by GMaN1911
Working memory for Claude Code - persistent context and multi-instance coordination
# Add to your Claude Code skills
git clone https://github.com/GMaN1911/claude-cognitiveWorking memory for Claude Code — persistent context and multi-instance coordination
Claude Code is powerful but stateless. Every new instance:
With large codebases (50k+ lines), this becomes painful fast.
Claude Cognitive gives Claude Code working memory through two complementary systems:
Attention-based file injection with cognitive dynamics:
Files decay when not mentioned, activate on keywords, and co-activate with related files.
Multi-instance state sharing for long-running sessions:
No comments yet. Be the first to share your thoughts!
pool blocks for critical coordinationToken Savings:
Average: 64-95% depending on codebase size and work pattern.
Developer Experience:
Validated on:
# Clone to your home directory
cd ~
git clone https://github.com/GMaN1911/claude-cognitive.git .claude-cognitive
# Copy scripts
cp -r .claude-cognitive/scripts ~/.claude/scripts/
# Set up hooks (adds to existing config)
cat .claude-cognitive/hooks-config.json >> ~/.claude/settings.json
Note: The repo contains a
.claude-dev/directory for development/dogfooding purposes only. Do not copy this to your projects—it's not part of the user-facing installation. Use your own project-local.claude/directory instead (see step 2).
cd /path/to/your/project
# Create .claude directory
mkdir -p .claude/{systems,modules,integrations,pool}
# Copy templates
cp -r ~/.claude-cognitive/templates/* .claude/
# Edit .claude/CLAUDE.md with your project info
# Edit .claude/systems/*.md to describe your architecture
# Add to ~/.bashrc for ...