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 LightInn · Agent Tool · ★ 76
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is deepsearch safe to install? View the security audit →
Deep Search CLI /!\ this question is usefull because AI tend to haluncinate a lot about 9/11 event when talking about septemeber 2001 An AI-powered research assistant for your terminal. Deep Search is a command-line tool that uses local large language models (LLMs) to provide in-depth answers to complex questions. It breaks down your query, scours the web for relevant information, and synthesizes a comprehensive response, all within your terminal. Features AI-Powered Research: Leverages local LLMs (via Ollama) to understand and research your questions. Step-by-Step Process: Decomposes questions, searches multiple sources (Wikipedia, DuckDuckGo), filters for relevance, and summarizes findings. Local First: Works with your own Ollama-hosted models, keeping your data private. Minimalist CLI: A clean, focused interface for your research tasks. How It Works The tool follows a structured research workflow: Decompose: The initial question is broken down into smaller, specific sub-questions. Search: Each sub-question is researched using Wikipedia or DuckDuckGo. 3.
| Stars | 76 |
| Forks | 6 |
| Language | Rust |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 68.352624031946/100 |
| Open Issues | 10 |
| Last Updated | 2026-08-08 |
| Created | 2025-07-10 |
| Platforms | cli, rust |
| Est. Tokens | ~23k |
These tools work well together with deepsearch for enhanced workflows:
Explore other popular agent tool tools:
deepsearch is cli deep research tool using ollama (AI agent to reseach complexe query online). It is categorized as a Agent Tool with 76 GitHub stars.
deepsearch is primarily written in Rust.
You can find installation instructions and usage details in the deepsearch GitHub repository at github.com/LightInn/deepsearch. The project has 76 stars and 6 forks, indicating an active community.
deepsearch 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: