Issue Station
Sign In
Tools hereToolbox

openclaw - 💡(How to fix) Fix Feature Request: Add TinyFish as a web_search provider [1 comments, 2 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
openclaw/openclaw#77817•Fetched 2026-05-06 06:20:56
View on GitHub
Comments
1
Participants
2
Timeline
2
Reactions
2
Author
baptitse-jnbaptitse-jn
Participants
baptitse-jnbaptitse-jnclawsweeper[bot]clawsweeper[bot]
Timeline (top)
closed ×1commented ×1

Add TinyFish as a native web_search provider, alongside existing providers like Brave Search.

Root Cause

Add TinyFish as a native web_search provider, alongside existing providers like Brave Search.

Code Example

GET https://api.search.tinyfish.ai
Header: X-API-Key: <key>
Query params: q, page, language, country, etc.

---

{
  "query": "search term",
  "results": [
    {
      "position": 1,
      "site_name": "Example",
      "title": "Result Title",
      "snippet": "Result snippet...",
      "url": "https://example.com/page"
    }
  ],
  "total_results": 42
}

---

POST https://api.fetch.tinyfish.ai
Header: X-API-Key: <key>
Body: { "url": "https://example.com" }
RAW_BUFFERClick to expand / collapse

Summary

Add TinyFish as a native web_search provider, alongside existing providers like Brave Search.

What is TinyFish?

TinyFish is a search API built specifically for AI agents. It offers:

  • Search API — structured web search results (title, snippet, URL)
  • Fetch API — web page content extraction

It is MCP-native and already works with Claude, Cursor, and other agent frameworks.

API Details

Search API

GET https://api.search.tinyfish.ai
Header: X-API-Key: <key>
Query params: q, page, language, country, etc.

Response Format

{
  "query": "search term",
  "results": [
    {
      "position": 1,
      "site_name": "Example",
      "title": "Result Title",
      "snippet": "Result snippet...",
      "url": "https://example.com/page"
    }
  ],
  "total_results": 42
}

Fetch API

POST https://api.fetch.tinyfish.ai
Header: X-API-Key: <key>
Body: { "url": "https://example.com" }

Why TinyFish?

Brave Search APITinyFish
CostPaid (free tier limited)Free with generous rate limits
Credit cardRequired for most plansNot required
Agent-focusedNoYes (MCP-native)
Structured resultsYesYes (title, snippet, URL, position)
Geo-targetingYesYes (country, language)
PaginationYesYes
Fetch/extractionSeparate tool neededBuilt-in Fetch API
Setup complexityModerateDead simple (one header, one endpoint)

Value for OpenClaw

  1. Zero-cost onboarding — new users can get web search working immediately without API keys or credit cards
  2. Simpler integration — straightforward REST API, minimal config
  3. Built for agents — TinyFish is purpose-built for AI agent workflows
  4. Fetch API included — could potentially replace or complement web_fetch as well
  5. Fallback provider — free tier makes it ideal as a default/fallback when other providers are unavailable

Proposed Implementation

  • Add tinyfish as a provider option in web_search config (alongside brave, etc.)
  • Support TINYFISH_API_KEY env var or config-based key
  • Map TinyFish response fields to OpenClaw's normalized search result format
  • Optionally integrate the Fetch API for web_fetch as well

Links

Happy to help test or contribute if there's interest.

extent analysis

TL;DR

Add TinyFish as a native web search provider by implementing its Search API and integrating it into the existing web search configuration.

Guidance

  • Review the TinyFish API documentation to understand the required query parameters and response format.
  • Implement the TinyFish Search API by sending a GET request to https://api.search.tinyfish.ai with the required X-API-Key header and query parameters.
  • Map the TinyFish response fields to OpenClaw's normalized search result format to ensure compatibility.
  • Consider integrating the TinyFish Fetch API for web_fetch to replace or complement existing functionality.

Example

// Example TinyFish search response
{
  "query": "search term",
  "results": [
    {
      "position": 1,
      "site_name": "Example",
      "title": "Result Title",
      "snippet": "Result snippet...",
      "url": "https://example.com/page"
    }
  ],
  "total_results": 42
}

Notes

The implementation details may vary depending on the specific requirements of OpenClaw's web search configuration and the desired level of integration with the Fetch API.

Recommendation

Apply workaround by integrating TinyFish as a native web search provider, as it offers a free tier with generous rate limits and a simple setup process, making it an attractive alternative to existing providers.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…
#api#mixed precision#training loop#device allocation#model download

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

openclaw - 💡(How to fix) Fix Feature Request: Add TinyFish as a web_search provider [1 comments, 2 participants]