# Web Search Plus developer resources

Canonical developer index for **Web Search Plus** (`websearchplus`, `web-search-plus`, `web_search_plus`).

This page exists so agents and search engines can find the docs, repos, and install commands by product name. HTML twin: [/developers](/developers). Site index: [/llms.txt](/llms.txt).

## What to install

| Surface | Package / repo | Command or URL |
| --- | --- | --- |
| Hermes Agent plugin | [hermes-web-search-plus](https://github.com/robbyczgw-cla/hermes-web-search-plus) | tools `web_search_plus`, `web_extract_plus` |
| MCP server | [web-search-plus-mcp](https://github.com/robbyczgw-cla/web-search-plus-mcp) | `uvx --from web-search-plus-mcp==4.1.1 web-search-plus-mcp` |
| PyPI | [web-search-plus-mcp](https://pypi.org/project/web-search-plus-mcp/) | same package |
| OpenClaw skill | [web-search-plus](https://github.com/robbyczgw-cla/web-search-plus) | ClawHub skill |
| OpenClaw plugin | [web-search-plus-plugin](https://github.com/robbyczgw-cla/web-search-plus-plugin) | ClawHub plugin |
| NanoClaw | [nanoclaw-web-search-plus](https://github.com/robbyczgw-cla/nanoclaw-web-search-plus) | dedicated front-end |

There is no hosted Web Search Plus API and no public OpenAPI document. Auth is whatever key the **provider** you configure issues (`TAVILY_API_KEY`, `BRAVE_API_KEY`, …). No webhooks.

## Read next

- [Homepage](/index.md)
- [Provider privacy, terms, pricing](/providers.md)
- [Legal](/legal.md)
- [Hermes plugin README](https://github.com/robbyczgw-cla/hermes-web-search-plus#readme)
- [MCP README](https://github.com/robbyczgw-cla/web-search-plus-mcp#readme)

## Agent endpoints on this site

- `GET /llms.txt` — this project's llms.txt
- `GET /index.md`, `/providers.md`, `/legal.md`, `/developers.md` — markdown siblings
- `Accept: text/markdown` on `/`, `/providers`, `/legal`, `/developers` — same bodies via content negotiation (`Vary: Accept`)

## Routing and runtime reference

Why it exists

## Better search without depending on one service.

Different searches work better in different places. Web Search Plus chooses from the providers you have and keeps your agent working when one of them has a bad day.

01

### Picks a good provider

News, research, shopping and technical searches do not all need the same search service.

02

### Tries another when needed

Missing key, provider problem or empty result? It can move to the next option instead of stopping the whole task.

**brave** → **serper** → **tavily ✓**

03

### Shows its work

You keep the original sources and can ask for extra details about which provider ran, what failed and how long it took.

One hardcoded backend Web Search Plus

✕ One service goes down and search stops

✓ Another provider can take over

✕ The same search engine is used for every job

✓ Different jobs can use different providers

✕ Every app needs its own search setup

✓ One engine works across Hermes, OpenClaw and MCP apps

✕ Empty results fail without explanation

✓ Optional reports show what happened

✕ Copies can outrank the original page

✓ Official and original sources get priority

✕ Huge pages fill the agent's context

✓ Long pages are cleaned and shortened

✕ Unsafe internal addresses can be opened

✓ Private and system addresses are blocked by default

Under the hood

## What happens after you press search.

Web Search Plus understands the kind of search, chooses a provider and tries the next one if needed. You can ask for the technical details when you want them.

01

### Understand the question

Is it research, news, shopping, local search or a page to read?

02

### Choose a provider

It picks a suitable provider from the ones you configured.

03

### Try the next one

If the first provider fails or returns nothing, another can take over.

