A second brain for Claude Code.
Claude re-reads files it already saw. It scans entire directories to find one function. It doesn't know your conventions until you tell it again. OpenWolf gives it persistent project intelligence through invisible hooks. No workflow changes.
Claude is powerful. But it works blind.
Claude doesn't know what a file contains until it opens it. It can't tell a 50-token config from a 2,000-token module. It reads the same file three times in one session without noticing. It has no map of your project, no memory of past corrections, no awareness of what it already tried.
OpenWolf gives Claude a project index, a learning memory, and a token-aware read layer. It makes every session sharper from the first prompt.
Same project. Same prompts. Different setups.
Everything works invisibly
OpenWolf hooks into Claude Code's lifecycle. No commands to remember. It just makes every session smarter.
Invisible Enforcement
You type claude and work normally. Hooks fire automatically, tracking tokens, updating project maps, enforcing learned preferences.
Token Intelligence
Claude reads blind. OpenWolf gives it a file index with descriptions and token estimates before every read. If the description is enough, Claude skips the full file. Repeated reads are caught and flagged.
Zero Overhead
All hooks are pure Node.js file I/O. No network requests, no external APIs, no extra cost. OpenWolf runs entirely on your machine.
Self-Learning
Every correction you make gets logged. Every bug fix gets remembered. Every preference gets enforced. Claude gets smarter with every session -- without you repeating yourself.
Design QC
Capture full-page sectioned screenshots with one command. Claude evaluates the design inline. No external services, no extra cost.
Reframe
Ask Claude to help pick a UI framework. Built-in knowledge base covers 12 component libraries, from shadcn/ui to Aceternity UI to DaisyUI.
Three steps. Then invisible.
Initialize
Run one command in any project. Creates .wolf/ directory, registers hooks, scans all files.
Work Normally
Just use claude as you always do. Hooks fire invisibly, tracking, learning, enforcing. You don't interact with any of it.
Get Smarter
Every session, OpenWolf learns preferences, logs bugs, prevents repeated mistakes. View everything on the real-time dashboard.
The .wolf/ directory
Every project gets a .wolf/ folder containing state, learning memory, and configuration. Markdown is the source of truth.
anatomy.md
File index with descriptions and token estimates. Prevents unnecessary full-file reads.
cerebrum.md
Learned preferences, conventions, Do-Not-Repeat mistakes. Gets smarter every session.
memory.md
Chronological action log. Every read, write, and decision recorded per session.
buglog.json
Bug encounter and resolution memory. Searchable. Prevents re-discovering the same fix.
hooks/
6 Node.js hooks that fire on every Claude action. Pure file I/O, no network, no AI calls.
config.json
All settings with sensible defaults. Token ratios, cron schedules, dashboard port, exclude patterns.
The enforcement layer
Six hooks fire on every Claude action. They warn but never block. Pure Node.js. No network, no AI, no extra cost.