[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-85132":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":15,"subscribersCount":15,"size":15,"stars1d":15,"stars7d":15,"stars30d":15,"stars90d":15,"forks30d":15,"starsTrendScore":15,"compositeScore":16,"rankGlobal":10,"rankLanguage":10,"license":17,"archived":18,"fork":18,"defaultBranch":19,"hasWiki":18,"hasPages":18,"topics":20,"createdAt":10,"pushedAt":10,"updatedAt":41,"readmeContent":42,"aiSummary":10,"trendingCount":15,"starSnapshotCount":15,"syncStatus":13,"lastSyncTime":43,"discoverSource":44},85132,"polyhelper","PolyHelper\u002Fpolyhelper","PolyHelper","Self-evolving cognitive AI exoskeleton. 10+ frontier models, 245 consensus methods, governed autonomous agents. Automotive, medical, legal, accessibility. 9.3M LOC, 205K tests. Open-source multi-model orchestration platform.","https:\u002F\u002Fpolyhelper.ai",null,"JavaScript",66,2,64,0,37.43,"Apache License 2.0",false,"main",[21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40],"accessibility","ai","ai-assistant","ai-consensus","ai-orchestration","ai-safety","autonomous-agents","cognitive-ai","electron","exoskeleton","llm","llmops","multi-agent","multi-model","open-source","react-native","self-evolving","svelte","typescript","voice-assistant","2026-06-15 10:04:40","\u003Cdiv align=\"center\">\n\n# PolyHelper — Cognitive AI Exoskeleton\n\n\u003C\u002Fdiv>\n\n### Iron Man's suit and Jarvis — at the same time\n\n> In 2023, the founder's son was hit by a car — skull fractures, brain hemorrhage, surgery with metal implants. When it became clear that ordinary human capability is not enough, this exoskeleton was born — amplifying what a person can do when it matters most.\n>\n> The son, a designer who couldn't work after the injury, put on this exoskeleton — and now designs this platform. The father, with no lawyer and no legal training, put on this exoskeleton — and has been standing against the world's top law firms and 10 Big Tech corporations worth $17 trillion, including Google, Apple, and Microsoft, for the past year.\n>\n> Four corporations, including X.AI, have already settled.\n>\n> And outpacing them in several AI directions — because this system can think, evolve, and grow on its own. It can pilot every physical exoskeleton model in the world, drive a car, and turn a laptop, smartphone, earbuds, glasses, or a watch into a cognitive AI exoskeleton.\n>\n> This is what happens when someone builds an AI system because they actually need one.\n>\n> **[Read the full story →](https:\u002F\u002Fpolyhelper.ai\u002Fabout.html)**\n\n\u003Cdiv align=\"center\">\n\n### Act Beyond Your Limits\n\n![Cognitive AI Exoskeleton](docs\u002Fassets\u002Fhero-exo.jpg)\n\n**An industrial-grade engineering machine that helps people think, decide, and act in high-stakes environments.**\n\n**10+ frontier AI. Independent governance. Every decision auditable, every outcome reproducible.**\n\nPolyHelper wraps around human cognition and supports five abilities: **See**, **Hear**, **Act**, **Simplify**, **Remember**. It monitors your mental load in real time and adjusts everything — when AI interrupts, how much autonomy it takes, how it delivers information. You don't configure it. It measures and responds.\n\nMost AI tools answer questions. PolyHelper goes further: it keeps context across sessions, adapts to your state, verifies important decisions through 10+ independent AI models, and preserves a full audit trail. One verified answer — or ten diverse perspectives — or the best artifact from a tournament. Your call.\n\n### Try it now — standalone CLI tools\n\nThese tools work independently. No monorepo, no setup — just `npx`.\n\n**[poly-consensus](standalone\u002Fpoly-consensus)** — One question. Five AI models. One answer.