Coco Super Intelligence turns the coding agent you already use into a team of specialists. One command installs it.

Your editor, arguing with itself before anything ships.

Your call

Coco's files and state stay on your machine. No telemetry. A version check may contact GitHub once a day.

The board argues before Coco answers.

Ask a hard question and Coco convenes the experts who actually disagree about it. They argue in rounds, positions move, and dissent is recorded by name rather than averaged away. You get the reasoning, the split, and who held which line.

A real SI-Decide run: routed panel, verdict, named dissent.

A real /SI-Decide run. The panel is routed, not fixed, and dissent is kept, not averaged away.

495

Expert personas

Each requires a live, checkable source link. Quotes are illustrative reconstructions, not verbatim; see the disclaimer.

13

Departments

Engineering, AI, product and design, finance, trading, legal and IP, risk and compliance, strategy, data, climate and energy, education, healthcare, sales and go-to-market.

388

Commands

46 shipped, plus 342 generated locally at install from the team registries.

34

Agents

Specialists that carry the decision into code, review it, and verify the result.

229 skills. One instruction set each.

Not prompt snippets.

Orchestrate

Teams

A four-layer role pipeline behind /team: research, execute, review, synthesize. It ships with the core install; there is nothing to enable.

Remember

Brain

Six skills that keep durable project knowledge, so context outlives the session it was learned in.

Travel

Any editor

Claude Code, Cursor, and Codex, from one install. The adapter changes; bundle availability varies.

Claude Code, Cursor, and Codex CLI shown as three identical cards, unified under one Coco layer
One layer. It installs into Claude Code, Cursor, or Codex CLI.

The same five situations, with a board behind them.

A five-row comparison of a standard AI assistant versus a Coco-orchestrated workspace, across hard decisions, feature development, code auditing, system debugging, and context resets
Before Coco and after, across five real workflows.

About 3 minutes on a fresh machine, including the download.

npx cocosuperintelligence installs the latest release. It clones the pinned release tag (currently v1.10.0, not floating main) into ./coco of the current directory, then runs install.sh. Run it from your home folder, so the clone is ~/coco and not a folder inside another project. Your model and your keys stay yours.

Step one

Run it

npx cocosuperintelligence

Step two

Convene the board

/SI-Decide "should we migrate to Postgres?"

Each of the 495 requires a live, checkable source. Then 229 skills ship what they decided.

By the numbers

Version1.10.0
Skills229 in the repository (77 core + 152 bundle).
Commands388 customer-facing (46 shipped + 342 generated at install).
Agents34. 10 core, plus 24 in the GSD bundle.
Personas495 across 13 departments, each behind an evidence-validation gate.
EditorsClaude Code, Cursor, Codex, and any AGENTS.md-compatible tool.
ExecutionCoco's files and state stay on your machine. Your coding agent still uses its own model provider. No telemetry and no hosted service; one optional version check against GitHub per day (COCO_NO_UPDATE_CHECK=1 turns it off).
InstallAbout 3 minutes on a fresh machine, including the download. The remote bootstrap prints the commit and waits for you to type y before it runs install.sh.
Bundles6 system bundles, installed by default: GSD (68 skills, 24 agents), HyperFrames (20 skills), Super Intelligence (13 skills), Brain (6 skills), M0 (4 skills), and Cognee (3 skills). --core-only skips them; the reverse-skill security pack is opt-in with --systems reverse-skill.
LicenceOpen-core — most of the framework is Apache-2.0; the Super Intelligence board is proprietary.