vultr/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-05-05 13:30:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

Updated Brave information

Browse Source
This commit is contained in:
Henry Loenwind
2026-02-25 21:44:25 +01:00
committed by Gustavo Madeira Santana
parent dbccc73d7a
commit 0317bd6bc0
2 changed files with 9 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
docs/brave-search.md
View File

@@ -36,6 +36,7 @@ OpenClaw uses Brave Search as the default provider for `web_search`.
## Notes
- The Data for AI plan is **not** compatible with `web_search`.
- Brave provides a free tier plus paid plans; check the Brave API portal for current limits.
- Brave provides paid plans; check the Brave API portal for current limits.
- Brave limits the use for AI, ruling out the "use the Search Results to create, evaluate, train, re-train, fine-tune, benchmark or otherwise improve artificial intelligence models or services offered by Customer or third parties". As long as you are not involved in AI model creation, don't use AI models that store usage data for improvement (e.g. many free OpenRouter models), or provide OpenClaw as a service for others, you _should_ be good. This is, however, not legal advice---Check the Terms of Service.
See [Web tools](/tools/web) for the full web_search configuration.

9
docs/tools/web.md
View File

@@ -33,7 +33,7 @@ These are **not** browser automation. For JS-heavy sites or logins, use the
| Provider | Pros | Cons | API Key |
| ------------------- | -------------------------------------------- | ---------------------------------------- | -------------------------------------------- |
| **Brave** (default) | Fast, structured results, free tier | Traditional search results | `BRAVE_API_KEY` |
| **Brave** (default) | Fast, structured results, ltd. no AI clause | Traditional search results | `BRAVE_API_KEY` |
| **Perplexity** | AI-synthesized answers, citations, real-time | Requires Perplexity or OpenRouter access | `OPENROUTER_API_KEY` or `PERPLEXITY_API_KEY` |
| **Gemini** | Google Search grounding, AI-synthesized | Requires Gemini API key | `GEMINI_API_KEY` |
| **Grok** | xAI web-grounded responses | Requires xAI API key | `XAI_API_KEY` |
@@ -94,9 +94,14 @@ Example: switch to Perplexity Sonar (direct API):
2. In the dashboard, choose the **Data for Search** plan (not “Data for AI”) and generate an API key.
3. Run `openclaw configure --section web` to store the key in config (recommended), or set `BRAVE_API_KEY` in your environment.
Brave provides a free tier plus paid plans; check the Brave API portal for the
Brave provides paid plans; check the Brave API portal for the
current limits and pricing.
Brave limits the use for AI, ruling out the "use the Search Results to create, evaluate, train, re-train, fine-tune, benchmark
or otherwise improve artificial intelligence models or services offered by Customer or third parties". As long as you are not
involved in AI model creation, don't use AI models that store usage data for improvement (e.g. many free OpenRouter models), or
provide OpenClaw as a service for others, you _should_ be good. This is, however, not legal advice---Check the Terms of Service.
### Where to set the key (recommended)
**Recommended:** run `openclaw configure --section web`. It stores the key in