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 HKUSTDial · Agent Tool · ★ 242
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is DeepEye safe to install? View the security audit →
DeepEye DeepEye harnesses the reasoning capabilities of large language models to autonomously orchestrate complex data analysis workflows. It combines a chat workspace, workflow orchestration, sandboxed execution, and artifact rendering for analytical outputs such as reports, dashboards, and data videos. Project Status: Active Development Preview DeepEye is being shared publicly while the codebase, documentation, tests, deployment workflow, and security hardening are still being actively improved. The repository is useful for local evaluation, collaboration, and understanding the architecture, but APIs, internal contracts, and setup details may continue to change as the project is refined. What DeepEye Does Turns data analysis requests into visible workflow drafts and execution runs. Works with uploaded files and database-backed data sources. Produces structured artifacts such as reports, dashboards, tables, files, and video previews. Provides a React workspace for chat, workflow inspection, output preview, and session state. Runs backend services, workers, storage, and runtime control through a local Docker Compose stack.
| Stars | 242 |
| Forks | 38 |
| Language | Python |
| Category | Agent Tool |
| License | Apache-2.0 |
| Quality Score | 67.0180564949367/100 |
| Open Issues | 46 |
| Last Updated | 2026-08-09 |
| Created | 2018-07-10 |
| Platforms | python |
| Est. Tokens | ~15k |
These tools work well together with DeepEye for enhanced workflows:
Looking for a DeepEye alternative? If you're comparing DeepEye 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.
[NAACL2025] LiteWebAgent: The Open-Source Suite for VLM-Based Web-Agent Applications
A curated list of tools, papers, and datasets for applying AI to cybersecurity tasks. This list primarily focu
The Library for LLM-based multi-agent applications
A multi-agent chatroom for AutoGen agents
A cross-platform desktop client supporting multiple LLM providers, integrated with AI search, developer tools,
State of the Art 82% OSWorld Computer Using Agent, production-ready. Remote and Local! Setup using one API Key
Explore other popular agent tool tools:
DeepEye is DeepEye: An Autonomous Data Agent System. It is categorized as a Agent Tool with 242 GitHub stars.
DeepEye is primarily written in Python. It covers topics such as agent, data-agent, data-agents.
You can find installation instructions and usage details in the DeepEye GitHub repository at github.com/HKUSTDial/DeepEye. The project has 242 stars and 38 forks, indicating an active community.
DeepEye is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to DeepEye on Agent Skills Hub include LiteWebAgent, Awesome-AI-For-Security, LiteMultiAgent. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
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: