Dirac ⚛️

Agent with a singular focus on token efficieny. Reduces API costs by more than 50%, produces better and faster work (see proof below). Uses Hash anchored parallel edits, AST manipulation and a whole lot of neat optimizations.

Dirac is designed to be the most token-efficient and accurate AI agent for software development. It understands your codebase structurally and makes precise edits that maintain code integrity.

Head to Head comparison

🚀 Key Features

• Hash-Anchored Edits: Dirac uses stable line hashes to target edits with extreme precision, avoiding the "lost in translation" issues of traditional line-number based editing.
• AST-Native Precision: Built-in understanding of language syntax (TypeScript, Python, C++, etc.) allows Dirac to perform structural manipulations like function extraction or class refactoring with 100% accuracy.
• Multi-File Batching: Dirac can process and edit multiple files in a single LLM roundtrip, significantly reducing latency and API costs.
• High-Bandwidth Context: Optimized context curation keeps the agent lean and fast, ensuring the LLM always has the most relevant information without wasting tokens.
• Autonomous Tool Use: Dirac can read/write files, execute terminal commands, use a headless browser, and more—all while keeping you in control with an approval-based workflow.

📦 Installation

VS Code Extension

Install Dirac from the VS Code Marketplace.

🛠️ Getting Started

1. Open the Dirac sidebar in VS Code.
2. Configure your preferred AI provider (Anthropic, OpenAI, OpenRouter, etc.).
3. Start a new task by describing what you want to build or fix.
4. Watch as Dirac explores your codebase and proposes changes.

📄 License

Dirac is licensed under the Dirac Community License Agreement v1.0.

• FREE forever for individuals, hobbyists, academics, and non-profits.
• FREE forever for early-stage companies (revenue < $1M AND funding < $1M).
• PAID commercial license required for larger enterprises.

See LICENSE.md for full details.

🤝 Acknowledgments

Dirac is a fork of the excellent Cline project. We are grateful to the Cline team and contributors for their foundational work.

Built with ❤️ by Dirac Delta Labs