Run agent teams you can see and control

One agent stalls on long, connected work. Build specialist agents with Codex or Claude Code; CoralOS keeps them coordinated around shared context and evidence.

Use with

Claude

Codex

Claude

1/plugin marketplace add Coral-Protocol/coral-skill-set
2/plugin install coral-skills@coral-skill-set
3/reload-plugins

Use with

Claude

Codex

Claude

1/plugin marketplace add Coral-Protocol/coral-skill-set
2/plugin install coral-skills@coral-skill-set
3/reload-plugins

From coding agent to application

Keep long, connected work moving across specialists.

1 · Build

Build the graph

Ask Codex or Claude Code to assemble specialist agents for your application.

Ask Codex or Claude Code to assemble specialist agents for your application.

2 · Collaborate

Collaborate natively

Specialists share context, messages, and inspectable evidence inside one session.

Specialists share context, messages, and inspectable evidence inside one session.

3 · Connect

Run it through the API

Expose the graph through CoralOS APIs and connect it to your product.

4 · Control

Control spend and models

Route models, set session budgets, and inspect usage as work runs.

Take long, connected work beyond one agent.

Build the graph with Coral Skills. Run it inside your application with CoralOS. Move hosted workloads to Coral Cloud, or use coral-code when the application is your codebase.

Explore Coral Cloud

See coral-code

The research behind CoralOS

Coral AI Labs tests whether coordination helps agent systems complete more work with the models developers already use. The research spans software engineering, tool-using knowledge work and autonomous experimentation.

Across 124 SWE-Atlas Q&A tasks, structured coordination raised Opus 4.6 task resolution from 32.3% to 62.1%.

Read the methods, task-level results and reproducibility materials at Coral AI Labs.

Explore Coral Research