moli
Moli is a lightweight, fast, and highly compatible headless browser designed for AI agents.
- Region
- Overseas
- Pricing
- Free
- Open source
- Yes
- GitHub Stars
- ★ 2.1k
- Views
- 9
- Source
- GitHub
- Added
- 2026-09-19
- Last verified
- 2026-09-19
- GitHub
- github.com/lexmount/moli

Overview
Moli is a production-ready headless browser built specifically for AI agents. It features on-demand layout and rendering, combining a full browser runtime with minimal resource consumption. Moli enables your AI agents to scrape and extract web content, perform web searches, and automate browser tasks. You can interact with Moli via CLI, CDP, WebDriver Classic, or WebDriver BiDi. Moli supports Linux, macOS, and Windows platforms.
Key features
- ▪Lightweight resource usage
- ▪Supports multiple protocols (CDP, WebDriver)
- ▪On-demand layout and rendering
- ▪Multi-platform support
Use cases
Pros
- +High performance with low resource consumption
- +Multi-protocol support
- +Cross-platform compatibility
Limitations / notes
- -Requires technical background
- -Higher learning curve
Who it's for
This overview was compiled by AI from public sources and may contain inaccuracies — please refer to the official site.
FAQ
Is it free?
Yes, Moli is an open-source project and can be used freely.
Does it support Chinese?
The documentation has a simplified Chinese version, but the primary language is English.
Does it require internet access?
Yes, installation and usage may require online downloads of dependencies.
Can it be used commercially?
Yes, Moli is an open-source project and is suitable for commercial use.
Similar agents
Cursor
FeaturedAI-powered code editor with Agent mode
Dify
FeaturedOpen-source LLMOps + Agent orchestration platform
扣子 Coze
FeaturedByteDance's no-code Agent/Bot building platform
Trae
FeaturedAI IDE (with Agent) from ByteDance
LangChain
FeaturedThe most mainstream LLM/Agent orchestration framework
Devin
FeaturedAutonomous software engineer Agent by Cognition
Something wrong? Let us know on the About page and we'll fix it.