Mindstone's Rebel Automates Enterprise AI Model Selection

AI agent orchestration platforms are proliferating, but London-based Mindstone's Rebel stands out as a promising solution. Launched this week, Rebel is a local-first, agentic AI operating system distributed under a 'Fair Source' license, allowing teams of under 100 users to adopt and customize it for free. The platform's core feature is its simplicity and customizability, based on markdown files and an organizational memory layer that ensures agents use the enterprise's preferred AI models for each task.

Rebel's architecture stores its state, prompts, task instructions, and memory hierarchy in local markdown files, allowing users to inspect, move, or modify them as needed. A primary configuration file, agents.md, acts as the agent's core instruction layer and runtime boundary. This approach reduces costs and vendor lock-in, as companies can easily move their data and workflows elsewhere if needed.

The platform enables multi-model orchestration, breaking tasks into parts and routing different steps to different models, including local and cloud-based ones. This feature allows enterprises to control costs and security, using cheaper models for routine work and more expensive models for complex reasoning. Rebel also lets users create repeatable AI workflows, saving multi-step procedures as 'skills' and adjusting agent behavior with 'operators.' Mindstone CTO Greg Detre emphasizes the importance of shared memory in enterprise AI, enabling agents to reliably use the enterprise's preferred AI models for each task.

'Shared memory is the most empowering thing you could possibly do with a knowledge-worker AI,' Detre said. 'You get this feeling of being a super-organism as a company that just gets smarter and smarter.' Rebel is available now for macOS and Windows, with Linux support in development. Mindstone has raised $5 million from private investors, including Pearson Ventures, Moonfire Ventures, and Zanichelli Venture.

The company points to customer rollout as early proof of Rebel's effectiveness. Epignosis, a 250-person workforce, deployed Rebel across its sales, engineering, product, finance, and customer success teams, recapturing the equivalent capacity of eight full-time roles over a 12-week deployment. Why this matters: Mindstone's Rebel addresses a critical challenge in enterprise AI adoption: ensuring that AI systems are not only powerful but also reliable, secure, and transparent.

By automating the selection of AI models for each task and subtask, Rebel enables enterprises to scale AI workflows while maintaining control over costs and security. This approach also gives developers and businesses a way to inspect and trust AI systems, which is essential for widespread adoption. As companies move from AI experimentation to AI operations, Rebel's shared-memory design and local-first architecture may become a key enabler of successful AI transformations.