by mengysun · Agent Tool · ★ 86
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
DataParasite The name is inspired by the ethos of Park & Greene's "A parasite's perspective on data sharing" [1] DataParasite is a simple yet versatile context engineered for scalable online data collection with LLMs. The project is optimized for coding agents (for example, Cursor-agent CLI automations) that orchestrate data collection runs end-to-end (with flexible level of human-in-the-loop), while still supporting a fully manual flow through the standalone Python script together with the ChatGPT web interface to help you draft task configs. Any reasonably capable coding agent can operate the workflow: give it a short task description, point it to for orientation, and it will draft configs, gather entities from a CSV you provide, or even curate the list online itself when internet access is available before running the pipeline. Key Advantages Solving the Long-Horizon Entity Collection Problem Traditional deep research tools excel at individual deep-dive inquiries but struggle with structured data collection tasks that require gathering information for long lists of entities. Data Parasite exploits a key insight: entity collection is embarrassingly parallel.
| Stars | 86 |
| Forks | 3 |
| Language | JavaScript |
| Category | Agent Tool |
| License | BSD-3-Clause |
| Quality Score | 65.5581058078726/100 |
| Last Updated | 2026-01-26 |
| Created | 2025-11-02 |
| Platforms | node |
| Est. Tokens | ~9k |
Looking for a DataParasite alternative? If you're comparing DataParasite 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.
A curated list of tools, papers, and datasets for applying AI to cybersecurity tasks. This list primarily focu
GEO 领域 AI 员工开源方案 · Open-source GEO AI-employee solution (MIT). GEO Skills package + curated lists of agents an
Build, Improve Performance, and Productionize your LLM Application with an Integrated Framework
Practical techniques for coding with ai assistants (Claude Code, Codex CLI, Cursor, GitHub Copilot, etc). Avai
mcp store manager, add & syncs MCP server configurations across clients like Claude code, Cursor💡mcphub
Lightweight AI Agent Harness for agentic coding: let strong models explore while humans steer with minimal spe
Explore other popular agent tool tools:
DataParasite is A simple yet versatile context engineered for scalable online data collection. It is categorized as a Agent Tool with 86 GitHub stars.
DataParasite is primarily written in JavaScript. It covers topics such as awesome, computational-social-science, data-curation.
You can find installation instructions and usage details in the DataParasite GitHub repository at github.com/mengysun/DataParasite. The project has 86 stars and 3 forks, indicating an active community.
DataParasite is released under the BSD-3-Clause license, making it free to use and modify according to the license terms.
The top alternatives to DataParasite on Agent Skills Hub include Awesome-AI-For-Security, recomby-geo, palico-ai. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.