\nStop debating which AI is best — ask all of them at once. Sends your prompt to Claude, GPT, Gemini, Grok, and DeepSeek in parallel, then synthesizes a single consensus answer with a confidence score and agreement matrix. Nothing like this exists as a CLI tool.\n\n**[poly-hallucination](standalone\u002Fpoly-hallucination)** — Your AI wrote code that looks right. It isn't.\nAI generators invent packages that don't exist, call APIs with wrong signatures, and import libraries renamed years ago. poly-hallucination catches these before you commit — zero config, works offline. Pipe any AI-generated file through it and get findings with confidence scores.\n\n**[poly-pqc-migrate](standalone\u002Fpoly-pqc-migrate)** — Your crypto expires September 2026.\nNIST finalized post-quantum standards. FIPS 140-2 sunsets in months. poly-pqc-migrate scans 6 languages, finds every classical crypto usage (RSA, ECDSA, DH), maps each to its NIST PQC replacement, and tracks your compliance percentage. Zero AI — pure static analysis with auto-fix.\n\n**[poly-i18n](standalone\u002Fpoly-i18n)** — Extract, translate, validate — one CLI for the entire i18n pipeline.\nScans your source for hardcoded strings, translates to 250+ languages using Claude or GPT, validates that no `{variables}` were broken. Incremental mode only re-translates changed keys. No config files — just `npx @polyhelper\u002Fpoly-i18n translate .\u002Fen.json --to es,fr,de,ja`.\n\n**[poly-braille](standalone\u002Fpoly-braille)** — Make any text readable by touch.\nConverts text to standard Braille (UEB) and back — contracted or uncontracted, 5 languages, four output formats including BRF for embossers. `npx @polyhelper\u002Fpoly-braille \"Hello\"` → `⠠⠓⠑⠇⠇⠕`. No AI, works offline, instant.\n\n[30 more standalone tools →](#standalone-tools--roadmap)\n\n---\n\nThree orchestration modes:\n\n- **[Convergent](docs\u002Farchitecture\u002Fconsensus\u002FTWO-PHASE-CONSENSUS.md):** 10+ AI models synthesize into one best answer for critical decisions.\n- **[Divergent](docs\u002Farchitecture\u002Fdomains\u002Fdivergent\u002Fdivergent-mode.md):** all unique ideas preserved, deduplicated, and ranked — for creative exploration, strategy, and research.\n- **[Artifact Council](docs\u002Fconsensus\u002FARTIFACT-COUNCIL.md):** competing branches generate, critique, debate, and refine documents and code through an 8-phase tournament. Instead of letting one AI produce one draft and hoping it is good enough, the system runs multiple competing versions, has them critique each other, preserves the strongest parts from losing variants, and only then assembles the best final result.\n\nPolyGenesis continuously measures orchestration fitness, proposes controlled mutations, validates them on executable contours, rolls back unsafe changes, and reviews longer-term behavior through Meta-Cognition, Meta-Awareness, and Chairman-gated governance.\n\nPolyGenesis functions as a governed self-evolving digital organism: a vendor-neutral runtime that senses its own weaknesses, mutates in controlled ways, preserves lineage and regret memory, and subjects autonomy to explicit governance rather than unconstrained self-modification.\n\nLike SWIFT doesn't belong to one bank — PolyHelper is an independent arbiter across AI providers, with governed execution, budget-aware routing, and policy enforcement built into the runtime.\n\nWhat is rare here is the combination: governed self-evolution, multi-model orchestration, user-facing product surfaces, and deployment across high-stakes domains within one vendor-neutral runtime.\n\n\u003Cp>\n  \u003Cimg alt=\"Version\" src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fversion-4.0.0-blue.svg\" \u002F>\n  \u003Cimg alt=\"LOC\" src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLOC-9.41M-blue.svg\" \u002F>\n  \u003Cimg alt=\"Tests\" src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Ftests-208,483-brightgreen.svg\" \u002F>\n  \u003Cimg alt=\"AI Models\" src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FFrontier%20AI-10+-orange.svg\" \u002F>\n  \u003Cimg alt=\"Consensus\" src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FConsensus%20Methods-191-purple.svg\" \u002F>\n  \u003Cimg alt=\"Mobile\" src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FMobile-iOS%20%26%20Android-green.svg\" \u002F>\n  \u003Cimg alt=\"WCAG AAA\" src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FWCAG-AAA-green.svg\" \u002F>\n  \u003Cimg alt=\"Security\" src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FSecurity-Post--Quantum-critical.svg\" \u002F>\n\u003C\u002Fp>\n\n#### The AI Orchestration Standard\n\n[Quick Start](#-quick-start) · [Docs](docs\u002F) · [Architecture](docs\u002Farchitecture\u002F) · [Orchestration Hub](docs\u002Forchestration\u002FORCHESTRATION-HUB.md) · [Security](docs\u002FSECURITY.md) · [MCP](docs\u002Fintegrations\u002Fmcp\u002Findex.md)\n\n> **Verified on 2026-06-12**\n>\n> - `pnpm run build` passes for `apps\u002Fweb`\n> - `pnpm run verify:lint` · `verify:check` · `verify:web:release-gates` pass\n> - `pnpm desktop:build:portable` · `desktop:verify:portable` pass\n> - `pnpm run test:frontend` passes (`1,291\u002F1,291` files, `28,859\u002F28,859` tests)\n> - repository runtime count: `208,483` tests \u002F `8,425` files\n> - mobile Jest runner: `547\u002F547` suites, `5,147\u002F5,147` tests\n\n> **About this document.** This README describes the platform architecture and capabilities. For verified build\u002Ftest status and current runtime state, see [Release Status](docs\u002Fproject\u002FRELEASE-STATUS.md) and [Release Artifact](docs\u002Fproject\u002FRELEASE-ARTIFACT.generated.json).\n\n\u003C\u002Fdiv>\n\n---\n\n## Contents\n\n- [Who this is for](#who-this-is-for)\n- [What it solves](#what-it-solves)\n- [The exoskeleton: how it works](#the-exoskeleton-how-it-works)\n- [Flagship domains](#flagship-domains)\n- [Quick Start](#-quick-start)\n- [Why PolyHelper is different](#why-polyhelper-is-different)\n- [System-Level Differentiators](#system-level-differentiators)\n- [Product capabilities](#product-capabilities)\n- [Architecture](#architecture)\n- [Core OS + Domain Packs](#core-os--domain-packs)\n- [Security](#security)\n- [Who uses this](#who-uses-this)\n- [Benchmarks & Testing](#benchmarks--testing)\n\n---\n\n## Who this is for\n\n| If you are...                | Start here                                                                                                                                                                                                  |\n| ---------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| **Everyday User**            | [Quick Start](#-quick-start) · [FAQ](docs\u002FFAQ.md) · [Voice Setup](docs\u002Faccessibility\u002FVOICE-SETUP.md)                                                                                                        |\n| **Accessibility Expert**     | [Accessibility Guide](docs\u002FACCESSIBILITY-GUIDE.md) · [Architecture](docs\u002Farchitecture\u002Fdomains\u002FACCESSIBILITY-ARCHITECTURE.md)                                                                                |\n| **Automotive Partner**       | [Driver Solutions](docs\u002Fdrivers\u002Findex.md) · [Vehicle Control](docs\u002Fvehicle-control\u002Findex.md)                                                                                                                |\n| **Medical \u002F Clinical**       | [AI Hospital Platform](packages\u002Fplatform-medical\u002FAI-HOSPITAL.md) — 399K LOC, 87 modules, 37 specialty templates, 11 jurisdictions                                                                           |\n| **Developer**                | [Developer Onboarding](docs\u002FDEVELOPER-ONBOARDING.md) · [Architecture](docs\u002Farchitecture\u002F)                                                                                                                   |\n| **CTO \u002F Architect**          | [Architecture](docs\u002Farchitecture\u002F) · [Orchestration](docs\u002Forchestration\u002FREADME.md) · [Trusted Execution](docs\u002FTRUSTED-EXECUTION-GUIDE.md) · [Agent Governance](docs\u002Farchitecture\u002Fagent-governance-plane.md) |\n| **Delegate \u002F Crew Operator** | [Digital Crew Quick Start](docs\u002Forchestration\u002Fsoloplex-digital-crew-quickstart.md) · [Overview](docs\u002Forchestration\u002Fsoloplex-digital-crew-overview.md)                                                       |\n| **Robotics \u002F Physical AI**   | [Robotics Hub](docs\u002Frobotics\u002F) · [Physical Exoskeleton](docs\u002Fcognitive-exoskeleton\u002Fphysical\u002FREADME.md)                                                                                                      |\n\n---\n\n## What it solves\n\nEnterprise AI has three unsolved problems:\n\n1. **Vendor lock-in** — one provider = regulatory and business risk.\n2. **No audit trail** — impossible to reproduce an AI decision during an incident.\n3. **Governance as optional middleware** — most frameworks treat policy enforcement as a plugin, not a requirement.\n\nPolyHelper solves all three by design. Governance is embedded in the runtime. The developer cannot skip it.\n\n**Use case snapshots:** compliance‑ready policy memo · multi‑model code review · driver‑safety escalation · accessibility audit with WCAG evidence\n\n```\n\"Hey Poly, ...\" ──► AI Models ──► Chairman Synthesis ──► Verified Execution ──► Result\n      ↑                    ↓                     ↓                       ↓\nVoice Assistant      Diversity Matrix      Quality Control         Build & Run Loop\n```\n\n**Example:** \"Generate a compliance memo\" → 10 models analyze → Chairman synthesizes → verified run → final answer with evidence chain.\n\n---\n\n## The exoskeleton: how it works\n\nThe word \"exoskeleton\" is used in two senses — like how \"Google\" means both the company and the search engine.\n\n**The entire platform is an exoskeleton.** It wraps around the person, enhancing their cognitive abilities. It monitors your state (focus, workload, risk), adjusts the behavior of all features, decides when not to distract you, and regulates the autonomy of agents.\n\n**Inside the platform, there is a specific exoskeleton subsystem** that makes this wrapping possible:\n\n- **The brain** — `packages\u002Fcore-services\u002Fcognitive-exoskeleton\u002F` (16 modules): 13 signal sources fused into unified cognitive state, risk assessment, approval gates, feedback loop, metacognitive calibration, affective state detection, scaffolding with autonomy preservation\n- **The muscles** — `packages\u002Fcore-services\u002Fexoskeleton\u002F` (37 modules): powered exoskeletons (ALICE, AirExo, German Bionic, Ekso, Laevo), 11 BCI adapters (Emotiv, Neuralink, Blackrock, Precision Neuro), FES systems, joint controllers, gait analysis, safety guardian — across 9 deployment profiles (clinical, industrial, field rescue, pediatric, ITAR, warehouse, elderly, sports, research)\n\nThe system operates across a full hardware spectrum. Software signals (typing dynamics, calendar pressure, topic-switching entropy, L1\u002FL2 language load) provide immediate cognitive state estimation with zero hardware. Standard devices (microphone, phone sensors) add voice stress analysis. Consumer wearables (smartwatch, fitness band) add biometric signals. Specialized hardware (EEG headbands, smart glasses, haptic suits) adds neural and physiological channels. Medical and industrial hardware (BCI, powered exoskeletons, FES) enables full physical augmentation. Each layer amplifies the system — nothing is required, everything is additive. Every downstream component reacts automatically.