Go to file
jared 0ceddcf02f os-context: reframe orchestration rules as identity, not exemption list
IRL audit of session 5043beab found the exemption-list framing loses to
conversational continuity: mechanical work interleaved with user
interaction (orientation reads, post-decision write-ups) got rationalized
into the main loop. Reframed: the main loop's one job is being the user's
interface; it reads only user-named files and sign-off evidence, and
never reads to orient — orientation is the first delegable task.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01S7wMwyTdADMoGTu2TrmMS8
2026-07-17 18:29:28 -04:00
.claude-plugin Audit os-* plugins against cc-architect standards + remediate 2026-07-16 15:34:41 -04:00
bin refresh-plugins: diff newest cache version dir, not first glob hit 2026-07-17 08:32:44 -04:00
docs os-context: absolute delegation policy (ADR-0043) 2026-07-17 10:19:32 -04:00
openspec openspec: to-issues renamed to to-tickets (Pocock v1.1) in issue-backlog spec 2026-07-16 16:24:36 -04:00
plugins os-context: reframe orchestration rules as identity, not exemption list 2026-07-17 18:29:28 -04:00
.dochygiene-rules.json wip: checkpoint before hygiene cleanup 2026-07-15 15:41:09 -04:00
.gitignore Remediate cc-architect audit findings across os-* plugins (#75-#79) 2026-07-16 16:36:23 -04:00
CLAUDE.md Merge branch 'worktree-os-sdlc' (os-sdlc concept map + to-tickets rename) 2026-07-16 16:24:25 -04:00
README.md Archive memsearch-episodic-layer change 2026-06-09 14:35:50 -04:00
graphify-interview Add Graphify setup & best-practices guide (11 docs + research) 2026-06-03 16:45:07 -04:00
indydevdan-agentic-engineering-overview-video.txt wip: checkpoint before hygiene cleanup 2026-07-15 15:41:09 -04:00
memory-systems-compared060326 Add Graphify setup & best-practices guide (11 docs + research) 2026-06-03 16:45:07 -04:00

README.md

cc-os — Cross-Project Memory for Claude Code

A personal memory system for Claude Code, designed for a multi-client freelancer. The system captures knowledge across projects and surfaces it automatically at the start of each Claude Code session.

Status

The memory plugin is live and working. Design documentation lives in docs/. Both episodic memory (memsearch) and semantic/knowledge memory (Graphify + Obsidian vault) are active.

What it does for you

  • Injects vault context at session start — Claude sees your SecondBrain graph summary, your conventions, and today's journal path before you type the first message.
  • Surfaces project structure on demand — run one command to build a graph of any project; Claude can then query it for patterns, architecture, and conventions.
  • Remembers conventions automaticallymemory-write stores evergreen knowledge (coding patterns, client rules, recurring decisions) in the correct vault location with proper tags.
  • Stays fresh without a daemon — the vault graph rebuilds in the background when stale; vault writes immediately invalidate the timestamp so the next session picks up changes.
  • Keeps project repos clean — all indexes are build artifacts (graphify-out/); nothing is committed to project repos.

User guide

See docs/USER-GUIDE.md for setup, onboarding new projects, using the skills, and known limitations.

Directory layout

Path Contents
docs/memory-system/ Architecture, ADRs, build plan, Graphify evaluation
docs/graphify/ Verified Graphify command handbook
docs/USER-GUIDE.md Practical usage guide
openspec/ Spec-driven change management (changes, specs)
graphify-interview, memory-systems-compared060326 Raw source transcripts (do not cite as fact)