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 LearningCircuit · Agent Tool · ★ 9.1k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is local-deep-research safe to install? View the security audit →
Local Deep Research [ for Deep Research. Support SSE API and MCP server.
Maid is a free and open source application for interfacing with llama.cpp models locally, and with Anthropic,
Multi-Agent Harness for Production AI
✨ AI Coding, Vim Style
A model-driven approach to building AI agents in just a few lines of code.
Explore other popular agent tool tools:
local-deep-research is ~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encryp. It is categorized as a Agent Tool with 9.1k GitHub stars.
local-deep-research is primarily written in Python. It covers topics such as academia, anthropic, arxiv.
You can find installation instructions and usage details in the local-deep-research GitHub repository at github.com/LearningCircuit/local-deep-research. The project has 9.1k stars and 832 forks, indicating an active community.
local-deep-research is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to local-deep-research on Agent Skills Hub include agentops, deep-research, maid. 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: