How long does the integration take?

Change one base URL in an OpenAI-compatible client, or install the Python or TypeScript SDK; the quickstart routes a first request in a few minutes.

Will this lock us into another vendor?

No. The router is Apache-2.0 open source, your provider keys stay yours, and the API is OpenAI-compatible, so leaving is a change of base URL.

What happens when a provider fails?

The router falls back to the next model your policy allows and records the fallback in the trace, so an outage costs a retry, not an incident.

90 days of the enterprise, pro and team plans free, no card needed. See the plans

OpenSmartRoute

nestbrowse-info-seeking - Skill - OpenSmartRoute

Skillv1.0.0

nestbrowse-info-seeking

Name: nestbrowse-info-seeking
Author: ADu2021

Scale information-seeking agents via nested architecture separating outer reasoning from inner page exploration. Minimal toolkit (search, visit, click, fill) handles dynamic web interactions, inner lo

by ADu2021(0) 0 installs

Free

Free account. Installing gives you the manifest plus copy-paste snippets.

See reviews

About

Imported from ADu2021/skillXiv (skills/skillxiv-v0.0.2-claude-opus-4.6/nestbrowse-info-seeking/SKILL.md). Install upstream with npx skills add ADu2021/skillXiv --skill nestbrowse-info-seeking. Copyright stays with the author (MIT).

Overview

Nested architecture decouples reasoning from page content extraction.

Core Technique

Nested Loop Structure:

# Outer loop: reasoning
reasoning = outer_agent.think(state)
tool_call = outer_agent.select_tool()

# Inner loop: extract relevant content
relevant_content = inner_agent.extract(page, goal)

# Return minimal content to reasoning

When to Use

Use when: Information-seeking agents, large-scale web interaction, efficiency critical.

References

Nested outer/inner loop architecture
Minimal browser toolkit
Content filtering before context injection

Use it

Copy one of these into your project. Installing also returns the manifest and these snippets.

Installed into a catalogue, chosen by a router

Install nestbrowse-info-seeking and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

Photo: RDNE Stock project

For the business

What it costs to adopt - in engineering time.

Same client, same code
One base URL
The OpenAI-compatible endpoint answers your existing SDK calls; model=auto lets the router choose.
The SDKs
One URL, every vendor
No vendor lock-in
Point your OpenAI-compatible client at one address; add, swap or retire providers in the catalogue without touching application code.
Every vendor side by side
Next eligible model answers
Failover built in
When a provider is down or over quota the request moves on; the trace says it did.

# after Install: the listing is in your workspace's routing pool - a plan picks it for its slot
curl -s -X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'

Manifest

An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.

adu2021-skillxiv-nestbrowse-info-seeking.ocm.jsonjson

{
  "ocm": "1",
  "id": "adu2021-skillxiv-nestbrowse-info-seeking",
  "kind": "skill",
  "name": "nestbrowse-info-seeking",
  "description": "Scale information-seeking agents via nested architecture separating outer reasoning from inner page exploration. Minimal toolkit (search, visit, click, fill) handles dynamic web interactions, inner loop filters content before context injection, multi-task learning trains outer/inner jointly—enabling 4B models to match larger competitors.",
  "publisher": "ADu2021",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "general"
    ],
    "tags": [
      "skill-md",
      "information-seeking",
      "web-agents",
      "nested-architecture",
      "efficiency",
      "github"
    ],
    "languages": [
      "en"
    ]
  },
  "quality_prior": 0.6,
  "examples": [
    "Scale information-seeking agents via nested architecture separating outer reasoning from inner page exploration. Minimal toolkit (search, visit, click, fill) handles dynamic web interactions, inner loop filters content before context injection, multi-task learning trains outer/inner jointly—enabling 4B models to match larger competitors."
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "github",
      "repository": "https://github.com/ADu2021/skillXiv",
      "path": "skills/skillxiv-v0.0.2-claude-opus-4.6/nestbrowse-info-seeking/SKILL.md",
      "ref": "10b9e2ab98d22d657cdca33fadb35feaf4a2e26b",
      "url": "https://github.com/ADu2021/skillXiv/blob/10b9e2ab98d22d657cdca33fadb35feaf4a2e26b/skills/skillxiv-v0.0.2-claude-opus-4.6/nestbrowse-info-seeking/SKILL.md",
      "key": "ADu2021/skillXiv/skills/skillxiv-v0.0.2-claude-opus-4.6/nestbrowse-info-seeking/SKILL.md"
    },
    "license": "MIT"
  },
  "instructions": "## Overview\n\nNested architecture decouples reasoning from page content extraction.\n\n## Core Technique\n\n**Nested Loop Structure:**\n\n```python\n# Outer loop: reasoning\nreasoning = outer_agent.think(state)\ntool_call = outer_agent.select_tool()\n\n# Inner loop: extract relevant content\nrelevant_content = inner_agent.extract(page, goal)\n\n# Return minimal content to reasoning\n```\n\n## When to Use\n\nUse when: Information-seeking agents, large-scale web interaction, efficiency critical.\n\n## References\n\n- Nested outer/inner loop architecture\n- Minimal browser toolkit\n- Content filtering before context injec",
  "cost": {
    "context_tokens": 151
  }
}

Fetch it by URL: GET /api/v1/registry/adu2021-skillxiv-nestbrowse-info-seeking/manifest?version=1.0.0

About

Overview

Core Technique

When to Use

References

Use it

Install nestbrowse-info-seeking and it becomes one more candidate the router can pick - when it fits.

What it costs to adopt - in engineering time.

One base URL

No vendor lock-in

Failover built in

Manifest

Reviews