OpenSearch-VL — security grade SAFE, quality 66/100

Security audit verdict: SAFE · quality 66/100

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 shawn0728 · Agent Tool · ★ 264

Last updated: 2026-07-30 · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is OpenSearch-VL safe to install? View the security audit →

About OpenSearch-VL

An Open Recipe for Frontier Multimodal Search Agents Cold-Start Agentic SFT  ·  Multi-Turn Fatal-Aware GRPO  ·  Visual Tool Use ![](https://img.shields.io/github/last-commit/shawn0728/OpenSearch-

deep-research-agent multimodal opensource search-agent think-with-image vlm-agent

Quick Facts

Stars	264
Forks	29
Language	Python
Category	Agent Tool
License	Apache-2.0
Quality Score	66.2642885593753/100
Open Issues	6
Last Updated	2026-07-30
Created	2026-05-03
Platforms	python
Est. Tokens	~20k

Compatible Skills

These tools work well together with OpenSearch-VL for enhanced workflows:

hyperresearch — semantic(0.32)+complementary+rare_topics+same_lang+similar_pop+shared_platform (61%)
deep-research-mcp — semantic(0.25)+complementary+same_lang+similar_pop+shared_platform (59%)
designing-real-world-ai-agents-workshop — semantic(0.24)+complementary+same_lang+similar_pop+shared_platform (58%)

OpenSearch-VL alternative? Top 6 similar tools

Looking for a OpenSearch-VL alternative? If you're comparing OpenSearch-VL 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.

LeanType by LeanBitLab · ⭐ 972
LeanType is an Open-source keyboard, fork of HeliBoard with additional features and customisation
mcpcan by Kymo-MCP · ⭐ 726
MCPCAN is a centralized management platform for MCP services. It deploys each MCP service using a container de
Agently-Daily-News-Collector by AgentEra · ⭐ 635
An open-source LLM based automatically daily news collecting workflow showcase powered by Agently AI applicati
rai by RobotecAI · ⭐ 583
RAI is a vendor agnostic agentic framework for Physical AI robotics, utilizing ROS 2 tools to perform complex
multimodal-agents-course by the-ai-merge · ⭐ 576
An MCP Multimodal AI Agent with eyes and ears!
cad2data-Revit-IFC-DWG-DGN by datadrivenconstruction · ⭐ 452
Workflow for AI Agents enables automated conversion of CAD files (such as `.rvt`, `.ifc`, `.dwg`) using comman

More Agent Tool Tools

Explore other popular agent tool tools:

awesome-claude-code ⭐ 54.3k
open-saas ⭐ 15.8k
notebooklm-skill ⭐ 7.8k
playwright-skill ⭐ 3.0k
skills ⭐ 2.0k
agent-skills ⭐ 6.5k
raptor ⭐ 3.8k
excalidraw-diagram-skill ⭐ 4.3k
chinese-novelist-skill ⭐ 2.8k
claude-code-skill-factory ⭐ 844

View all Agent Tool tools →

Popular Python Agent Tools

TrendRadar ⭐ 62.2k · MCP Server
gpt-researcher ⭐ 29.2k · MCP Server
Scrapling ⭐ 82.4k · MCP Server
serena ⭐ 29.6k · MCP Server
MaxKB ⭐ 22.8k · MCP Server

Frequently Asked Questions

What is OpenSearch-VL?

OpenSearch-VL is 🔍 OpenSearch-VL provides a fully open recipe for training strong multimodal deep search agents through high-quality data curation, diverse visual/search tools, and fatal-aware agentic reinforcement l. It is categorized as a Agent Tool with 264 GitHub stars.

What programming language is OpenSearch-VL written in?

OpenSearch-VL is primarily written in Python. It covers topics such as deep-research-agent, multimodal, opensource.

How do I install or use OpenSearch-VL?

You can find installation instructions and usage details in the OpenSearch-VL GitHub repository at github.com/shawn0728/OpenSearch-VL. The project has 264 stars and 29 forks, indicating an active community.

What license does OpenSearch-VL use?

OpenSearch-VL is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to OpenSearch-VL?

The top alternatives to OpenSearch-VL on Agent Skills Hub include LeanType, mcpcan, Agently-Daily-News-Collector. 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