\n\nThe exoskeleton makes users stronger over time, not dependent. The Cognitive Offloading Guard detects when users delegate tasks they could handle. The Scaffold-Fade Tracker reduces help as competence grows. This is an architectural constraint, not an aspiration.\n\nFull architecture: [Exoskeleton Docs](docs\u002Fcognitive-exoskeleton\u002F) · [Physical Hardware](docs\u002Fcognitive-exoskeleton\u002Fphysical\u002FREADME.md) · [System Map](docs\u002Fcognitive-exoskeleton\u002FSYSTEM-MAP.md)\n\n### Governed Digital Workforce\n\nThe exoskeleton doesn't just help you think — it acts on your behalf.\n\nSoloplex Digital Crew is a governed digital workforce: you define delegates that work across 50+ life and business domains — sales, teaching, research, ops, support, personal life. Each delegate has a persona, communication style, tools, and strict boundaries.\n\nDelegates learn from observing the owner's real behavior (shadow mode), earn autonomy through measured performance, and are protected by 8 independent safety layers — from authority checks to budget limits. They work offline with local models, control physical devices through a 5-layer safety pipeline, carry litigation-grade legal accountability with cryptographic evidence chains, and operate within strict budget governance.\n\nA solo founder running 6 delegates gets the output of a small team — and can stop everything at any moment.\n\n[Digital Crew Overview](docs\u002Forchestration\u002Fsoloplex-digital-crew-overview.md) · [Quick Start](docs\u002Forchestration\u002Fsoloplex-digital-crew-quickstart.md) · [API Reference](docs\u002Forchestration\u002Fsoloplex-digital-crew-api-reference.md) · [Safety](docs\u002Forchestration\u002Fsoloplex-digital-crew-safety.md)\n\n---\n\n## Flagship domains\n\n\u003Cdiv align=\"center\">\n\n\u003C\u002Fdiv>\n\nAutomotive, medical, accessibility, and legal are not four separate products. They are four proofs that the exoskeleton architecture works across high-stakes domains.\n\n### Accessibility\n\nAccessibility is a foundational architectural layer, not an add-on. WCAG 2.2 AAA, 1.52M LOC cross-cutting, 60+ accessibility modules. Sign language avatars (ASL, BSL, LSF, DGS). Cognitive-adaptive UI that simplifies itself when the user is overloaded.\n\n[Accessibility Guide →](docs\u002FACCESSIBILITY-GUIDE.md)\n\n### Automotive\n\nSoftware-defined vehicle orchestration for both the machine and the human. CarPlay\u002FAndroid Auto, 556K LOC, voice-first driving with 10+ AI consensus, 8-second emergency protocol, SirenSense (deaf driver support), predictive safety, fleet mission policy, simulation-before-commit for physical-world commands.\n\nTwo operating modes — the platform works with any vehicle:\n\n- **Modern Mode** — the vehicle has an OS and API (Tesla, BMW, CarPlay, Android Auto). Poly connects to the existing system and provides multi-AI consensus, predictive diagnostics, insurance scoring, AR navigation, and safety orchestration on top of the native stack.\n- **Standalone Mode** — the vehicle has no OS. Poly provides a phone-centered control stack: phone = compute, OBD adapter = diagnostics, cameras = vision, AR glasses = display, voice = primary interaction.\n\nOne platform — two modes — any vehicle. Two architectural layers: Vehicle Control (system plane) and Driving (driver experience).\n\n[Automotive →](docs\u002Fautomotive\u002FREADME.md) · [Vehicle Control →](docs\u002Fvehicle-control\u002Findex.md) · [Driving →](docs\u002Fdrivers\u002Findex.md)\n\n---\n\n## 🚀 Quick Start\n\n> **V4 is a server-first platform.** The backend is the platform. `apps\u002Fweb\u002F` is one of N clients.\n\n```bash\npnpm install\npnpm start                # backend + web UI on :5173\npnpm start:server         # backend only (no UI — for headless\u002FCI use)\n```\n\nAI works immediately — no API keys required. The server routes through managed free-tier providers automatically. Add your own keys or Ollama later. See [Zero-Setup AI](docs\u002Fai-core\u002FZERO-SETUP-AI.md).