Run agent teams you can see and control

Build specialist agents with Codex or Claude Code. CoralOS gives them explicit communication, scoped application tools and an inspectable record of the work.

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

Turn a system brief into a running agent team.

1 · Design

Build the graph that fits

Use supervisors and pipelines for known sequences. Use topic threads, negotiation or temporary coalitions when the work changes as agents learn.

2 · Bound

Give agents clear responsibility

Define who can communicate, what each agent owns and which actions require approval. Keep durable product data in your application.

3 · Connect

Run it inside your product

Create an isolated session for each request. Pass in custom tools, surface progress through the API and receive results through webhooks.

4 · Inspect

See and control the work

Inspect agents, threads and message telemetry. Route models, configure fallbacks and control cost from one runtime.

What developers build

Use Coral in new and existing applications.

Deep research with mandatory review

Assign specialists to separate research angles. Let them write evidence to a shared blackboard, then require a negotiation before the system accepts the result. Codex can turn the agreed output into the requested document or presentation.

Improve an existing agent chain

Ask Codex to inspect a sequential specialist system and design a Coral topology that fits the work. Start a live session, then review its threads, proposals and agent state in Coral Console.

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

Controlled enterprise deployment

Bounded autonomy for regulated environments.

For enterprise teams operating under the EU AI Act and adjacent requirements, Coral supports on-prem deployment, isolated sessions, scoped tools and explicit approval boundaries. It gives engineers deterministic controls around probabilistic models, with inspectable threads and execution records for review.

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