WALT

by SalesforceAIResearch · Agent Tool · ★ 73

About WALT

WALT: Web Agents that Learn Tools Web Agents that Learn Tools - Automatic tool discovery from websites for LLM agents WALT enables LLM agents to automatically discover and learn reusable tools from any website. Point WALT at a website, and it will explore, understand, and generate ready-to-use tool definitions.

Quick Facts

Stars73
Forks11
LanguagePython
CategoryAgent Tool
LicenseMIT
Quality Score66.0808122910945/100
Open Issues2
Last Updated2026-06-02
Created2025-10-14
Platformsbrowser, python
Est. Tokens~531k

Compatible Skills

These tools work well together with WALT for enhanced workflows:

  • crawl4ai-mcp — semantic(0.19)+complementary+same_lang+similar_pop+shared_platform (57%)
  • canvas-mcp — semantic(0.17)+complementary+same_lang+similar_pop+shared_platform (56%)
  • claude-worktrace — semantic(0.22)+complementary+same_lang+similar_pop+shared_platform (53%)
  • openclaw-qa — semantic(0.22)+complementary+same_lang+similar_pop+shared_platform (53%)
  • skyll — semantic(0.21)+complementary+same_lang+similar_pop+shared_platform (52%)

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Python Agent Tools

Frequently Asked Questions

What is WALT?

WALT is Code for WALT – Web Agents that Learn Tools. It is categorized as a Agent Tool with 73 GitHub stars.

What programming language is WALT written in?

WALT is primarily written in Python.

How do I install or use WALT?

You can find installation instructions and usage details in the WALT GitHub repository at github.com/SalesforceAIResearch/WALT. The project has 73 stars and 11 forks, indicating an active community.

What license does WALT use?

WALT is released under the MIT license, making it free to use and modify according to the license terms.

View on GitHub → Browse Agent Tool tools