policy, contradictions, recall and audit: docs/how-it-works.md.
66 held-out turns, all seven deciders given the same state, 2026-09-23 (method, regression set, pricing, p95, retries):
| Decider | save/skip | save+kind | contradictions | p50 | $/decision |
|---|---|---|---|---|---|
| GPT-6 Astra | 98.5% | 98.5% | 5/5 | 3,469 ms | $0.007489 |
| GPT-6 Luna | 93.9% | 93.9% | 5/5 | 2,927 ms | $0.000089 |
| Claude Fable 5.1 | 95.5% | 95.5% | 5/5 | 4,290 ms | $0.013256 |
| Claude Opus 5.5 | 97.0% | 97.0% | 5/5 | 2,784 ms | $0.005186 |
| Gemini 3.8 Flash | 92.4% | 92.4% | 5/5 | 2,850 ms | $0.001174 |
| Grok 4.7 | 90.9% | 90.9% | 4/5 | 3,320 ms | $0.004602 |
jevmem auto |
98.5% | 95.5% | 5/5 | 300 ms | $0.000127 |
The 0.30 s is the Jev API decision; through a real Stop hook process, Node start-up included, it is 0.6 s end to end (cost and latency).
On 66 held-out turns, jevmem's median decision took 0.30 s, against 2.8–4.3 s for six current LLMs. Its accuracy was within the LLMs' range: 98.5% save/skip (tied with GPT-6 Astra for highest) and 95.5% save+kind, against 90.9–98.5% for the LLMs. GPT-6 Astra (98.5%) and Claude Opus 5.5 (97.0%) were more accurate on save+kind; Claude Fable 5.1 tied; GPT-6 Luna, Gemini 3.8 Flash and Grok 4.7 were less accurate. It found 5/5 contradictions, as did five of the six LLMs. GPT-6 Luna was cheaper ($0.000089 against $0.000127) but less accurate (93.9%) and about 10× slower. This is a single run, and differences of one or two turns are within run-to-run noise. If the most accurate decision matters most, GPT-6 Astra or Claude Opus 5.5 are better, at about 40–60× the cost per decision and 9–12× the latency. jevmem is for when you want a fast, cheap decision on every message.
- Sent to TypeSafe AI: the user message of each turn (and the assistant reply for questions and bug reports), the previous two turns, and your memory lines, to be scored. No telemetry. If you set an OpenAI or Anthropic key, the text of a saved turn also goes to that provider to write the line.
- Scrubbed first: common credential shapes (API keys, tokens,
*_PASSWORD=style pairs, connection-string passwords, private keys), email addresses and 16-digit numbers; names, phone numbers and addresses are not caught. - Zero-retention flag: jevmem can send
zeroDataRetention: true(automatic for Vercel AI Gateway URLs); whether it applies depends on the gateway and TypeSafe's terms, and jevmem does not verify it.
Exactly what is sent, stored and scrubbed: SECURITY.md.
- Early: v0.4; both eval sets were written by the author, and neither is an independent benchmark.
- Not the most accurate: GPT-6 Astra and Claude Opus 5.5 scored higher on save+kind; jevmem's edge is speed and cost.
- Recall quality is not measured: that relevant lines are injected is tested; whether answers get better is not.
- Long-run drift is not measured: the harness covers five-turn sessions, not weeks of use.
- Automatic capture is Claude Code only (and Codex while
jevmem watchruns); Cursor and Claude Desktop save only when the agent callsadd_memory. - Jev outages drop turns: each Jev call has a 2 s budget; when the API is slow or down, the turn is skipped and logged in
.jevmem/log.jsonl, not retried later.
jevmem init [--tool claude|cursor|codex|claude-desktop|all] [--no-hooks] [--command "<cmd>"]
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
jevmem mcp [--root <dir>] Stdio MCP server
jevmem audit [--dry-run] Re-score every memory against the repo, flag [stale?]
jevmem search <query> [--limit N] Rank memories by relevance
jevmem list [--all] Print memories
jevmem add <kind> <text> Add a line by hand (secrets scrubbed; no Jev check)
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
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 Latency p50/p95, cost per day, cache hit rate, escalation rate, labels, last fit
jevmem log Per-label latency, token and cost summary of .jevmem/log.jsonl
Every command accepts --help. Set JEVMEM_VERBOSE=1 for a one-line latency/cost summary after every hook run.