This release adds 1 notable feature for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Topics
+14 more
Affected surfaces
Summary
AI summaryHistorical telemetry backfill adds anonymized daily activity rollups to PostHog on first worker start after upgrade.
Changes in this release
| Type | Severity | Summary | CVE |
|---|---|---|---|
| Security | Medium |
Honors existing consent mechanisms (DO_NOT_TRACK, CLAUDE_MEM_TELEMETRY=0, telemetry.json opt-out) for the backfill Honors existing consent mechanisms (DO_NOT_TRACK, CLAUDE_MEM_TELEMETRY=0, telemetry.json opt-out) for the backfill Source: granite4.1:30b@2026-06-13-audit Confidence: low |
— |
| Feature | Medium |
Adds one-time historical telemetry backfill on first worker start after upgrade Adds one-time historical telemetry backfill on first worker start after upgrade Source: llm_adapter@2026-06-13 Confidence: low |
— |
| Feature | Low |
Performs a one-time backfill of anonymized daily activity into PostHog on first worker start after upgrade Performs a one-time backfill of anonymized daily activity into PostHog on first worker start after upgrade Source: granite4.1:30b@2026-06-13-audit Confidence: low |
— |
| Feature | Low |
Runs the backfill only once per install using a completion marker Runs the backfill only once per install using a completion marker Source: granite4.1:30b@2026-06-13-audit Confidence: low |
— |
| Feature | Low |
Retries failed backfill sends on subsequent worker starts with duplicate-safe UUIDs Retries failed backfill sends on subsequent worker starts with duplicate-safe UUIDs Source: granite4.1:30b@2026-06-13-audit Confidence: low |
— |
| Feature | Low |
Enables dry-run mode via CLAUDE_MEM_TELEMETRY_DEBUG=1 to output payload without sending Enables dry-run mode via CLAUDE_MEM_TELEMETRY_DEBUG=1 to output payload without sending Source: granite4.1:30b@2026-06-13-audit Confidence: low |
— |
Full changelog
📊 Historical Telemetry Backfill
claude-mem's growth metrics now extend back before telemetry existed. On the first worker start after this upgrade, each install performs a one-time backfill of anonymized daily activity rollups into PostHog via historical-migration ingestion — so installs-over-time, reconstructed WAU/MAU, and cohort retention reflect real usage history instead of starting at the telemetry ship date.
What gets sent
Anonymous counts only — never titles, prompts, file contents, or project names:
- One profile-less
historical_activityevent per active day: observation/session/summary/prompt counts, observation-type breakdown, session outcomes, platform buckets, subagent counts, and compression discovery-token totals — all taggedbackfilled: true - One
install_inferredevent carrying the install's first active date, drawn from trustworthy session timestamps
Privacy & safety
- Honors the exact same consent gates as live telemetry:
DO_NOT_TRACK,CLAUDE_MEM_TELEMETRY=0, andtelemetry.jsonopt-out. Opting out before your first post-upgrade worker start prevents the backfill entirely; a later opt-in still backfills. - Runs once per install, latched by a completion marker written only after confirmed delivery — failed sends retry on the next worker start, and deterministic event uuids make retries duplicate-safe.
CLAUDE_MEM_TELEMETRY_DEBUG=1dry-runs the full payload to stderr without sending anything.- Legacy epoch normalization and corrupt-row guards keep bad timestamps out of the historical record; partial days are never shipped.
Full disclosure documented at docs.claude-mem.ai/telemetry.
PR: #2912
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About claude-mem
A Claude Code plugin that automatically captures everything Claude does during your coding sessions, compresses it with AI (using Claude's agent-sdk), and injects relevant context back into future sessions.
Related context
Related tools
Earlier breaking changes
- v13.11.0 Retires the standalone `cloud-sync.mjs` daemon.
Beta — feedback welcome: [email protected]