jared
/
cc-os
1
0
Fork 0
Code Issues 17 Pull Requests Packages Projects Releases Wiki Activity
90 Commits 2 Branches 0 Tags 2.9 MiB
Python 54.9%
Ruby 36.5%
Shell 7.8%
JavaScript 0.8%
Go to file
jared ef8b7e4a52 os-doc-hygiene: deterministic file_length scanner signal (issue #25 part 1) 
Objective signal (line count + estimated tokens) fires when either
threshold is exceeded; defaults 400 lines / 4000 tokens, configurable via
constructor and --max-lines/--max-tokens. Injectable token estimator for
tests. Suite: 286 passed. Parts 2-3 (implementation-status distill +
index+PD convention ADR) remain human-gated.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CLeMz48rvG3s9XpAsDxeho
 		2026-07-13 08:06:48 -04:00
bin Fix skill namespacing (drop name: frontmatter), add refresh-plugins, wire eval howto 2026-07-04 14:01:58 -04:00
docs ADR-030: read-only work uses plan mode; no /readonly shortcut 2026-07-13 08:06:48 -04:00
openspec openspec: archive completed add-os-status-plugin change, sync specs to main 2026-07-10 10:08:17 -04:00
plugins os-doc-hygiene: deterministic file_length scanner signal (issue #25 part 1) 2026-07-13 08:06:48 -04:00
.gitignore os-status: aggregated in-process SessionStart status checks (ADR-022) 2026-07-07 12:46:10 -04:00
CLAUDE.md os-context: prompt-composer plugin supersedes os-orchestration; prompt files authored (ADR-031) 2026-07-13 08:06:48 -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
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 automatically — memory-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)