Local LLM
vLLM
A high-throughput and memory-efficient inference and serving engine for LLMs
★ 93.1k starsApache-2.0
View guide →// local-llm · 0xMassi/webclaw
webclaw
webclaw is an open-source local llm project by 0xMassi (0xMassi/webclaw on GitHub). It has 2,366 GitHub stars and 235 forks, is released under the AGPL-3.0 license, and was last updated on GitHub on 23 September 2026.
Fast Rust scraper that turns web pages into clean data for LLMs.
💎 Hidden gem★ 2.4k stars⑂ 235 forksAGPL-3.0updated 2026-09
▦ visual — this project's README ships no embeddable screenshot,
so here's a placeholder. The guide below is complete regardless.
so here's a placeholder. The guide below is complete regardless.
// project facts
Project facts
- Repository
- 0xMassi/webclaw
- GitHub stars
- 2,366
- Forks
- 235
- License
- AGPL-3.0
- Last updated on GitHub
- 23 September 2026
- Category
- Local LLM
- Listing
- Hidden gem — a shorter page for a lesser-known project
- Official site
- Official site
// how it works
How it works
- Install webclaw
Get the Rust-built binary or build from source.
- Point at a page
Give it a URL to scrape or crawl.
- Extract
Get clean markdown or structured data back.
- Feed your LLM
Pipe results to agents via CLI, API, or MCP.
// features
Why people love it
Rust speed
Fast extraction with low resource use.
Local-first
Runs on your machine, no cloud required.
HTML to markdown
Clean page conversion for LLMs.
Crawling
Follow links across whole sites.
REST API
Integrate extraction into any stack.
MCP server
Give AI agents direct scraping tools.
Advertisement
// run it
Run it yourself
- Step 1 — Clone the repo
Download the source and move into the project folder.
git clone https://github.com/0xMassi/webclaw.git cd webclaw - Step 2 — Check the README
Every project documents its own setup; start with install requirements.
cat README.md | head -60 - Step 3 — Run it
Follow the project's launch command — Docker, pip, npm, or a binary release.
# see README for the exact launch command
// use cases
What you can build
- Scrape pages for LLM pipelines.
- Crawl sites into clean markdown.
- Give agents web-reading tools via MCP.
- Replace paid scraping APIs locally.
Advertisement
// faq
Questions, answered
How is it different from Firecrawl?
It is local-first and open source, so no per-page API fees.
What does AGPL-3.0 mean for me?
Commercial use is allowed, but network use of modified versions requires sharing source.
Can it handle JavaScript sites?
Check the docs for rendering capabilities.
Is there really an MCP server?
Yes, agents can call it through the Model Context Protocol.
Do I need Rust installed?
Only if building from source; binaries avoid that.
// keep exploring
Similar tools
Local LLM
Web LLM
High-performance In-browser LLM Inference Engine
★ 19.2k starsApache-2.0
View guide →Local LLM
Cactus
Quantization, kernels, runtime and inference engine for mobiles, wearables, smart home and robots
★ 6.1k starsCustom (check repo)
View guide →Local LLM
WebMCP
Early proposal and implementation for connecting LLMs to web pages.
★ 883 starsMIT
View guide →Local LLM
BrowserAI
Run local LLMs like Llama and DeepSeek right inside your web browser.
★ 1.5k starsMIT
View guide →Local LLM
MNN
Alibaba's lightweight, blazing-fast inference engine for on-device LLMs and edge AI.
★ 16.2k starsApache-2.0
View guide →// alternatives
Alternatives in Local LLM
The most-starred other Local LLM projects in the LibreAI catalogue — the realistic shortlist if webclaw is not the right fit.
- Ollama★ 182.1k
The simplest way to run open language models on your own machine.
- Open Webui★ 153.9k
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
- llama.cpp★ 130.2k
LLM inference in C/C++
- vLLM★ 93.1k
A high-throughput and memory-efficient inference and serving engine for LLMs
- lobehub★ 83.0k
🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.
// more in local-llm
More in Local LLM
Nearby Local LLM projects in the catalogue, closest in stars to webclaw — keep exploring the shelf either side of it.
- comfyui_LLM_party★ 2.4k
LLM Agent Framework in ComfyUI includes MCP sever, Omost,GPT-sovits, ChatTTS,GOT-OCR2.0, and FLUX prompt nodes,access to Feishu,discord,and adapts to all llm…
- WhisperJAV★ 2.3k
Noise-robust subtitle generator powered by Whisper and local ASR models.
- TokenSpeed★ 2.5k
TokenSpeed — a speed-of-light LLM inference engine designed for agentic workloads, with TensorRT-LLM-level performance and vLLM-level usability
- kalosm★ 2.2k
Run controllable pre-trained AI models locally, written in Rust.
- handy-ollama★ 2.5k
动手学Ollama，CPU玩转大模型部署，在线阅读地址：https://datawhalechina.github.io/handy-ollama/
- claude-real-video★ 2.2k
Let any LLM actually watch a video — frames plus transcript, run locally.
Get webclaw
Free and open — grab the source, star the repo, and start creating.