Google Cloud introduces Open Knowledge Format to standardise AI agent context

Google Cloud has launched the Open Knowledge Format, an open source specification designed to standardise how organisational knowledge is structured for AI agents. This framework provides a consistent way to package curated data and context, ensuring that enterprise models have access to accurate and governed information.

For teams building production grade agents, this specification reduces the friction of data preparation and improves interoperability between different AI systems. It allows developers to maintain better governance over the context provided to models, directly addressing accuracy issues in enterprise environments.

  • Open specification for structuring curated knowledge and context for AI agents
  • Aims to improve accuracy by providing a standard way to store and retrieve organisational data
  • Designed to facilitate better governance and interoperability across enterprise AI platforms
AI Agents & Automation AI Apps & Platforms Generative AI
All AI news

More AI news

Models

Jensen Huang advocates for open weight models to democratise enterprise AI

NVIDIA CEO Jensen Huang used his debut post on X to highlight the transformative power of open weight AI models across all industries. He argued that making these models accessible will accelerate global innovation and significantly improve productivity for developers worldwide. This public stance reinforces the growing industry momentum behind open source architectures.

Models

Claude Opus 5 (max) takes the top spot on the SevenLab AI leaderboard

Anthropic's Claude Opus 5 (max) has officially reached the number one position on the SevenLab AI leaderboard. This ranking is derived from a value adjusted analysis of performance data provided by Artificial Analysis. The model now leads the ranking which balances performance metrics with cost considerations for enterprise applications.

Models

Kx launches early access programme for kdb.ai vector database

Kx has introduced an early access programme for kdb.ai, a vector native database designed for real time and high volume time series analytics. The initiative allows developers to experiment with advanced vector search capabilities integrated into high performance data environments.

Ready to build something
extraordinary?

15 minutes. No pitch deck. Just a conversation about what AI can do for your team.

Talk directly with our AI specialists

15 min, no strings
No sales pressure
Prototype in 7 days