claude-mem

v13.3.0 Feature

This release adds 3 notable features for engineering teams evaluating rollout.

Published 13d AI Coding Tools

View tool

✓ No known CVEs patched

Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

ai ai-agents ai-memory anthropic artificial-intelligence chromadb

+14 more

claude claude-agent-sdk claude-agents claude-code claude-code-plugin claude-skills embeddings long-term-memory mem0 memory-engine openmemory llm sqlite supermemory

ReleasePort's take

Moderate signal

editorial:auto 13d

Release v13.3.0 removes duplicate `.mcp.json` root entries and disables Codex transcript replay after hooks migration, while adding three new skills (design‑is audit, weekly‑digests, oh‑my‑issues) and a performance toggle for legacy Codex ingestion.

Why it matters: Patch to v13.3.0 immediately if you use `.mcp.json` configuration or rely on Codex transcript replay; test the new design‑is, weekly‑digests, and oh‑my‑issues skills in development before production deployment.

Summary

AI summary

Updates New skills, What's New, and mcp across a mixed release.

Changes in this release

Type	Severity	Summary	CVE
Feature
Feature	Medium	Introduces design-is skill to audit designs against Dieter Rams principles. Introduces design-is skill to audit designs against Dieter Rams principles. Source: llm_adapter@2026-05-21 Confidence: low	—
Feature	Medium	Introduces weekly-digests skill to produce ISO-weekly project digests. Introduces weekly-digests skill to produce ISO-weekly project digests. Source: llm_adapter@2026-05-21 Confidence: low	—
Feature	Medium	Introduces oh-my-issues skill for root‑cause issue clustering and consolidation. Introduces oh-my-issues skill for root‑cause issue clustering and consolidation. Source: llm_adapter@2026-05-21 Confidence: low	—
Feature	Low	Provides CLAUDE_MEM_CODEX_TRANSCRIPT_INGESTION env var to opt back into legacy Codex JSONL watcher. Provides CLAUDE_MEM_CODEX_TRANSCRIPT_INGESTION env var to opt back into legacy Codex JSONL watcher. Source: granite4.1:30b@2026-05-21-audit Confidence: low	—
Performance	Medium	Enables legacy Codex transcript ingestion via environment variable if needed. Enables legacy Codex transcript ingestion via environment variable if needed. Source: llm_adapter@2026-05-21 Confidence: low	—
Bugfix	Medium	Removes duplicate root `.mcp.json` causing Claude Code /doctor warnings. Removes duplicate root `.mcp.json` causing Claude Code /doctor warnings. Source: llm_adapter@2026-05-21 Confidence: high	—
Bugfix	Medium	Disables Codex transcript replay after hooks migration to prevent history injection. Disables Codex transcript replay after hooks migration to prevent history injection. Source: llm_adapter@2026-05-21 Confidence: high	—

Full changelog

What's New

New skills

design-is (#2483) — audits a design against Dieter Rams' ten "Good design is..." principles. Produces per-principle 0–3 scores with file:line evidence and a NEW / REFINE / REDESIGN verdict, then hands off a ready-to-run /make-plan prompt.
weekly-digests (#2399) — produces a chapter-per-ISO-week serial digest of a project's full claude-mem timeline. Sequential subagent pipeline keeps the narrative coherent across 30+ chapters.
oh-my-issues (#2409) — root-cause issue clustering. Codifies the consolidation method that turned ~100 open issues into 6 plan-masters during the v13.0.1 cycle. Three modes: cluster pass, triage, bundle.

Fixes

fix(mcp): drop duplicate root .mcp.json (#2411) — Claude Code's /doctor was warning "MCP server mcp-search skipped — same command/URL as already-configured mcp-search" for every plugin user. The root copy was vestigial; the plugin's namespaced registration now wins.
fix: stop Codex transcript replay after hooks migration (#2365) — disables the default ~/.codex/sessions/**/*.jsonl watch (native Codex hooks are now authoritative). Repairs ~/.codex/config.toml to set [features] hooks = true and [plugins."claude-mem@claude-mem-local"] enabled = true directly. Fixes transcript replay where files discovered after startup ignored startAtEnd and re-injected history.

Opt back into legacy Codex transcript ingestion with CLAUDE_MEM_CODEX_TRANSCRIPT_INGESTION=true if you depend on the JSONL watcher.

View diff on GitHub

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

Share on X Share on Bluesky

Track claude-mem

Get notified when new releases ship.

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.

All releases →