CLI tools for managing a "second brain" (PARA-style markdown notes) + Lobster workflow pipelines.
Built by Alfred in 30 minutes.
AI assistants burn tokens orchestrating multi-step tasks. 10 tool calls for an inbox triage? Expensive and fragile.
Move orchestration into deterministic workflows with explicit approval checkpoints.
# Clone the repo
git clone https://github.com/bloomedai/brain-cli.git
# Add to PATH
export PATH="$PATH:$(pwd)/brain-cli/bin"
# Optional: Install Lobster for pipelines
npm install -g @clawdbot/lobster
brain-categorize uses AI when available, falls back to bilingual keyword matching (EN/DE).
Backends (auto-detected):
claude CLI (Anthropic)ollama with llama3.2Force mode:
USE_AI=false brain-categorize # Keywords only
USE_AI=true brain-categorize # Require AI (fails if unavailable)
brain stats # Overview of all brains
brain inbox [brain] # List inbox items
brain tasks [brains] # Find open [ ] todos
brain scan [days] # Find stale files (default: 7 days)
brain memory list # List recent memory files
brain memory daily # Output daily memories as JSON
For piping between commands:
JSON_MODE=true brain inbox all | brain-categorize | brain-file --approve
| Pipeline | Description |
|---|---|
weekly-review.lobster | Scan stale files β summarize β archive (approval) |
inbox-triage.lobster | Collect β categorize β file (approval) |
memory-consolidation.lobster | Distill daily memories β MEMORY.md (approval) |
shared-task-sync.lobster | Sync family-tagged tasks to shared brain (approval) |
# With Lobster CLI
lobster run pipelines/inbox-triage.lobster
# Via Clawdbot (if Lobster tool enabled)
# Just ask: "run the inbox triage pipeline"
The CLI expects a PARA-style structure:
brain/
βββ jero/ # Personal brain
βββ jeanine/ # Partner's brain (optional)
βββ shared/ # Shared brain (optional)
β βββ 0-inbox/
β βββ 1-projects/
β βββ 2-areas/
β βββ 3-resources/
β βββ 4-archive/
Configure the root path:
export BRAIN_ROOT="$HOME/notes/brain"
Less tokens. More deterministic. Full audit trail.
MIT
Built with πͺ by Alfred & @plattenschieber
3 commits
Shell
100.0%
CLI tools for managing a "second brain" (PARA-style markdown notes) + Lobster workflow pipelines.
Built by Alfred in 30 minutes.
AI assistants burn tokens orchestrating multi-step tasks. 10 tool calls for an inbox triage? Expensive and fragile.
Move orchestration into deterministic workflows with explicit approval checkpoints.
# Clone the repo
git clone https://github.com/bloomedai/brain-cli.git
# Add to PATH
export PATH="$PATH:$(pwd)/brain-cli/bin"
# Optional: Install Lobster for pipelines
npm install -g @clawdbot/lobster
brain-categorize uses AI when available, falls back to bilingual keyword matching (EN/DE).
Backends (auto-detected):
claude CLI (Anthropic)ollama with llama3.2Force mode:
USE_AI=false brain-categorize # Keywords only
USE_AI=true brain-categorize # Require AI (fails if unavailable)
brain stats # Overview of all brains
brain inbox [brain] # List inbox items
brain tasks [brains] # Find open [ ] todos
brain scan [days] # Find stale files (default: 7 days)
brain memory list # List recent memory files
brain memory daily # Output daily memories as JSON
For piping between commands:
JSON_MODE=true brain inbox all | brain-categorize | brain-file --approve
| Pipeline | Description |
|---|---|
weekly-review.lobster | Scan stale files β summarize β archive (approval) |
inbox-triage.lobster | Collect β categorize β file (approval) |
memory-consolidation.lobster | Distill daily memories β MEMORY.md (approval) |
shared-task-sync.lobster | Sync family-tagged tasks to shared brain (approval) |
# With Lobster CLI
lobster run pipelines/inbox-triage.lobster
# Via Clawdbot (if Lobster tool enabled)
# Just ask: "run the inbox triage pipeline"
The CLI expects a PARA-style structure:
brain/
βββ jero/ # Personal brain
βββ jeanine/ # Partner's brain (optional)
βββ shared/ # Shared brain (optional)
β βββ 0-inbox/
β βββ 1-projects/
β βββ 2-areas/
β βββ 3-resources/
β βββ 4-archive/
Configure the root path:
export BRAIN_ROOT="$HOME/notes/brain"
Less tokens. More deterministic. Full audit trail.
MIT
Built with πͺ by Alfred & @plattenschieber
3 commits
Shell
100.0%