ToolMaker — security grade SAFE, quality 70/100

Security audit verdict: SAFE · quality 70/100

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 →

by KatherLab · Agent Tool · ★ 82

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is ToolMaker safe to install? View the security audit →

About ToolMaker

Turn GitHub repositories into LLM-compatible tools. This repository contains the official code for the paper: LLM Agents Making Agent Tools Georg Wölflein, Dyke Ferber, Daniel Truhn, Ognjen Arandjelović and Jakob N. Kather Annual Meeting of the Association for Computational Linguistics (ACL), July 2025. Read abstract Tool use has turned large language models (LLMs) into powerful agents that can perform complex multi-step tasks by dynamically utilising external software components. However, these tools must be implemented in advance by human developers, hindering the applicability of LLM agents in domains which demand large numbers of highly specialised tools, like in life sciences and medicine. Motivated by the growing trend of scientific studies accompanied by public code repositories, we propose ToolMaker, a novel agentic framework that autonomously transforms papers with code into LLM-compatible tools. Given a short task description and a repository URL, ToolMaker autonomously installs required dependencies and generates code to perform the task, using a closed-loop self-correction mechanism to iteratively diagnose and rectify errors.

agentsfunction-callingllm-agentsmedicinepathologyradiologytool-creationtool-use

Quick Facts

Stars82
Forks16
LanguagePython
CategoryAgent Tool
Quality Score69.7317235297227/100
Open Issues1
Last Updated2025-05-16
Created2025-02-16
Platformspython
Est. Tokens~157k

ToolMaker alternative? Top 6 similar tools

Looking for a ToolMaker alternative? If you're comparing ToolMaker with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • mcp-sse by sidharthrajaram · ⭐ 301

    A working pattern for SSE-based MCP clients and servers

  • avatar by zou-group · ⭐ 242

    (NeurIPS 2024) AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoning

  • ToolBrain by ToolBrain · ⭐ 205

    A framework for agentic tool use training with reinforcement learning

  • Awesome-AI-For-Security by AmanPriyanshu · ⭐ 145

    A curated list of tools, papers, and datasets for applying AI to cybersecurity tasks. This list primarily focu

  • VT.ai by vinhnx · ⭐ 118

    VT.ai - multimodal AI chat app with dynamic conversation routing

  • llm-tool-collection by skissue · ⭐ 96

    Curated collection of tools for agentic LLMs in Emacs

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Python Agent Tools

Frequently Asked Questions

What is ToolMaker?

ToolMaker is Turn GitHub repositories into LLM tools. (ACL 2025). It is categorized as a Agent Tool with 82 GitHub stars.

What programming language is ToolMaker written in?

ToolMaker is primarily written in Python. It covers topics such as agents, function-calling, llm-agents.

How do I install or use ToolMaker?

You can find installation instructions and usage details in the ToolMaker GitHub repository at github.com/KatherLab/ToolMaker. The project has 82 stars and 16 forks, indicating an active community.

What are the best alternatives to ToolMaker?

The top alternatives to ToolMaker on Agent Skills Hub include mcp-sse, avatar, ToolBrain. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

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:

View on GitHub → Browse Agent Tool tools