Omnigent - Nimble Docs

Overview

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:

export NIMBLE_API_KEY="your-api-key"

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:

spec_version: 1
name: research-agent
prompt: |
  You are a research assistant. Use web_search to ground your
  answers in current information from the web.

executor:
  type: omnigent
  model: databricks-claude-sonnet-4-6   # run on any model

tools:
  builtins:
    - name: web_search
      search_provider: nimble
      api_key: ${NIMBLE_API_KEY}

3. Run the agent

Reference the agent by its directory path:

omni run ./research-agent -p "What were the biggest AI model releases this month?"

The agent now calls Nimble whenever it searches the web.

Configuration

The web_search builtin accepts these keys under the Nimble provider:

search_provider

Required. Set to nimble to route web search through Nimble.

api_key

Required. Your Nimble API key. Use ${NIMBLE_API_KEY} to read it from the environment instead of hardcoding it in the spec.

max_results

Optional. Number of results to return, from 1 to 100. Defaults to 5. Values outside the range are clamped.

search_depth

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:

tools:
  builtins:
    - name: web_search
      search_provider: nimble
      api_key: ${NIMBLE_API_KEY}
      max_results: 10
      search_depth: deep

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.

​Overview

​Web search for any model

​Quick Start

​1. Get a Nimble API key

​2. Enable the provider in your agent spec

​3. Run the agent

​Configuration

​Additional Resources