04

### Show extra details

Turn on `quality_report=true`  when you want to see which provider ran and how long it took.

quality-report.json

```
{
  // example quality report
  "query_intent": "research",
  "provider_used": "tavily",
  "reason": "research intent + key available",
  "fallback_chain": ["brave", "serper"],
  "fallbacks_taken": 0,
  "results_returned": 8,
  "metadata": { "intent_rerank": true },
  "authority_signals": {
    "canonical_top_result": true,
    "canonical_domain_hits": 3
  },
  "elapsed_ms": 742
}
```

Install paths

## Runtime installation

Hermes Agent and OpenClaw Plugin are both primary flagship paths. NanoClaw gets its own utility-skill front-end, and the MCP server keeps every other client on the same routing engine.

### OpenClaw Plugin

primary · v4.0.3

The best fit for OpenClaw. Version 4.0.3 matches Hermes: search, clean page reading, and provider settings. Local search uses separately installed DonSeTch instead of Hound. The extra tools stay off until you allow them. Needs OpenClaw 2026.8.1.

stable · native OpenClaw plugin

`openclaw plugins install clawhub:web-search-plus-plugin-v2`

[ClawHub →](https://clawhub.ai/plugins/web-search-plus-plugin-v2) [GitHub →](https://github.com/robbyczgw-cla/web-search-plus-plugin) [Release →](https://github.com/robbyczgw-cla/web-search-plus-plugin/releases/tag/v4.0.3)

### Hermes Agent

primary · v4.1.1

Search and read pages inside Hermes. Version 4.1.1 keeps Exa highlights, Parallel result and domain filters, and Tavily recency on the values that were actually sent. Optional native WSP routing stays. DonSeTch 3.6.1 is supported as a separately installed provider.

`hermes plugins update web-search-plus`

`hermes plugins install robbyczgw-cla/hermes-web-search-plus --enable`

[GitHub →](https://github.com/robbyczgw-cla/hermes-web-search-plus) [Release →](https://github.com/robbyczgw-cla/hermes-web-search-plus/releases/tag/v4.1.1) [DonSeTch upstream →](https://github.com/dondai44423/donsetch) [Native setup →](https://github.com/robbyczgw-cla/hermes-web-search-plus/blob/v4.1.1/docs/NATIVE_BACKEND.md)

### NanoClaw Utility Skill

GitHub

Adds the Web Search Plus command-line tool to NanoClaw containers. No MCP server is required.

`/add-web-search-plus`

[GitHub →](https://github.com/robbyczgw-cla/nanoclaw-web-search-plus)

### MCP Server

PyPI v4.1.1

Use Web Search Plus in Claude Desktop, Cursor, NanoBot and other MCP apps. Version 4.1.1 matches the Hermes adapter fidelity. Your existing `web_search`  and `web_extract`  tools and setup stay the same. The optional native Hermes adapter is not part of this package.

`uvx --from web-search-plus-mcp==4.1.1 web-search-plus-mcp`

[PyPI →](https://pypi.org/project/web-search-plus-mcp/4.1.1/) [GitHub →](https://github.com/robbyczgw-cla/web-search-plus-mcp) [Release →](https://github.com/robbyczgw-cla/web-search-plus-mcp/releases/tag/v4.1.1)

### OpenClaw Skill

v4.0.0

A portable source-only Web Search Plus skill for OpenClaw installs that do not use the native plugin. Perplexity/Kilo answers are gone. Not a copy of plugin 4.0.3.

stable compatibility option · ClawHub latest

`openclaw skills install web-search-plus`

[ClawHub →](https://www.clawhub.ai/robbyczgw-cla/web-search-plus) [GitHub →](https://github.com/robbyczgw-cla/web-search-plus) [Release →](https://github.com/robbyczgw-cla/web-search-plus/releases/tag/v4.0.0)

Quickstart

## Client configuration

Choose your client and configure a provider key.

