CLI for the CASS (Contextual Agent Session Search) knowledge flywheel. Automates knowledge capture, retrieval, and reinforcement learning across Claude Code sessions.
go install github.com/boshu2/agentops/cli/cmd/ao@latest# From your repo root: create `.agents/` + register hooks
ao init --hooks
# Verify installation
ao hooks testThat's it. Knowledge now flows automatically between sessions.
SessionStart: Injects relevant prior knowledge weighted by freshness and utility.
SessionEnd: Extracts learnings and updates the feedback loop.
| Command | Purpose |
|---|---|
ao inject |
Inject knowledge into current session |
ao forge transcript |
Extract learnings from session transcripts |
ao feedback-loop |
Update utility scores based on outcomes |
ao metrics report |
View flywheel health and escape velocity |
Track progress through the RPI (Research → Plan → Implement) workflow:
ao ratchet gate plan # Check if ready for planning
ao ratchet record research # Lock research completion
ao ratchet status # View current progressao init --hooks # Recommended: repo setup + hooks (SessionStart + Stop)
ao init --hooks --full # Optional: all 8 lifecycle events
# Lower-level (hooks only; does not create `.agents/`)
ao hooks init # Generate hooks configuration
ao hooks install # Install to Claude Code
ao hooks show # View current hooks
ao hooks test # Verify hooks workao lookup --query "kubernetes" # Look up knowledge about k8s
ao search "error handling" # Search knowledge baseSync Claude Code tasks with CASS maturity system:
ao task-sync # Sync current tasks
ao task-sync --promote # Promote completed tasks
ao task-status # View maturity distributionThe flywheel equation:
dK/dt = I(t) - δ·K + σ·ρ·K
- δ = 0.17/week - Knowledge decay rate (Darr et al.)
- σρ > δ - Escape velocity for compounding knowledge
See docs/HOOKS.md for details.
For a complete command reference, see docs/COMMANDS.md.
MIT