Introducing Omnigent: The Ultimate Meta-Harness for AI Agents
Summary
Omnigent is a new open-source meta-harness for AI agents that provides a unified interface for composition, control, and collaboration across multiple models and agent workflows. It enables stateful, data-centric policies for guardrails and allows real-time sharing and steering of live agent sessions with teammates.
Summary generated by brickster.ai from the video transcript.
More from Databricks
NewsHow DEFRA and Natural England Accelerate Peatland Restoration with AI and Databricks
DEFRA and Natural England utilize AI and Databricks to accelerate peatland restoration by automating the mapping of peatland features and peat dams across England. This technology significantly reduces the time required for mapping, enabling faster identification and restoration of these crucial carbon-storing habitats.
NewsAI Stack Explained in 3 Layers (LLM, Agent Harness, Omnigent)
The AI stack now includes a third layer, the meta harness, which sits above individual agent harnesses. This meta harness, exemplified by Databricks' open-sourced Omnigent, allows for routing queries to appropriate agents and orchestrating tasks across multiple agents, enabling seamless interaction and context sharing between them.
NewsWhat’s coming next to Free Edition
Databricks announces the availability of Genie, GPUs, Agent Hooks, Lakehouse, and Lake Flow Designer on its Free Edition. This update provides virtually all of Databricks' production platform features for free, enabling users to learn and build data and AI projects.
NewsDatabricks + Panther: advancing the security lakehouse
Databricks acquired Panther, a cybersecurity company that developed an AI SOC platform to make security teams smarter and faster. Panther's platform helps security teams detect and respond to threats and manage compliance by leveraging large datasets without requiring deep data infrastructure expertise.
CommunityDefending against a tidal wave of AI attacks with Lakewatch, the agentic security Lakehouse
Databricks introduces LakeWatch, an agentic security lakehouse designed to defend against AI-powered attacks by enabling security and data teams to work together. It allows for the ingestion and analysis of all security data, automates detection rule creation and incident investigation using AI agents, and breaks down proprietary data silos.
ReleasesIntroducing CustomerLake – the agentic CDP built in Databricks
Databricks introduces CustomerLake, an agentic Customer Data Platform (CDP) built within the Databricks Lakehouse, designed to power "infinity campaigns" for real-time, one-to-one customer personalization. CustomerLake features Profile Agents for automated customer 360 data creation and Campaign Agents for generating and managing continuously adapting, personalized marketing campaigns.