Skip to main content

​
Overview

A Databricks-hosted agent in Omnigent running grounded web search through Nimble

Omnigent is an open-source AI agent framework and meta-harness from Databricks. It gives you one orchestration layer over Claude Code, Codex, Cursor, Pi, and agents you write yourself, with shared sessions, policies, and sandboxing. Nimble ships as a first-class web_search provider in Omnigent. Set search_provider: nimble in any agent spec and the agent gets grounded, live web results from Nimble’s Search API. No fork, no plugin.

​
Web search for any model

Omnigent lets you run any model and swap harnesses with a one-line change. Nimble brings that same flexibility to web search. The web_search builtin pairs each model with a search backend. Set search_provider: nimble and any model gets grounded web search through Nimble: Claude, Llama, and the Databricks-hosted models you run in Omnigent. One model-agnostic backend, with anti-bot handling, JS rendering, and geo-targeting underneath. Databricks-hosted models get grounded, live web search through Nimble out of the box.

​
Quick Start

​
1. Get a Nimble API key

Get your API key from Nimble’s dashboard (free trial available) and export it:

​
2. Enable the provider in your agent spec

A custom agent lives in its own directory with a config.yaml at the root. Create research-agent/config.yaml, add the web_search builtin, and set search_provider: nimble:

​
3. Run the agent

Reference the agent by its directory path:
The agent now calls Nimble whenever it searches the web.

​
Configuration

The web_search builtin accepts these keys under the Nimble provider:
Required. Set to nimble to route web search through Nimble.
Required. Your Nimble API key. Use ${NIMBLE_API_KEY} to read it from the environment instead of hardcoding it in the spec.
Optional. Number of results to return, from 1 to 100. Defaults to 5. Values outside the range are clamped.
Optional. Controls the speed-vs-richness tradeoff. Defaults to lite.
  • lite: titles, URLs, and snippets. Lowest latency, best for broad discovery.
  • deep: full real-time page extraction for each result. Higher latency, richer content.
See Search Depth for details.
A fully configured provider looks like this:

​
Additional Resources

Omnigent on GitHub

The open-source agent framework and meta-harness.

Omnigent Custom Agents

Define and run a custom agent: directory layout, config.yaml, and the run command.

Nimble Search API

The Search endpoint behind the provider: parameters and response format.

Nimble on Databricks

The full Databricks integration: Marketplace MCP, Genie, and SQL-native enrichment.