coco

CoCo Super Intelligence

Summon an advisory board of 495 world-class minds — right inside your AI coding session.

CoCo Super Intelligence is the orchestration layer that turns Claude Code, Cursor, or Codex into an entire engineering department: routed expert panels that deliberate and decide, then 226 skills, 386 commands, and disk-persistent state that ship what they decided.

Open-core (MIT core · proprietary Super Intelligence) · installs in 90 seconds · 100% local · no telemetry

---

One developer writing single prompts? That was last year.

CoCo Super Intelligence convenes a cross-team board of 495 named experts to pressure-test your hardest calls — then puts an orchestrated team of agents to work executing the verdict: parallel build waves, deterministic verification gates, and phase state that survives every /clear.

npx cocosuperintelligence
# or: npm i -g cocosuperintelligence && coco
# alternate: git clone https://github.com/coco-research/coco.git && cd coco && bash install.sh

---

What CoCo Is (and Isn't)

CoCo is not a new AI model, and it is not another agent harness. It doesn't run a model or an agent loop of its own. It's a portable layer of Markdown and YAML that installs into the agent harness you already use — Claude Code, Cursor, Codex CLI, or any AGENTS.md-compatible tool — and upgrades it with an expert advisory board, a skills library, persistent project memory, specialized subagents, and verification gates.

Your model, your tool, your keys, your machine. When you see "parallel subagent waves," those subagents are executed by your host harness's own agent machinery; CoCo supplies the orchestration structure that makes it all behave like a coordinated team. That is exactly why CoCo is vendor-neutral: it's the operating layer, not the engine.

---

⭐ The Board — CoCo Super Intelligence

A cross-team advisory board of 495 world-class minds

Super Intelligence is CoCo's signature capability. It lets you summon custom, real-world expert panels directly inside your coding session to guide architectural, engineering, risk, finance, and business decisions — each contribution attributed to a named expert, grounded in cited public sources.

/SI-Decide "Should we migrate our database to pgvector?"
/SI-AI-Decide "Which embedding model gives the best cost/performance?"
/SI-Eng-Pre-Mortem "Review our zero-downtime cache migration strategy"
/SI-GRC-Review "Check this customer onboarding flow for GDPR compliance"

495 expert personas, organized across 13 specialized departments:

Department	Experts	Focus
Engineering	70	Software architecture, cloud systems, systems coding, compilers, infrastructure
AI	59	Neural-network research, LLM optimization, safety, alignment, vector databases
Product & Design	56	Design systems, UX, product strategy, growth loops
Finance	47	Valuation, corporate finance, macro modeling, fintech infrastructure
Trading	46	Quant analysis, market microstructure, derivatives pricing, crypto liquidity
Legal & IP	31	Privacy law, antitrust, patent and copyright policy, digital rights
Risk & Compliance (GRC)	30	GDPR, HIPAA, SOC 2, security auditing, international regulation
Strategy	29	Platform economics, business models, competitive analysis
Data & Analytics	29	Data engineering, pipeline optimization, predictive modeling
Climate & Energy	25	Decarbonization policy, clean-energy economics, carbon markets, circular economy
Education & EdTech	25	Learning science, curriculum design, education policy, assessment
Healthcare & Life Sciences	25	Health economics, genomics, clinical medicine, public health policy
Sales / GTM / Marketing	23	Product-market fit, sales ops, growth marketing, enterprise GTM

• 342 generated slash commands. 17 cross-team meta commands (like /SI-Decide or /SI-Tradeoff, routing across domains) plus 325 per-team commands (25 verbs × 13 teams, such as /SI-AI-Decide or /SI-Eng-Pre-Mortem). These are generated locally at install time from the team registries — no command files are transmitted or stored remotely.
• 70 expertise cells. Each department is subdivided into focused cells (e.g. Engineering has 11, AI has 8) so the router can assemble a precise panel rather than a generic crowd.
• Cross-team meta-orchestration. For complex queries spanning domains ("build and sell an AI audit tool"), a local router scores your prompt against team registries and cells, then greedily assembles a proportional 16–32-person panel.
• Citable and grounded. Every stance is verified from public sources and carries a direct evidence URL. Personas are validated against a strict anti-fabrication gate.
• --debate deliberation. Panels can argue in reacting rounds before returning a verdict, surfacing named dissent instead of false consensus.

The selection algorithm (two-stage routing + approval)

The meta-orchestrator uses a staged algorithm so it never has to load the entire persona filesystem at runtime:

1. Stage A — team & cell routing (cheap). Reads the meta-registry (systems/superintelligence/registry.json) and scans only team descriptions and cell definitions, scoring relevance by keyword and domain overlap to select the top 1–4 teams. If one team dominates, it delegates to that team's own orchestrator.
2. Stage B — scoped persona selection. Loads compact persona records (slugs, cells, domains, stances, conflict mappings) for only the selected teams, allocates the 16–32-person budget proportionally, runs the greedy scorer (0.40·domain + 0.30·cell-coverage + 0.30·conflict-pairing), and applies a cross-team tension pass to pair opposing viewpoints (e.g. security vs. growth).
3. Stage C — approval & execution. Presents the roster grouped by team with a one-line rationale. The action verb then consumes the approved roster and returns output with full line-by-line attribution (e.g. "Aswath Damodaran (Finance): …").

Persona build & validation pipeline

The 495-persona roster was compiled with a systematic multi-tier workflow. Candidate generation was evaluated across local Qwen (via LM Studio), a hosted small model, and Gemini Flash, but Claude research agents proved the quality winner for resolving historical data and citing verifiable signal. Personas are checked by an advisory validation gate (validate_persona.py) that enforces five things: every required frontmatter field is present; at least 4 cited URLs resolve live (non-404); every public_stance carries an evidence_url, so no stance is uncited; at least 2 recent signals within 12 months (or 2 persistent signals for historical archetypes); and any pairs_well_with / productive_conflict_with slug refers to a real roster member. Two limits are worth stating plainly: the gate confirms that a stance is cited, not that a quotation is authentic, and home_team is only checked for presence, not validated against the list of real teams. A NEEDS-TOPUP verdict is advisory — it does not currently affect which personas a council selects at runtime.

---

The Framework Underneath

The board decides. The framework ships. Three pillars turn the verdict into merged, verified code.

1. Autonomous team execution

/team:ship runs a fully coordinated build pipeline — 6 development stages, 7 hard verification gates, and 2 architecture conformance gates. Specialized agents act in their domains (Research, Architecture, Plan, Review, Build, QA). Code must clear the Test Evidence Protocol (independent re-runs, strict coverage, skip-prevention) and land where the plan said it would before a pull request is opened.

2. Disk-persistent state

AI chat context is fragile and wipes on /clear. CoCo persists phase state, decisions, and progress logs to disk across resets, with atomic git commits for every successful step — so you can review history, roll back a bad design path, or resume a long-running migration from any checkpoint.

3. Vendor-neutral portability

CoCo compiles its rules, templates, and agent definitions into pure Markdown and YAML frontmatter. Native IDE adapters inject the same library into Claude Code, Cursor, Codex CLI, PI-Desktop, VS Code, or any AGENTS.md tool — so your workflows follow you even if you switch AI editors.

---

Architecture conformance: the gate tests cannot give you

Every test suite in existence shares one blind spot. Tests fail when behaviour breaks — not when your architecture quietly dissolves. A component can be relocated, folded into another module, or deleted outright, and a green build will tell you nothing. Requirements pass. Coverage holds. The design you agreed to is gone.