Fathom-DeepResearch — security grade SAFE, quality 62/100

Security audit verdict: SAFE · quality 62/100

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 FractalAIResearchLabs · Agent Tool · ★ 63

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

🔒 Is Fathom-DeepResearch safe to install? View the security audit →

About Fathom-DeepResearch

Fathom-DeepResearch: Unlocking Long Horizon Information Retrieval And Synthesis For SLMs -

agentartificial-intelligencedeep-searchfunction-callinginformation-seekingllmmulti-agentreinforcement-learningtool-useweb-agent

Quick Facts

Stars63
Forks11
LanguagePython
CategoryAgent Tool
LicenseMIT
Quality Score61.5961461684685/100
Open Issues2
Last Updated2025-10-07
Created2025-09-09
Platformsbrowser, python
Est. Tokens~2022k

Compatible Skills

These tools work well together with Fathom-DeepResearch for enhanced workflows:

  • ToolRegistry — semantic(0.24)+complementary+rare_topics+same_lang+similar_pop+shared_platform (58%)
  • MetaClaw — semantic(0.21)+complementary+rare_topics+same_lang+similar_pop+shared_platform (57%)
  • LiteMultiAgent — semantic(0.20)+complementary+rare_topics+same_lang+similar_pop+shared_platform (56%)
  • LiteWebAgent — semantic(0.19)+complementary+rare_topics+same_lang+similar_pop+shared_platform (56%)

Fathom-DeepResearch alternative? Top 6 similar tools

Looking for a Fathom-DeepResearch alternative? If you're comparing Fathom-DeepResearch 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.

  • VT.ai by vinhnx · ⭐ 118

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

  • LiteMultiAgent by PathOnAIOrg · ⭐ 103

    The Library for LLM-based multi-agent applications

  • oreilly-ai-agents by sinanuozdemir · ⭐ 299

    An introduction to the world of AI Agents

  • llm-movieagent by tomasonjo · ⭐ 247

    Semantic layer on top of a graph database to provide an LLM with a set of robust tools to interact with the da

  • Awesome-LLM-Papers-Comprehensive-Topics by shure-dev · ⭐ 223

    Awesome LLM Papers and repos on very comprehensive topics.

  • LiteWebAgent by PathOnAIOrg · ⭐ 153

    [NAACL2025] LiteWebAgent: The Open-Source Suite for VLM-Based Web-Agent Applications

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Python Agent Tools

Frequently Asked Questions

What is Fathom-DeepResearch?

Fathom-DeepResearch is Fathom-DeepResearch: Unlocking Long Horizon Information Retrieval And Synthesis For SLMs. It is categorized as a Agent Tool with 63 GitHub stars.

What programming language is Fathom-DeepResearch written in?

Fathom-DeepResearch is primarily written in Python. It covers topics such as agent, artificial-intelligence, deep-search.

How do I install or use Fathom-DeepResearch?

You can find installation instructions and usage details in the Fathom-DeepResearch GitHub repository at github.com/FractalAIResearchLabs/Fathom-DeepResearch. The project has 63 stars and 11 forks, indicating an active community.

What license does Fathom-DeepResearch use?

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

What are the best alternatives to Fathom-DeepResearch?

The top alternatives to Fathom-DeepResearch on Agent Skills Hub include VT.ai, LiteMultiAgent, oreilly-ai-agents. 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