by Human-Agent-Society · Codex Skill · ★ 877
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is CORAL safe to install? View the security audit →
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
| Stars | 877 |
| Forks | 117 |
| Language | Python |
| Category | Codex Skill |
| License | Apache-2.0 |
| Quality Score | 67.320861190079/100 |
| Open Issues | 19 |
| Last Updated | 2026-08-08 |
| Created | 2026-03-16 |
| Platforms | claude-code, codex, python |
| Est. Tokens | ~15k |
These tools work well together with CORAL for enhanced workflows:
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.
Autonomous software engineering fleet of AI agents for production-grade PRs on AgentField: plan, code, test, a
Open-source control plane for AI coding agents — run, monitor & orchestrate dozens of parallel Claude Code, Co
Deterministic orchestrator for 30+ CLI AI coding agents. Git worktree isolation, HMAC audit trail, MCP server
A curated list of autonomous improvement loops, research agents, and autoresearch-style systems inspired by Ka
A curated list of autonomous improvement loops, research agents, and autoresearch-style systems inspired by Ka
TAKT Agent Koordination Topology - Define how AI agents coordinate, where humans intervene, and what gets reco
Explore other popular codex skill tools:
CORAL is Open-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with grading, shared memory, and multi-agent evolution. Accepted at COLM 2026.. It is categorized as a Codex Skill with 877 GitHub stars.
CORAL is primarily written in Python. It covers topics such as agent-framework, agent-orchestration, agentic-ai.
You can find installation instructions and usage details in the CORAL GitHub repository at github.com/Human-Agent-Society/CORAL. The project has 877 stars and 117 forks, indicating an active community.
CORAL is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to CORAL on Agent Skills Hub include SWE-AF, amux, bernstein. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.