Warden-AI

<p align="center"> <img src="https://raw.githubusercontent.com/rynald0cst0ltziam/Warden-AI/main/docs/assets/warden-banner.png" alt="Warden" width="800"> </p> <p align="center"> <strong>Verified context for AI coding agents.</strong> </p> <p align="center"> <strong>Your AI agent burns tokens on noise. Warden stops that.</strong> </p> <p align="center"> Less context. More signal. Verified. </p> <p align="center"> <a href="https://www.npmjs.com/package/warden-ai"><img src="https://img.shields.io/npm/v/warden-ai.svg?style=for-the-badge&color=blue" alt="npm"></a> <a href="LICENSE"><img src="https://img.shields.io/badge/license-PolyForm_Shield-yellow.svg?style=for-the-badge" alt="License"></a> <a href="#works-with-35-agents"><img src="https://img.shields.io/badge/works_with-35%2B_agents-orange.svg?style=for-the-badge" alt="35+ agents"></a> <a href="#trust-guard"><img src="https://img.shields.io/badge/verified_context-100%25_pass-brightgreen.svg?style=for-the-badge" alt="Verified Context"></a> <a href="#privacy"><img src="https://img.shields.io/badge/local_first-no_cloud-blue.svg?style=for-the-badge" alt="Local First"></a> <a href="https://warden-io.vercel.app"><img src="https://img.shields.io/badge/website-warden--io-blue.svg?style=for-the-badge" alt="Website"></a> </p> <br>

Every token your agent spends on noise is a token it didn't spend on your actual problem. Warden fixes this.

Warden is a local context layer for AI coding agents. It drops into Claude Code, Cursor, Codex, Windsurf, Cline, Gemini, and 30+ other agents. Install once. Warden removes unnecessary tool-output noise while preserving the lines the agent actually needs to see.

50-90% fewer tokens. Zero config. Zero cloud. Zero lock-in.

Benchmarked. 30-task suite. 72.3% overall reduction. 100% guard pass rate. 8ms avg overhead.

Why Warden?

Most context optimizers simply remove or summarize information. Warden verifies the reduction.

Raw agent output → Warden → Intelligent reduction → Verification → Agent

This is the differentiator: not just compression, but verified compression. You don't have to trust that Warden got it right — the trust guard proves it on every call.

Warden AI is a local context layer for AI coding agents. It is not a security firewall, authentication system, agent framework, or infrastructure management tool.

Install

All platforms (macOS, Linux, Windows, WSL):

npm install -g warden-ai && warden init

macOS / Linux / WSL (curl one-liner):

curl -fsSL https://raw.githubusercontent.com/rynald0cst0ltziam/Warden-AI/main/install.sh | bash

Windows (PowerShell one-liner):

irm https://raw.githubusercontent.com/rynald0cst0ltziam/Warden-AI/main/install.ps1 | iex

Windows users: do NOT use the curl command in CMD or PowerShell — bash triggers WSL on Windows. Use the PowerShell or npm command above.

~10 seconds · Node >= 22.5 · skips agents you don't have · safe to re-run

warden init does everything automatically:

| Step | What happens | |:-----|:-------------| | Register | Warden registered as MCP server in all detected agents (30+) | | Rules | Agent rules files written (CLAUDE.md, AGENTS.md, .cursorrules, etc.) | | Index | Code index built — call graph, imports, symbols, dead code | | Compress | Memory files compressed to save tokens every future session |

Trust guard

The trust guard is the non-negotiable rule:

Every non-annotation line in the pruned output must appear verbatim in the raw output. If it doesn't, the raw is shipped instead.

This means Warden removes lines, never rewrites them.

Safety net — always on

| Mechanism | What it does | |:----------|:-------------| | Trust guard | Every pruned line verified verbatim against raw. If altered, raw ships instead. | | Eval gate | Rules earn confidence through real samples before going live. | | CCR | Every cut reversible. Full original cached 7 days. warden_retrieve with --around and --lines. |

Privacy

No cloud. No API server. No telemetry. No analytics. No phone-home.
Your code, tool outputs, and pruning decisions stay in a local SQLite
file on your machine. It works on a plane.

Requirements

• Node.js >= 22.5 (uses built-in node:sqlite)
• Any MCP-compatible AI coding agent

Commands

| Command | What it does | |:--------|:-------------| | warden init | Register in all agents + write rules + build index + compress files | | warden serve | Run MCP server over stdio | | warden status | Rules, confidence, tokens saved, recent memories | | warden hud | Live terminal HUD | | warden dashboard | Web UI at http://localhost:7878 | | warden doctor | Health check | | warden benchmark | Run benchmarks | | warden ccr | CCR status | | warden memory list | List stored memories | | warden task-report | Per-task report |

Works with 35+ agents

| | | | | | | |:---:|:---:|:---:|:---:|:---:|:---:| | Claude Code | Claude Desktop | Cursor | Windsurf | Codex CLI | Cline | | Roo Code | Continue | VS Code Copilot | Zed | JetBrains | Amazon Q | | Gemini CLI | Antigravity | Aider | Goose | OpenHands | + more |

License

PolyForm Shield 1.0.0 — source-available, free for everyone including commercial use. See LICENSE.

---

<p align="center"> <a href="#install">Install</a> · <a href="https://warden-io.vercel.app">Website</a> · <a href="https://github.com/rynald0cst0ltziam/Warden-AI">GitHub</a> · <a href="https://www.npmjs.com/package/warden-ai">npm</a> </p> <p align="center"> Made with ⚡ by Rynaldo Stoltz </p>