mirror of
https://github.com/thedotmack/claude-mem.git
synced 2026-09-20 04:23:02 +08:00
Alex Newman
2dcb556d26
* feat(cowork): add claude-mem-cowork plugin — memory for Claude app cloud sessions Cowork/Claude-app cloud sessions run in ephemeral containers where the local worker can't live. This plugin replaces it with thin HTTP hook shims: PostToolUse streams raw tool-use fragments to POST /api/hooks/ingest (spool + batch-flush on failure), SessionStart injects compiled context from GET /api/hooks/context with a project-scoped fallback to the live /api/mcp memory_search, and PreToolUse on Task/Agent prepends relevant observations into every spawned agent's prompt via updatedInput. - project naming is always automatic (cmem_work_root / cmem_work_<folder>), deliberately not a setting - empty projects inject a 'Claude-Mem is taking notes' notice with the local worker viewer link (port from ~/.claude-mem/settings.json) - unpaired installs are fully inert; every hook exits 0 unconditionally - bundled skills: mem-search (progressive search) and mem-setup (pairing) - PRO-ENDPOINT-SPEC.md documents the two server endpoints; ingest maps 1:1 onto the existing worker fragment queue - 32-test mock-server suite in cowork/test/run-tests.mjs - registered in .claude-plugin/marketplace.json Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_012mXp3icorS7jwf42fFv9Wt * fix(cowork): read real claude-mem settings keys in the ~/.claude-mem fallback The compat fallback looked for syncToken/userId/syncHubUrl/workerPort, but a local claude-mem install writes CLAUDE_MEM_CLOUD_SYNC_TOKEN / _USER_ID / _HUB_URL / CLAUDE_MEM_WORKER_PORT (SettingsDefaultsManager). Honor those first (old short names still accepted), update mem-setup + README, and make the fallback test use the real key names. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01JAjZBD6Qi5A8EuFmbcycDH * fix(cowork): include cwd in the session-end envelope so the summary lands on the session's project Verified live: a session-end sent from a different working directory filed its summary under the hook process's project instead of the session's. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01JAjZBD6Qi5A8EuFmbcycDH * fix(cowork): redact secrets before envelope, per-user 0600 spool, merge-don't-clobber spool recovery Addresses greptile P1 findings on PR #3707: - observation/prompt payloads pass a secret-redaction pass (PEM blocks, auth headers, JWTs, vendor token prefixes, key=value assignments) before the envelope is built, so neither ingest nor the retry spool sees raw credentials - spool moved from world-readable /tmp to ~/.claude-mem/cowork-spool.jsonl, created 0600 - failed spool flush now merges the claim back via append instead of renameSync over a replacement spool created by a concurrent hook, so concurrent events are no longer dropped - test harness: hermetic $HOME, redaction + spool-permission checks (38 checks) Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01JAjZBD6Qi5A8EuFmbcycDH * fix(cowork): strip <private>-tagged regions before observation envelopes Ports the local plugin's tag-stripping convention (src/utils/tag-stripping.ts) into the cowork shim: <private>, <claude-mem-context>, <system-instruction>, <persisted-output>, and <system-reminder> regions are removed from tool payloads and session-init prompts before the envelope exists, so explicitly non-storable content reaches neither ingest nor the retry spool. Stripping runs before truncation so a cut-off closing tag can never leak a partial private region. 4 new harness checks (42 total). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01JAjZBD6Qi5A8EuFmbcycDH * fix(cowork): redact connection-string credentials (scheme://user:pass@) URI userinfo with a password now redacts to scheme://[cmem-redacted]@host — covers postgres/mysql/redis/amqp/mongodb-style DATABASE_URLs that matched neither the vendor-token patterns nor KEYVALUE_RE. Bare user@ URIs (ssh://git@github.com) stay intact — that's signal, not secret. Mirrors the userinfo rule in src/services/telemetry/error-scrub.ts. 3 new harness checks (45 total). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01JAjZBD6Qi5A8EuFmbcycDH * fix(cowork): full URI userinfo redaction, Cookie header redaction, oldest-first spool recovery Round 3 of greptile P1s: - URI credential redaction now covers passwords containing literal '/', ':' or '@' — userinfo is everything up to the LAST '@' in the URI token, so postgresql://admin:pa/ss@host and admin:pa@ss@host both fully redact (bare user@ like ssh://git@github.com still passes through as signal) - Cookie:/Set-Cookie: header values redact wholesale regardless of cookie name - failed-flush recovery drains a concurrent replacement spool onto the claim's tail (old→new) and restores via wx (no clobber, append fallback); flushSpool additionally stable-sorts the batch by ts so replay is always oldest-first - 6 new harness checks (50 total) Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01JAjZBD6Qi5A8EuFmbcycDH * fix(cowork): overflow spool re-spools the remainder instead of dropping oldest events flushSpool sent only the newest SPOOL_MAX lines but deleted the whole claim on success, permanently losing anything older once the spool exceeded 200 events. It now sends the OLDEST 200 and re-spools the remainder for the next flush — bounded batches, zero silent drops. On failure the untouched claim still restores in full. 4 new harness checks incl. a 201-event drain (54 total). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01JAjZBD6Qi5A8EuFmbcycDH * fix(cowork): claim spool before reading it; redact any Authorization scheme - flushSpool now renames (claims) the spool FIRST and reads the claim, so an event appended between read and rename can no longer travel into the claim unread and be deleted on success — later appenders always write a fresh spool - Authorization/Proxy-Authorization header values redact wholesale regardless of scheme (Token, ApiKey, custom), and the inline scheme pattern gains Token - 2 new harness checks: Token credential absent from request body and from the failed-delivery spool (56 total) Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01JAjZBD6Qi5A8EuFmbcycDH * docs: add Memory Prize scorecard and slides (hackathon 05) Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(cowork): redact short and whitespace-bearing credential values; align marketplace version - KEYVALUE_RE no longer requires 6+ non-whitespace chars: sensitive-key values are redacted in full through the line or record delimiter, so short passwords and passphrases containing spaces never reach the ingest payload or spool (Greptile P1) - marketplace.json bumped to 0.1.3 to match plugin.json and the X-CMEM-Plugin runtime header (Greptile P2) - regression tests for short, whitespace-bearing, and short query-string credential values Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Claude-Mem Hackathon Kit — Sunday Aug 23, 2026
Everything for the $1,000 Memory Prize track: decks, cheatsheet, tutorial, source docs.
Share links (wooow.now, permanent)
| Deck | Pages | Link | Best for |
|---|---|---|---|
| Field Guide — Story | 15 | https://wooow.now/claude-mem-field-guide-story | Richest single deck; covers everything |
| Field Guide — Picture Book | 12 | https://wooow.now/claude-mem-field-guide-picture-book | Live talk — one idea per slide, minimal text |
| Cheat Sheet | 14 | https://wooow.now/claude-mem-cheat-sheet | Handout / reference; flat, scannable |
| Tutorial | 9 | https://wooow.now/claude-mem-tutorial | Walkthrough: do this / you'll see / what it means |
| Memory Prize | 13 | https://wooow.now/the-memory-prize | Prize pitch: one slide per direction |
One-page HTML cheatsheet (printable): https://claude.ai/code/artifact/e6c93b0d-0f8f-45f9-9b15-1c07c63b2d6c
Recommended "best of" assembly (~15 slides for a talk)
- Picture Book p1–p2 — forgetful builder, every morning is day one
- Story p3 — the three costs (time / money / lost decisions)
- Story p2 — builder vs observer spread
- Story p5 — every action → "is this worth a note?"
- Picture Book p6 — the funnel: only the "aha" moments
- Story p6 — anatomy of a note (glowing notebook)
- Cheat Sheet p6 — anatomy of a note (clean, accurate example)
- Story p8 — titles first, details on demand
- Cheat Sheet p8 — three-layer recall
- Story p9 — observer's job description is swappable
- Story p10 — photo / transcript / Slack dump → structured notes
- Cheat Sheet p10 — modes that exist + /mode-creator
- Cheat Sheet p11 — building blocks
- Prize p3 — "make memory matter" (not bigger context, not stuffing)
- Cheat Sheet p13 or Prize p4–p10 — seven directions
- Prize p11 — Monday-morning test
- Story p14 — five-minute start + FASTHACK30
Known render glitches (NotebookLM)
- Story p7: "context. context." duplicated; p13: "Claude-Mem rrropers" (should be "developers")
- Picture Book p2: "the the same files"; p12: "100,000 100,000 developers"
- Cheat Sheet p3: builder card layout slightly garbled
- Tutorial / Prize: clean
Regenerate any deck cheaply: notebook + source already exist; just rerun generate with a tweaked prompt.
Source docs (plain-English, no jargon)
01-what-is-claude-mem-field-guide.md— master guide (3.2k words)02-claude-mem-cheatsheet.md— cheatsheet03-claude-mem-tutorial.md— stage-by-stage tutorial04-the-memory-prize.md— prize copy + plain-English framingclaude-mem-cheatsheet.html— printable one-pager
NotebookLM notebooks (for regenerating)
- Story: 158427e7-80d8-437a-8e92-c581054a7afc
- Picture Book: ddc457db-0430-4e8f-956e-5c2fb9fe0425
- Cheat Sheet: 4ad95081-a12a-4fd1-8d15-4f537399c76d
- Tutorial: 979aec4c-74bb-4cfd-8012-3bb5c4ea5863
- Prize: 77ab6061-e560-4488-a44c-6a0718abbd06