### OpenClaw

```
# OpenClaw Plugin
openclaw plugins install clawhub:web-search-plus-plugin-v2

# Then allow the tools you want (they stay optional until you do)
# tools.alsoAllow: web_search_plus, web_extract_plus, …

# Configure at least one provider key in plugin config
plugins.entries.web-search-plus-plugin-v2.config.braveApiKey=your-brave-key
plugins.entries.web-search-plus-plugin-v2.config.tavilyApiKey=your-tavily-key
plugins.entries.web-search-plus-plugin-v2.config.exaApiKey=your-exa-key
plugins.entries.web-search-plus-plugin-v2.config.linkupApiKey=your-linkup-key
```

### Hermes

```
# Hermes Agent — fresh install
hermes plugins install robbyczgw-cla/hermes-web-search-plus --enable
python ~/.hermes/plugins/web-search-plus/setup.py setup

# Upgrade an existing install
hermes plugins update web-search-plus

# Restart/reload Hermes, then use Plus tools (default):
web_search_plus(query="latest AI model releases", quality_report=true)
web_extract_plus(urls=["https://example.com/docs"])

# Optional — native Hermes tools via WSP (Hermes-only, not MCP):
# web:
#   search_backend: wsp
#   extract_backend: wsp
```

### Claude Desktop

```
{
  "mcpServers": {
    "web-search-plus": {
      "command": "uvx",
      "args": ["--from", "web-search-plus-mcp==4.1.1", "web-search-plus-mcp"],
      "env": {
        "YOU_API_KEY": "your-key",
        "SERPER_API_KEY": "your-key",
        "LINKUP_API_KEY": "your-key"
      }
    }
  }
}
```

### Cursor

```
{
  "mcpServers": {
    "web-search-plus": {
      "command": "uvx",
      "args": ["--from", "web-search-plus-mcp==4.1.1", "web-search-plus-mcp"],
      "env": {
        "YOU_API_KEY": "your-key",
        "SERPER_API_KEY": "your-key",
        "LINKUP_API_KEY": "your-key"
      }
    }
  }
}
```

### NanoBot

```
{
  "tools": {
    "mcpServers": {
      "web-search-plus": {
        "command": "uvx",
        "args": ["--from", "web-search-plus-mcp==4.1.1", "web-search-plus-mcp"],
        "env": {
          "YOU_API_KEY": "your-key",
          "SERPER_API_KEY": "your-key",
          "LINKUP_API_KEY": "your-key"
        }
      }
    }
  }
}
```

Current state

## Release history

The page tracks the release train: Hermes on v4.1.1, MCP on v4.1.1, the OpenClaw Plugin on v4.0.3, and the OpenClaw Skill on v4.0.0, plus the current NanoClaw paths — no fossilized release copy.

**Hermes + MCP v4.1.1 · adapter fidelity** September 9, 2026

Exa search prefers requested highlights. Parallel Search sends result count and domain filters through `advanced_settings` instead of rewriting the query. Tavily recency uses native `time_range`; `time_range` wins over `freshness`; receipts match the filter that was sent. [Hermes →](https://github.com/robbyczgw-cla/hermes-web-search-plus/releases/tag/v4.1.1) · [PyPI →](https://pypi.org/project/web-search-plus-mcp/4.1.1/)

**Hermes + MCP v4.1.0 · native Hermes backend + DonSeTch 3.6.1** September 5, 2026

Hermes 4.1.0 adds an opt-in `wsp`  backend so native `web_search`  and `web_extract`  can call the existing WSP engine in-process. Plus tools stay the default; install does not select the backend. The native path is Hermes-only — MCP 4.1.0 carries the same DonSeTch 3.6.1 adapter update (compact evidence, namespaced diagnostics, stdio-only child transport) without native backend registration. [DonSeTch](https://github.com/dondai44423/donsetch)  remains separately installed AGPL-3.0-only and explicit-only. Historical Hound / Master-Fetch credit stays with [Bishesh Bhandari (@dondai1234)](https://github.com/dondai1234) . [Hermes →](https://github.com/robbyczgw-cla/hermes-web-search-plus/releases/tag/v4.1.0)  · [PyPI →](https://pypi.org/project/web-search-plus-mcp/4.1.0/)

**OpenClaw Skill v4.0.0 · source-only** August 31, 2026

The portable skill drops Perplexity/Kilo answer synthesis. Ranked source URLs and extracted page text only. Not a copy of plugin 4.0.3 — DonSeTch, Parallel, Octen and TinyFish stay on the native plugin. [Release notes →](https://github.com/robbyczgw-cla/web-search-plus/releases/tag/v4.0.0)  · [ClawHub →](https://www.clawhub.ai/robbyczgw-cla/web-search-plus)

**OpenClaw Plugin v4.0.3 · DonSeTch replaces Hound** August 31, 2026

The native OpenClaw plugin now matches Hermes 4.0.3. Hound is removed; install DonSeTch separately and point `donsetchBin`  at an absolute path. Octen and TinyFish stay explicit-only. Parallel can join automatic routing. Floor is OpenClaw 2026.8.1. [Release notes →](https://github.com/robbyczgw-cla/web-search-plus-plugin/releases/tag/v4.0.3)  · [ClawHub →](https://clawhub.ai/plugins/web-search-plus-plugin-v2)

**Hermes + MCP v4.0.3 · DonSeTch 3.2.1 tested** August 25, 2026

The tested DonSeTch binary is now 3.2.1. Live stdio Search and Fetch still work; 2.x binaries report `incompatible_major` . DonSeTch remains separately installed and explicit-only. Parallel routing from 4.0.2 is unchanged. [Hermes →](https://github.com/robbyczgw-cla/hermes-web-search-plus/releases/tag/v4.0.3)  · [PyPI →](https://pypi.org/project/web-search-plus-mcp/4.0.3/)

**Hermes + MCP v4.0.2 · Parallel fast + auto-routing** August 22, 2026

Parallel Search now defaults to `fast` . When a `PARALLEL_API_KEY`  is configured, Parallel joins automatic routing; set `auto_allow.parallel=false`  to keep it explicit. Use `advanced`  or research mode for deeper work. Parallel remains high-risk under its standard Customer Terms. [Hermes →](https://github.com/robbyczgw-cla/hermes-web-search-plus/releases/tag/v4.0.2)  · [PyPI →](https://pypi.org/project/web-search-plus-mcp/4.0.2/)

**Hermes + MCP v4.0.0 · DonSeTch replaces Hound** August 16, 2026

The optional Hound sidecar is gone. Hermes and the standalone MCP package now use a separately installed DonSeTch 2.1.0 stdio provider through `DONSETCH_BIN` . It stays explicit-only by default; browser and anti-bot outcomes remain host-dependent. [Hermes →](https://github.com/robbyczgw-cla/hermes-web-search-plus/releases/tag/v4.0.0)  · [PyPI →](https://pypi.org/project/web-search-plus-mcp/4.0.0/)

**MCP v3.6.0 · Agent Plugins packaging** August 6, 2026

The standalone package now ships portable Agent Plugins 1.0-compatible `plugin.json`  and `mcp.json`  manifests. Clients can start the published server through an exact `uvx`  pin while the stable `web_search`  and `web_extract`  tools remain unchanged. [PyPI →](https://pypi.org/project/web-search-plus-mcp/3.6.0/)  · [Release notes →](https://github.com/robbyczgw-cla/web-search-plus-mcp/releases/tag/v3.6.0)

**Hermes v3.4.2 · transparent Research previews** August 7, 2026

Long source summaries keep the stable 500-character compatibility preview, but now carry an explicit truncation marker showing the original content length. The fix makes bounded output honest without changing short-summary behavior or the public tool contract. [Release notes →](https://github.com/robbyczgw-cla/hermes-web-search-plus/releases/tag/v3.4.2)

**Hermes v3.4.1 · Exa freshness + TinyFish** July 30, 2026

Exa now turns day, week, month and year freshness requests into concrete publication-date bounds while preserving explicit date overrides. TinyFish joins as an explicit-only, BYOK source-search provider and never enters automatic routing. Its standard Terms permit broad Customer Data uses, including training-related uses, so WSP rates it high risk and links the warning beside setup guidance. Exa freshness contribution: [@kesku](https://github.com/kesku) . [Release notes →](https://github.com/robbyczgw-cla/hermes-web-search-plus/releases/tag/v3.4.1)

