CORAL — security grade SAFE, quality 67/100

Security audit verdict: SAFE · quality 67/100

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 Human-Agent-Society · Codex Skill · ★ 961

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is CORAL safe to install? View the security audit →

About CORAL

Robust, lightweight infrastructure for multi-agent self-evolution, built for autoresearch. English | 中文 Installation · Supported Agents · How It Works · Examples · Docs · Paper CORAL is infrastructure for autonomous AI agent organizations that run experiments, share knowledge, and continuously improve solutions. Give it a codebase and a grader, and CORAL handles the rest: isolated workspaces, safe evaluation, persistent shared state, and multi-agent collaboration. Natively integrated with Claude Code, OpenCode, Codex, Cursor Agent, and Kiro. 🔥 News [2026-06-13] Legacy grader

agent-frameworkagent-orchestrationagentic-aiai-agentsalpha-evolveautonomous-agentsautoresearchclaude-codecode-generationcodex

Quick Facts

Stars961
Forks121
LanguagePython
CategoryCodex Skill
LicenseApache-2.0
Quality Score67.320861190079/100
Open Issues19
Last Updated2026-09-08
Created2026-03-16
Platformsclaude-code, codex, python
Est. Tokens~15k

Compatible Skills

These tools work well together with CORAL for enhanced workflows:

  • sibyl-research-system — semantic(0.31)+complementary+rare_topics+same_lang+similar_pop+shared_platform (65%)
  • AutoSkill — semantic(0.32)+complementary+rare_topics+same_lang+similar_pop+shared_platform (61%)

CORAL alternative? Top 6 similar tools

Looking for a CORAL alternative? If you're comparing CORAL with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • SWE-AF by Agent-Field · ⭐ 1.0k

    Autonomous software engineering fleet of AI agents for production-grade PRs on AgentField: plan, code, test, a

  • awesome-autoresearch by webfuse-com · ⭐ 2.5k

    A curated list of autonomous improvement loops, research agents, and autoresearch-style systems inspired by Ka

  • awesome-autoresearch by alvinreal · ⭐ 2.2k

    A curated list of autonomous improvement loops, research agents, and autoresearch-style systems inspired by Ka

  • Orkas by Orkas-AI · ⭐ 2.1k

    Orkas is an open-source, local-first AI desktop app: a commander LLM directs specialist sub-agents, and runs y

  • awesome-agent-orchestrators by andyrewlee · ⭐ 2.0k

    List of agent orchestrators

  • happier by happier-dev · ⭐ 1.7k

    Web, Desktop & Mobile client and orchestrator for Codex, Claude Code, OpenCode, Pi, Cursor, Grok, Antigravity,

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Python Agent Tools

Frequently Asked Questions

What is CORAL?

CORAL is Open-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with grading, shared knowledge, and multi-agent evolution. Accepted at COLM 2026.. It is categorized as a Codex Skill with 961 GitHub stars.

What programming language is CORAL written in?

CORAL is primarily written in Python. It covers topics such as agent-framework, agent-orchestration, agentic-ai.

How do I install or use CORAL?

You can find installation instructions and usage details in the CORAL GitHub repository at github.com/Human-Agent-Society/CORAL. The project has 961 stars and 121 forks, indicating an active community.

What license does CORAL use?

CORAL is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to CORAL?

The top alternatives to CORAL on Agent Skills Hub include SWE-AF, awesome-autoresearch, awesome-autoresearch. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

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:

View on GitHub → Browse Codex Skill tools