by SalesforceAIResearch · Agent Tool · ★ 76
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is WALT safe to install? View the security audit →
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 Start Installation Basic Usage bash Run agent with tools walt agent "find and return the URL of the cheapest blue kayak" \ --tools walt-tools/classifieds/ \ --start-url http://localhost:9980 Discover new tools from any website walt discover --url https://example.com Or generate a specific tool (faster!) walt generate --url https://zillow.com --goal "Search for homes with filters" List available tools walt list walt-tools/shopping/ Start an MCP server walt serve walt-
uv pip install sfr-walt
git clone https://github.com/salesforceairesearch/walt.gitTaken from the project's README on GitHub. Check the security audit before running it.
No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
| Stars | 76 |
| Forks | 12 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 66.0808122910945/100 |
| Open Issues | 2 |
| Last Updated | 2026-06-02 |
| Created | 2025-10-14 |
| Platforms | browser, python |
| Est. Tokens | ~531k |
These tools work well together with WALT for enhanced workflows:
Explore other popular agent tool tools:
WALT is Code for WALT – Web Agents that Learn Tools. It is categorized as a Agent Tool with 76 GitHub stars.
WALT is primarily written in Python.
The README on GitHub (github.com/SalesforceAIResearch/WALT) gives: uv pip install sfr-walt , then git clone https://github.com/salesforceairesearch/walt.git. Usage details are in the same README.
WALT is released under the MIT license, making it free to use and modify according to the license terms.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: