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 KeaBase · Agent Tool · ★ 200
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is kea-research safe to install? View the security audit →
5 AIs. 4 Steps. 1 Answer You Can Trust. Multi-AI collaboration platform that combines responses from multiple AI models, cross-validates information, and delivers verified, consensus-backed answers. The Challenge When you ask a question to different AI models, you often get different answers — each presented with equal confidence. There is no built-in mechanism to determine which response is most accurate or to identify potentially incorrect information. KEA Research addresses this by orchestrating multiple AI models to work together, evaluate each other's responses, and surface only the information that achieves consensus. See It In Action Installation & Update Requires Docker: Docker Desktop (Mac/Windows) or Docker Engine (Linux) Same command installs or updates — it detects existing installation automatically. Linux / Mac Windows (PowerShell)
| Stars | 200 |
| Forks | 17 |
| Language | TypeScript |
| Category | Agent Tool |
| Quality Score | 66.0938107789338/100 |
| Open Issues | 1 |
| Last Updated | 2026-01-25 |
| Created | 2026-01-17 |
| Platforms | gemini, node |
| Est. Tokens | ~268k |
These tools work well together with kea-research for enhanced workflows:
Looking for a kea-research alternative? If you're comparing kea-research 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.
TypeScript SDK to call 100+ LLM Providers in OpenAI format.
Python library for building with LLMs. One interface across 11 providers (OpenAI, Anthropic, Gemini, DeepSeek,
Agent samples built using the Strands Agents SDK.
A Python library powered by Language Models (LLMs) for conversational data discovery and analysis.
Run LLM prompts from your shell
An example agent demonstrating streaming, tool use, and interactivity from your terminal. This agent builder c
Explore other popular agent tool tools:
kea-research is KEA Research - Multi-AI collaboration platform that combines responses from multiple AI models, cross-validates information, and delivers verified, consensus-backed answers.. It is categorized as a Agent Tool with 200 GitHub stars.
kea-research is primarily written in TypeScript. It covers topics such as ai, anthropic, gemini.
You can find installation instructions and usage details in the kea-research GitHub repository at github.com/KeaBase/kea-research. The project has 200 stars and 17 forks, indicating an active community.
The top alternatives to kea-research on Agent Skills Hub include abso, SimplerLLM, samples. 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: