webclaw is a skill AI agent for To automatically extract structured data from web pages for use with local LLMs. Pricing: Free. As of 2026-10-23, KanonAgent records 47 upvotes. First indexed by KanonAgent on 2026-08-16.
A lightweight, high-performance web content extraction tool built in Rust for developers to locally scrape and structure web data for use with LLMs.
47 upvotes
Tracked by Kanon since Aug 16, 2026
Status basis: npm_downloads_7d momentum fell to -12 per 3d from 11 (<= 40% of the prior window)
📈 Timelinewhat changed, and when
- Cooling npm_downloads_7d momentum fell to -12 per 3d from 11 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -10 per 3d from 11 (<= 40% of the prior window)
- Anomaly daily change -111.0 is -5.7 standard deviations from this entity's own prior mean (1.4±19.7, baseline excludes this point) — unusual, not necessarily adoption
- Cooling npm_downloads_7d momentum fell to -7 per 3d from 13 (<= 40% of the prior window)
- Anomaly daily change -111.0 is -5.7 standard deviations from this entity's own prior mean (1.4±19.7, baseline excludes this point) — unusual, not necessarily adoption
- Cooling npm_downloads_7d momentum fell to -4 per 3d from 137 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 2 per 3d from 106 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 13 per 3d from 95 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 13 per 3d from 95 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 106 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Accelerating npm_downloads_7d gained 95 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Anomaly daily change 60.0 is 3.4 standard deviations from this entity's own prior mean (-1.7±18.2, baseline excludes this point) — unusual, not necessarily adoption
- Accelerating npm_downloads_7d gained 95 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Anomaly daily change 60.0 is 3.4 standard deviations from this entity's own prior mean (-1.7±18.2, baseline excludes this point) — unusual, not necessarily adoption
- Cooling npm_downloads_7d momentum fell to -77 per 3d from 12 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -54 per 3d from 12 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -68 per 3d from 12 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -68 per 3d from 12 (<= 40% of the prior window)
- first observed Kanon started keeping permanent history for this agent
🔎 Known / Unknown
12 of 23 fields unknown
| Machine-callable | — | unknown | — |
| Open source | 1 | verified | 1 quote(s) |
| Self-hostable | 1 | inferred | 1 quote(s) |
| Bring your own key | — | unknown | — |
| Autonomy level | 2 | inferred | 1 quote(s) |
| Pricing model | — | unknown | — |
| Integrations | mcp | inferred | 2 quote(s) |
“Unknown” means we have not verified it — it is not a “no”. Hard filters never treat unknown as false.
🤖 Agent teardown · skill
Job to be doneTo automatically extract structured data from web pages for use with local LLMs.
AutonomyL2 · tool-calling(evidence: "Scrape, crawl, extract structured data — all from Rust.…")
Who it is forDevelopers
Prerequisitesopen source · self-hostable
Integrationsmcp
PricingFree
Traction · why it is risingGained 47 upvotes on Product Hunt
Why it matters
Its local-first design, Rust-powered performance, and support for MCP make it a strong choice for building efficient, private AI data pipelines.
Evidence quotesverbatim, from the product’s own materials
“public GitHub repository (README fetched)”— structural
“self-hostable server”— readme
“Scrape, crawl, extract structured data — all from Rust.”— description
“CLI, REST API, and MCP server.”— description
“This repo contains the open-source CLI, MCP server, extraction engine, and self-hostable server.”— readme
“CLI, MCP server, REST API, and SDKs for AI agents and RAG pipelines.”— readme
Signal source: GitHub
Visit official site →
📛 Official badgefor your site / README
Building webclaw? Pick a style above — the embed code updates live. Deep color control via URL params: bg= / fg= / accent= (hex). It links back to this page.
On mobile tap Share for WeChat / RED (Xiaohongshu) / X; on desktop use Copy text and paste into the app.
FAQ
What is webclaw?
A lightweight, high-performance web content extraction tool built in Rust for developers to locally scrape and structure web data for use with LLMs.
What does webclaw do?
To automatically extract structured data from web pages for use with local LLMs.
Why does webclaw matter?
Its local-first design, Rust-powered performance, and support for MCP make it a strong choice for building efficient, private AI data pipelines.
How much does webclaw cost?
Free
Is webclaw free?
Yes — webclaw has a free tier. Pricing as stated on its own page: Free
Is webclaw open source?
Yes — webclaw is open source.
Can I self-host webclaw?
Yes — webclaw can be self-hosted.
What does webclaw integrate with?
mcp
How popular is webclaw?
As tracked by KanonAgent: 47 upvotes (first indexed 2026-08-16).
What are the best webclaw alternatives?
Similar AI agents tracked by KanonAgent: Stealth Venture, archify, open-design, deer-flow, ruflo, career-ops.