Your AI brain, externalized. It remembers everything you do, then becomes whatever role you need. Same skeleton can run as your chief of staff, lawyer, PM, or investigator. Plain markdown. Built on Claude Code.
Hook Claude Code
Runs when a session starts on startup, startup, resume, clear and compact, executing git-health-check.sh, session-start.py, md-prune.py, lessons-index.py, auto-update.sh, open-loops.py, fleet-board-refresh.py, memory-confidence-surface.py, memory-scores-surface.py, memory-freshness-check.py…
Hook Claude Code
Runs when you submit a prompt, before the agent sees it, executing token-guard.py, voice-dna-loader.py and lessons-inject.py via python3 (3 commands). From assafkip/kipi-system.
Hook Claude Code
Runs before the agent uses a tool for Write, Edit, MultiEdit and Bash tool calls, executing token-guard.py, read-first-gate.py, claude-path-write-guard.py and merge-bypass-gate.py via python3 (4 commands). From assafkip/kipi-system.
Hook Claude Code
Runs after a tool call finishes for Edit, Write, MultiEdit, Bash, Edit, Write, MultiEdit, Edit, Write, MultiEdit, Write, Edit and MultiEdit tool calls, executing token-guard.py, claude-path-write-guard.py, claude-integrity-tripwire.py, prompt-only-enforcement-guard.py, enforced-claim-lint.py, wiring-check.py…
Hook Claude Code
Runs after the context is compacted, executing post-compact.sh via bash. From assafkip/kipi-system.
Hook Claude Code
Runs when the agent finishes a response, executing code_claim_grounding_guard.py, blocked-claim-evidence-lint.py, voice-stop-gate.py, auto-commit.py, stop-logger.sh, memory_autocapture.py and kb-graph-guard.py (7 commands). From assafkip/kipi-system.