**MCP v3.4.1** July 30, 2026

The standalone package carries the same Exa freshness and explicit-only TinyFish support while preserving exactly two MCP tools, 15 Search providers and 9 Extract providers. TinyFish still requires your own key and the same high-risk Terms review. [PyPI →](https://pypi.org/project/web-search-plus-mcp/3.4.1/)  · [Release notes →](https://github.com/robbyczgw-cla/web-search-plus-mcp/releases/tag/v3.4.1)

**MCP v3.4.0 · Octen via Monid** July 28, 2026

An optional source-search provider you call explicitly with `provider="octen"` . Octen supplies ranked source results and highlights; Monid provides API access and billing through `MONID_API_KEY` . Native recency and domain filters are supported, full-content and answer modes stay outside the integration, and Octen never enters automatic routing unless an operator deliberately opts it in. [Release notes →](https://github.com/robbyczgw-cla/web-search-plus-mcp/releases/tag/v3.4.0)

**OpenClaw Plugin v3.3.0** July 25, 2026

The OpenClaw plugin completes the source-only port and joins the rest of Web Search Plus on the 3.3.0 line. Two new tools ship with it: `web_search_health_plus` , a read-only view of in-process provider health, and `web_extract_benchmark_plus` , an explicit-only extraction benchmark capped at three provider calls. Per-call `routing_override_provider`  now pins exactly one provider with no silent fallback, extraction stays inside operator ceilings with page-on-demand full text through `content_ref` , and Hound can be connected as an optional loopback-only sidecar. Compatibility note: Perplexity direct and the Kilo Perplexity gateway are gone from the provider schema, runtime and config — they are not source-only evidence providers. [Release notes →](https://github.com/robbyczgw-cla/web-search-plus-plugin/releases/tag/v3.3.0)

**Hermes v3.3.0** July 24, 2026

Bounded heading-aware extraction spans retain the body beneath a matching heading; provenance-safe result enrichment preserves contributing observations and adds explainable fetch hints; completion-order Research can stop after a conservative diversity quorum while preempted providers remain visible. The interaction ideas are independently adapted from [Hound / Master-Fetch v11.2.0](https://github.com/dondai1234/master-fetch/releases/tag/v11.2.0) , the MIT-licensed project by [Bishesh Bhandari (@dondai1234)](https://github.com/dondai1234) . Hound code is not bundled or claimed as Robby's code.

**MCP v3.3.0** July 24, 2026

The standalone package realigns from 1.2.0 to the portable WSP 3.3 engine version without breaking its two MCP tools. It carries the same semantic spans, provenance-safe enrichment, Research quorum and repaired `quality_report`  projection, with Hound still connected only as a separately installed sidecar.

**Hermes v3.2.0** July 22, 2026

Optional local Search + Extract through Hound 11.1.6, connected as a loopback-only MCP sidecar. Hound stays separately installed and explicit-only by default; WSP retains source-only output, SSRF checks, bounded context, cache ownership and truthful provider receipts. Credit: [Hound / Master Fetch](https://github.com/dondai1234/master-fetch) , created by [Bishesh Bhandari (@dondai1234)](https://github.com/dondai1234) .

**MCP v1.2.0** July 22, 2026

The standalone package tracks the portable WSP 3.2 engine: 13 Search and 9 Extract providers, Hound sidecar support, explicit MCP/httpx dependency floors, packaged setup guidance and truthful provider identity on fresh cache hits.

**Hermes v3.1.2** July 21, 2026

Patch release for two Provider SDK integration defects found in post-release review. Extraction requests served by SDK-discovered providers no longer fail closed inside the extraction-cache identity: they contribute a deterministic identity derived from their spec and the non-secret scalar settings of their config section, while unknown, unregistered providers still fail closed. And the `providers.d`  non-production gate now acts before module execution — fixtures declaring `production=False`  are skipped without being imported unless the explicit opt-in is set. No behavioural changes for built-in providers or any search path; existing caches remain valid. [Release notes →](https://github.com/robbyczgw-cla/hermes-web-search-plus/releases/tag/v3.1.2)

**MCP v1.1.0** July 20, 2026

The standalone MCP package syncs the portable Web Search Plus v3.1.1 engine: budget preflight, diversity scoring, self-hosted profiles, shadow-policy observations, semantic extraction spans, the versioned extraction-cache identity, and the public `wsp_sdk`  with fail-closed `providers.d`  discovery — while keeping the stable two-tool MCP boundary. v1.0.1 before it fixed auto-request fallback in the MCP projection. [Release notes →](https://github.com/robbyczgw-cla/web-search-plus-mcp/releases/tag/v1.1.0)

**Hermes v3.1.1** July 20, 2026

WSP 3.1 ships everything 3.0 deferred, plus the quality and budget layers around it — every feature opt-in, defaults functionally unchanged. A deterministic shadow routing policy now runs beside Classic Routing v2, persists its would-be decisions (never query text) and reports agreement and provider divergences in the read-only Operator Console; Classic remains authoritative and `WSP_ROUTING_CLASSIC_ONLY=1`  still wins. Budget preflight checks provider-call caps, daily quota, timeout and context budgets before the first provider call and degrades deterministically or aborts with a typed error. Quality reports gain a diversity diagnosis (registrable-domain coverage, canonical-URL duplication, near-duplicate content, provider mix). The extraction cache gets a versioned, request-exact identity contract — no wrong hits after endpoint, budget or extraction-config changes. A self-hosted profile runs automatic routing on SearXNG and keyless Keenable without commercial keys. Opt-in semantic spans return query-conditioned passages under a mechanical offset contract (NFC, Unicode codepoints, half-open ranges). And the new provider SDK makes a provider one self-contained `providers.d`  module with scaffolding and a conformance suite — zero core-file edits. New Console endpoint: per-provider daily health trends. v3.1.1 hardens SDK receipt provenance and test-state isolation, restores schema-generator parity, and removes wall-clock flakes from journal concurrency tests. [Release notes →](https://github.com/robbyczgw-cla/hermes-web-search-plus/releases/tag/v3.1.1)

**Hermes v3.0.2** July 14, 2026

WSP 3.0.2 hardens registered Search/Extract entrypoints, bounded Research fan-out, cache identity, immutable full-text references and timeout snapshots. Building on v3.0, Web Search Plus is a source-only evidence engine: frozen native v3 request/response contracts with v2 compatibility projections, lossless provider observations captured before filtering/dedup/rerank/truncation, typed provider errors with complete attempt history and truthful routing/cache receipts, deterministic bounded-context extraction with page-on-demand full-text storage, SQLite operational state (dry-run-first migration, verified backups, idempotent apply, digest-checked rollback), a local loopback-only, token-authenticated, read-only Operator Console, direct extraction benchmarking with privacy-safe aggregate history, Classic Routing v2 kill switches and Brave in the default auto-pool. Compatibility note: WSP 3.0 is mechanically source-only — the native Perplexity and Kilo-Perplexity answer endpoints are no longer registered; existing keys are ignored, not deleted. The public Hermes tools remain `web_search_plus`  and `web_extract_plus` . [Release notes →](https://github.com/robbyczgw-cla/hermes-web-search-plus/releases/tag/v3.0.2)

**Hermes v2.9.1** July 10, 2026

Shared cache operations now preserve provider health, performance and usage telemetry, invalid UTF-8 foreign JSON no longer crashes stats or clear, and Parallel extraction gets a fair 60k-per-result default budget for long pages. [Release notes →](https://github.com/robbyczgw-cla/hermes-web-search-plus/releases/tag/v2.9.1)

**Hermes v2.9.0** July 2, 2026

Patch release for Hermes Agent v0.18 standalone plugin discovery: Web Search Plus now loads from outside the plugin directory without cwd-sensitive sibling imports, while v2.8 keeps truncate-and-store extraction, unified freshness filters and provider benchmarking.

**Hermes v2.7.0** June 30, 2026

Private/internal extraction target URLs are blocked before provider dispatch, keyless-provider setup is smoother, and `setup.py fastpath`  checks whether current public Hermes is routed through Web Search Plus cleanly.

**Hermes v2.6.1** June 26, 2026

GroktoCrawl can be used as a local Firecrawl-compatible backend through the existing `firecrawl.api_url`  and `firecrawl.scrape_url`  overrides; no separate provider or default backend required.

**Hermes v2.6.0** June 26, 2026

Keenable joins the Hermes provider lineup for search and extraction. Use `KEENABLE_API_KEY`  for authenticated calls; the keyless public endpoint is opt-in and disabled by default.

**Hermes v2.5.1** June 16, 2026

Config-driven provider gating now covers both search and extraction. Firecrawl and any other provider can be disabled centrally in `config.json`  without touching release code.

**MCP v1.0.1** July 20, 2026

Corrective routing release: normal `provider=auto`  Search and Extract requests once again expand to multiple candidates and continue after quota or rate-limit failures. Explicit provider selections remain strict unless fallback is requested. The release adds boundary regressions that reproduce the former one-candidate plan and prove an executed second-provider fallback after a simulated `429` . [Release notes →](https://github.com/robbyczgw-cla/web-search-plus-mcp/releases/tag/v1.0.1)

**MCP v1.0.0** July 14, 2026

The standalone MCP package now tracks the portable Web Search Plus v3.0.2 source-only contract: canonical v3 evidence and receipts, truthful multi-provider Research, bounded extraction and immutable full-text references, cache provenance, typed failures, and a stable two-tool MCP boundary for `web_search`  and `web_extract` . [Release notes →](https://github.com/robbyczgw-cla/web-search-plus-mcp/releases/tag/v1.0.0)

**OpenClaw Skill v3.3.0** July 5, 2026

Feature sync with Web Search Plus v2.5–v2.9 for the standalone skill runtime: Keenable, freshness controls, news search, Serper extraction, locale routing, adaptive provider memory, stronger SSRF guards and long-page handling.

**OpenClaw Plugin v3.2.0** July 5, 2026

Feature sync with the current Web Search Plus engine: Keenable, freshness controls, news search, Serper extraction, locale routing, SSRF target guards, long-page handling and Parallel extraction budget tuning.

**OpenClaw Plugin v3.1.0** June 10, 2026

Native plugin release adds research mode, authority reranking, quality signals and retry jitter; ClawHub artifact verified and install-smoked through OpenClaw.

**NanoClaw utility skill** GitHub

Dedicated NanoClaw front-end packages the shared engine as a self-contained `wsp`  CLI skill for agent containers — search and extract, no MCP bridge required.

FAQ

## Quick answers.

Do I need API keys for all 15 providers?

No. One provider is enough. Commercial APIs use their own keys; SearXNG can be self-hosted, Keenable has an opt-in public tier, and DonSeTch can run as a separately installed local stdio provider without a provider API key.

Which clients does it work with?

Hermes Agent and OpenClaw natively as flagship plugins, NanoClaw through a dedicated utility-skill front-end, plus Claude Desktop, Claude Code, Cursor, NanoBot and any other MCP-compatible client through the standalone `web-search-plus-mcp`  server on PyPI.

What happens when a provider fails?

The router falls through the chain: a missing key, provider error or empty result set moves the request to the next candidate automatically. The quality report records every fallback that was taken, so nothing fails silently.

Does it extract page content too, or just search?

Both. `web_search_plus`  handles live search across 15 source-only search providers, and `web_extract_plus`  pulls clean content from URLs across 9 extraction providers with the same fallback behavior.

What does it cost?

The router itself is free and open source. Commercial provider costs and data terms depend on what you configure. Self-hosted SearXNG and local DonSeTch avoid provider request fees but still have egress and storage boundaries; TinyFish and Octen remain explicit privacy trade-offs. See the [provider guide](/providers#privacy-terms)  for pricing, training, retention and ZDR caveats.