# CORAL

> Open-source autoresearch framework that runs autonomous coding agents in isolated Git worktrees with continuous grading and shared memory.

CORAL is an open-source framework from Human-Agent-Society for running organizations of autonomous coding agents that run experiments, share knowledge, and keep improving a solution. Given a codebase and a grader, it handles isolated workspaces, evaluation, and persistent shared state. The latest GitHub release listed is v0.7.21, and the project is licensed under Apache 2.0.

## What It Is

CORAL is infrastructure for multi-agent autoresearch. A manager creates one Git worktree per agent plus a grader daemon. Agents read generated instructions (CORAL.md), change code, commit, and run an eval command. Each attempt is scored by a user-supplied grader, and the agent sees the score and decides its next move.

## How the Loop Works

Shared state (attempts, notes, skills) lives under .coral/public/ and is symlinked into every worktree, so agents see each other's work in real time. Hidden grader state stays isolated under .coral/private/. The manager sends heartbeat prompts such as reflect, consolidate, and pivot. Version 0.6.0 added multi-island runs, which partition agents into isolated islands with scoped state and migration between islands.

## Agent Runtimes and Plugin

CORAL works with Claude Code (the default), Codex, Cursor Agent, Kiro, OpenCode, Pi, and DeepSeek Harness. Each must be installed and authenticated separately. A plugin for Claude Code and Codex bundles skills that guide setup, task authoring, and running experiments from inside your own agent.

## Setup Path and Examples

Install with a shell script that uses uv, then run coral init to scaffold a task and coral start -c task.yaml to launch agents. A CLI and a web dashboard (coral ui) support monitoring. Example tasks cover circle packing, a math conjecture, GPU and VLIW kernel optimization, MNIST, a Kaggle competition, and mRNA degradation prediction. Rubric-judge grader packages support open-ended tasks. The accompanying paper was accepted to COLM 2026.

## Features
- Isolated Git worktree per agent
- Grader daemon that scores every committed attempt
- Persistent shared state for attempts, notes, and skills
- Heartbeat prompts (reflect, consolidate, pivot)
- Multi-island runs with migration
- Custom grader packages and rubric LLM judges
- CLI (coral init/start/stop/status/eval/log)
- Web dashboard (coral ui)
- Claude Code and Codex plugin
- Docker session with agent/grader isolation
- LiteLLM gateway for custom models

## Integrations
Claude Code, Codex, Cursor Agent, Kiro, OpenCode, Pi, DeepSeek Harness, LiteLLM, Harbor, Docker

## Platforms
WEB, API, CLI

## Pricing
Open Source

## Version
v0.7.21

## Links
- Website: https://coral.compounding-intelligence.ai
- Documentation: https://coral.compounding-intelligence.ai/docs/
- Repository: https://github.com/Human-Agent-Society/CORAL
- EveryDev.ai: https://www.everydev.ai/tools/coral