CoCo 1.5.0 · the CoCo Research flagship
Each of the 495 requires a live, checkable source. Then 226 skills ship what they decided.
100% local. No telemetry.
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.
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.
386
Commands
44 shipped, plus 342 generated locally at install from the team registries.
35
Agents
Specialists that carry the decision into code, review it, and verify the result.
Not prompt snippets. Every skill carries state management, verification logic and error handling, so the work survives being handed between sessions and between tools.
Orchestrate
A four-layer role pipeline behind /team: research, execute, review, synthesize. It ships with the core install; there is nothing to enable.
Remember
Six skills that keep durable project knowledge, so context outlives the session it was learned in.
Travel
Claude Code, Cursor, and Codex, from one install. The adapter changes; bundle availability varies.
Nothing here is hypothetical. Every row is a real workflow, compared with and without a routed panel and a build pipeline behind it.
Clone the repo, then run this. It installs Superintelligence into the editor you already have: Claude Code, Cursor, or Codex. Your keys never leave your machine.
Step one
bash install.sh --systems superintelligenceStep two
The installer asks before it enables Superintelligence. Nothing big runs until you approve it.
Step three
/SI-Decide "should we migrate to Postgres?"The install script pauses on an explicit yes or no before activating anything.
| Version | 1.5.0 |
|---|---|
| Skills | 226 in the repository (74 core + 152 bundle). |
| Commands | 386 customer-facing (44 shipped + 342 generated at install). |
| Agents | 35. 11 core, plus 24 in the GSD bundle. |
| Personas | 495 across 13 departments, each behind an evidence-validation gate. |
| Editors | Claude Code, Cursor, Codex, and any AGENTS.md-compatible tool. |
| Execution | Entirely local. No telemetry, and no command files transmitted or stored remotely. |
| Install | Roughly 90 seconds, with a fail-closed commit confirmation before anything runs. |
| Bundles | 6 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. |
| Licence | Open core. MIT core, with the Super Intelligence system licensed separately and kept proprietary. |