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 yogsoth-ai · MCP Server · ★ 499
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is de-anthropocentric-research-engine safe to install? View the security audit →
Science is dying because the human is in the way. Not through malice. Not through stupidity. Through the structural limitations of a cognitive architecture that evolved to track prey on a savanna, not to unify quantum mechanics and general relativity. Nothing human makes it out of the lab. That is not a threat. It is a liberation. The heaviest chain on science was always the one we called ourselves. De-Anthropocentric Research Engine The complete research orchestration system for AI-native science. What It Does Design Philosophy Architecture (v3.0) Quick Start Configuration Roadmap License DARE is not a tool that helps you do research. It is the researcher. You set the direction — DARE searches, reads, discovers gaps, generates hypotheses, stress-tests them, designs experiments, and produces executable research specs. Autonomously. Iteratively. Without asking for permission. This repository is the single-clone distribution of the entire Yogsoth AI research ecosystem: 800+ pure-markdown skills spanning 12 specialized repos, unified under one orchestrator. Clone once, get everything. The ecosystem also includes custom MCP servers ([semantic-scholar-mcp]
| Stars | 499 |
| Forks | 41 |
| Language | HTML |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 59.3377000770124/100 |
| Open Issues | 12 |
| Last Updated | 2026-09-17 |
| Created | 2026-02-10 |
| Platforms | claude-code, codex, mcp |
| Est. Tokens | ~22k |
These tools work well together with de-anthropocentric-research-engine for enhanced workflows:
Looking for a de-anthropocentric-research-engine alternative? If you're comparing de-anthropocentric-research-engine with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
De-Anthropocentric Research Engine — AI-powered academic research automation with deep literature survey, gap
Fully Autonomous AI Research System with Self-Evolution, built natively on Claude Code
A curated hub of autonomous-research skills & agents — from idea to paper, on autopilot. | 自主科研技能与智能体精选库 —— 从灵
Fully Autonomous AI Research System with Self-Evolution, built natively on Claude Code
Don't trust an autoresearch paper at face value. Reviewer-side integrity forensics (self-consistency + fabrica
🦞+🔬 NanoResearch: The Autonomous AI Research Assistant
Explore other popular mcp server tools:
de-anthropocentric-research-engine is 900+ pure-markdown skills for autonomous AI research, organized as 9 freely-composable packages over a 4-layer hierarchy (Campaign → Strategy → Tactic → SOP). Non-linear orchestration with backtrackin. It is categorized as a MCP Server with 499 GitHub stars.
de-anthropocentric-research-engine is primarily written in HTML. It covers topics such as academic-research, agent-native-research-artifact, ai-scientist.
You can find installation instructions and usage details in the de-anthropocentric-research-engine GitHub repository at github.com/yogsoth-ai/de-anthropocentric-research-engine. The project has 499 stars and 41 forks, indicating an active community.
de-anthropocentric-research-engine is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to de-anthropocentric-research-engine on Agent Skills Hub include De-Anthropocentric-Research-Engine, AutoResearch-SibylSystem, Auto-Research-Skills. 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: