// Your machine. Your models. Your code.
Proverbs is a fully self-contained, faith-based smart coding language — with its own built-in AI, a browser code editor, memory that never forgets, on-device model training, and 70+ commands. No cloud. No subscriptions. Nothing leaves your machine.
// What it does
Its own built-in AI, a browser code editor, project memory that sticks, and 70+ shortcut commands.
Drop a model file into ~/.proverbs/models/ and start coding.
No external services. No internet required after setup.
/ide./remember saves facts about your project permanently. Auto-injected into every session so Proverbs never forgets your stack, conventions, or decisions./train tokenizer, /train embed, /train prune./goal <condition> — Proverbs loops autonomously until the condition is met. Like Claude Code's agentic mode, fully local./backend auto finds it for you./cwd change./scan detects your stack, import aliases, conventions, and git history. Injected into every prompt automatically.~/.proverbs/plugins/ to add custom tools the model can call — same interface as built-in tools./cloud key to route through Claude (Haiku by default, Opus on demand) for frontier-quality coding — with automatic fallback to your local model when offline. Or set ANTHROPIC_API_KEY/OPENAI_API_KEY directly. You choose: fully local, or cloud-fast./branch saves a named conversation checkpoint. /checkout restores it. Never lose a working state./rewind N rolls back N conversation turns. /undo restores any file write. Full time-travel for both chat and code./agents spawns 3 parallel sub-instances each attacking the task from a different angle. /fork runs a sub-task non-blocking./security runs a full OWASP audit — injection, XSS, hardcoded secrets, missing auth — entirely on local inference. /review high for code review./sandbox on blocks destructive bash patterns before they reach your shell. Rate limiting, auth middleware, audit log — all built in./profile shows live latency, tokens/sec, cache hit rate, memory usage, and backend stats. Know exactly what's happening under the hood./update downloads the latest release and hot-swaps itself with zero downtime. No npm, no package manager required.// Browser interface
Run /ide from the terminal to open a full development environment at localhost:4400.
File tree, tabbed editor, built-in smart terminal, git panel — all powered by the same AI running on your machine.
// Get started
One command. The built-in AI starts automatically — just drop a model file into
~/.proverbs/models/ and run proverbs. No external setup.
Node.js 18+ and installs it if missing via HomebrewProverbs AI automatically — nothing else to installproverbs command globally. Run proverbs to chat or proverbs /ide for the browser IDE.Node.js LTS silently if not presentProverbs AI automatically — nothing else to installproverbs CLI globally and registers it in PATHproverbs to chat or proverbs /ide for the browser IDE..gguf model into ~/.proverbs/models/ — or let the installer fetch onenpm install -g proverbs-aiproverbs in any project folder, or proverbs /ide for the browser IDE.// How it stacks up
Claude Code is excellent — Proverbs is what you run when you want no cloud dependency, full data privacy, and the ability to train your own model.
| Feature | Proverbs | Claude Code |
|---|---|---|
| Cost | Free forever | Per token |
| Works offline | ✓ | ✗ |
| Data privacy | 100% local | Cloud processed |
| Browser IDE | ✓ (VS Code-style, /ide) | ✗ |
| Persistent project memory | ✓ (/remember, auto-injected) | CLAUDE.md only |
| File read / write / patch | ✓ | ✓ |
| Bash execution | ✓ | ✓ |
| Git integration | ✓ | ✓ |
| Web search | ✓ (no API key) | ✓ |
| Session persistence | ✓ (save/resume/branch) | ✗ |
| Train your own model | ✓ (fine-tune on your own code) | ✗ |
| Near-instant repeat responses | ✓ (40–80% faster follow-ups) | — |
| Goal / autonomous mode | ✓ (/goal condition) | ✓ |
| Code review | ✓ (/review low|med|high) | ✓ |
| Conversation branches | ✓ (/branch, /checkout) | ✗ |
| Plugin system | ✓ (JS files in plugins/) | MCP servers |
| Self-critique loop | ✓ | ✗ |
| Test runner integration | ✓ (jest, vitest, pytest) | ✗ |
| Security auditor | ✓ (OWASP, local) | ✗ |
| Multi-agent mode | ✓ (/agents, /fork) | ✓ |
| Where the AI runs | Built-in · LM Studio · Jan · your own server | Anthropic cloud only |
| Context window | 32k–128k (model dependent) | 200k |
| Reasoning quality | Good (qwen2.5-coder 1.5b–7b, codestral 22b) | Excellent (Claude 4) |
| Cloud model fallback | Direct Anthropic / OpenAI | Anthropic only |