Focused, open source tools for AI development, testing, and governance. From code review to prompt optimisation, each tool solves a specific problem in the AI engineering workflow.
Agentic CI Gateway: tiered code review via cheap critics plus frontier adjudication. Automate early-stage code review with AI agents, escalate to senior engineers.
View on GitHub
Turn fuzzy intent into hardened, machine-readable specifications. Convert natural language requirements into formal, executable specifications for AI systems.
View on GitHub
Intent-driven model & prompt optimiser. Takes a paragraph of intent, returns an optimised system prompt, recommended model, and regression eval suite.
View on GitHubAll our tools are open source and ready for contribution. Join us on GitHub. Issues and pull requests welcome.
Alongside these tools, the Odokai platform handles production AI deployment, governance and orchestration. Ask us about our enterprise offerings.
Notes on governed models, operational automation, and how teams move from AI-assisted pilots to broader adoption.
18 October 2026
The ICO has opened a call for evidence on agentic AI, closing 20 November. What it covers, six checks before an agent touches personal data, and what does not change yet.
Read more16 September 2026
Five stages, three approaches, and a warning about the traps. How SMEs cut invoice handling time by 70 to 90 percent, and what the first working version looks like.
Read more