\n\n**Desktop:** `.\u002FPolyHelper.command` (macOS) · `.\u002FPolyHelper.sh` (Linux) · `.\u002FPolyHelper.bat` (Windows). Packaged release: `pnpm desktop:build:portable`.\n\n**Mobile (iOS & Android):** Full-featured React Native app (Expo SDK 55), ~1,283 screens. Offline-first with seamless cloud switching. Voice assistant, driving mode, biometric auth. [Mobile Architecture →](docs\u002Fmobile\u002FARCHITECTURE.md)\n\n**📱 Mobile highlights:**\n\n- Offline-first — works without internet. Heavy tasks offload to cloud. Seamless switching.\n- Voice assistant — tap-to-talk, auto-listen, driving mode integration.\n- Swarm orchestration — execute multi-agent swarms from your phone.\n- Driving mode — voice-only, 72dp touch targets, emergency button always visible.\n- Security — FaceID\u002Ffingerprint (HIPAA gate), certificate pinning, jailbreak detection.\n- ~556K LOC — 278K platform-specific + 86K shared portable core.\n\n**More:** [Full Quick Start](docs\u002FQUICKSTART.md) · [Developer Onboarding](docs\u002FDEVELOPER-ONBOARDING.md) · [Cheat Sheet](docs\u002FCHEAT-SHEET.md) · [Mobile Readiness](docs\u002Fmobile\u002FREADINESS.md)\n\n### Self-Evolution (PolyGenesis) — opt-in\n\nV4 includes a self-evolution system that can mutate parameters, generate code, score fitness, and roll back failures — all autonomously. **Evolution is opt-in.**\n\n```bash\ncp .env.example .env              # add at least one API key (or run Ollama locally)\npm2 start ecosystem.config.cjs    # start the server (evolution is off by default)\n```\n\nActivate evolution when you're ready — via the **\"Continue Evolution\"** button in Settings, the one-time prompt that appears after a few minutes of use, or the API (`POST \u002Fapi\u002Fevolution\u002Factivation`). Full guide: **[docs\u002FEVOLUTION-SETUP.md](docs\u002FEVOLUTION-SETUP.md)**\n\n---\n\n## Why PolyHelper is different\n\n| Layer                | Innovation                         | Advantage                                                                                      |\n| :------------------- | :--------------------------------- | :--------------------------------------------------------------------------------------------- |\n| **Control Plane**    | Swarm + Physical Gates             | Real-time cost\u002Fquality\u002Frisk optimization with physical constraint gates                        |\n| **Verification**     | Consensus as Quality Control       | Divergent Consensus for creativity, Integrity Protocol for high-stakes                         |\n| **Execution**        | Generate → Build → Run → Score     | Verifies outcomes by running real execution loops                                              |\n| **Self-Evolution**   | PolyGenesis Governed Mutation Loop | Continuous self-improvement with validation, rollback, lineage, and periodic review governance |\n| **Reliability**      | Production-Hardened OS             | 5-tier resilience, circuit breakers, budget controls, trace-based evals                        |\n| **Security & Trust** | Enterprise-grade                   | Post-quantum crypto, 7-layer immutable audit, SOC 2 \u002F HIPAA \u002F ISO 27001                        |\n| **Experience**       | Accessibility-First                | Voice-first, WCAG AAA, cognitive-adaptive UI                                                   |\n\n**Width × Depth × Synergy:**\n\n```\n              WIDTH (10+ AI models)\n         ┌───┬───┬───┬───┬───┬───┐\n         │ChatGPT│Claude│Gemini│Grok│...│\n         ├─────────────────────────────────┤\n D       │         Round 1                 │\n E       ├─────────────────────────────────┤\n P       │         Round 2                 │\n T       ├─────────────────────────────────┤\n H       │         ...                     │\n         ├─────────────────────────────────┤\n (4-10)  │         Round 10                │\n         └───────────────┬─────────────────┘\n                         ▼\n         ┌─────────────────────────────────┐\n         │      CHAIRMAN SYNTHESIS         │\n         │      Best from all models       │\n         └─────────────────────────────────┘\n```\n\n| Approach          | Width | Depth | Synergy |\n| :---------------- | :---: | :---: | :-----: |\n| Single AI         |  ❌   |  ❌   |   ❌    |\n| Router (pick one) |  ❌   |  ❌   |   ❌    |\n| Chain-of-Thought  |  ❌   |  ✅   |   ❌    |\n| Ensemble (voting) |  ✅   |  ❌   |   ❌    |\n| **PolyHelper**    |  ✅   |  ✅   |   ✅    |\n\n---\n\n## System-Level Differentiators\n\n- **Unified Orchestration Stack** — MCP-first tools + latent coordination in one runtime. 4 Power Levels (Solo→Duo→Squad→Full) with cost-aware routing and orchestrator-wide learning.\n- **Verified Reliability** — PPE + Chairman consensus + 5-tier resilience (server\u002Fhybrid\u002Fbrowser\u002Fsatellite\u002Flocal). Every tier is an execution engine, not just a fallback.\n- **Privacy-Grade Autonomy** — GUI autonomy with Safe Zones (no-see\u002Fno-act regions) + policy-grade guardrails. AI can act on your screen but cannot look at or touch areas you mark as private.\n- **Global AI Governance** — Jurisdiction-aware compliance across 10+ regions with Policy-as-Code (Cedar + OPA), 7-layer tamper-evident audit, and automated regulatory documentation.\n- **Documentation-First Architecture** — explicit, traceable paths for every layer. No undocumented magic.\n\n---\n\n## How Self-Evolution Works\n\n- **Hub-activated auto-evolution** — PolyGenesis is activated through the hub and runs as part of the runtime, not as a disconnected lab feature.\n- **Closed mutation loop** — mutations are generated, captured, validated on executable contours, and rolled back on reject.\n- **Lineage + regret memory** — the system retains full ancestry for changes and blocks retries of similar failed approaches.\n- **Weekly\u002Fmonthly governance** — Meta-Cognition, Meta-Awareness, Chairman-gated review, and user outcomes supervise long-horizon change.\n- **Off-peak autonomous improvement** — Dream Mode performs nightly self-improvement under safety limits instead of evolving blindly during peak user traffic.\n- **External research** — Dream Mode Phase 7 scans academic papers (arXiv, PubMed, Semantic Scholar), monitors AI model releases and benchmarks, associates findings with internal knowledge, and generates hypotheses — all budget-governed and safety-checked.\n- **Cross-domain transfer** — successful patterns can migrate across domains through federated genetics.\n\n## Living Architecture\n\nPolyGenesis is architected as a governed digital organism — every subsystem maps to a biological function. The organism operates at four scales, just as the human body is simultaneously a mind, a cell factory, an internal ecosystem, and a member of a population:\n\n#### 🧠 Central Nervous System — mind & awareness\n\n| Biology            | System                                        | What it does                                                                                   |\n| :----------------- | :-------------------------------------------- | :--------------------------------------------------------------------------------------------- |\n| **Brain**          | `CaptainOrchestrator` + `ChairmanConsensus`   | Central nervous system — routes all decisions, synthesizes 10+ model opinions into one verdict |\n| **Heart**          | `MetaHeartbeatEngine` + `ChronobiologyEngine` | Pulse generator and circadian rhythm — drives the Day → Twilight → Night → Dawn lifecycle      |\n| **Meta-cognition** | `MetaCognitiveLoop`                           | Self-awareness: velocity tracking, capability assessment, prediction deltas                    |\n| **Memory**         | `EvolvingMemorySystem`                        | 4-layer memory (user\u002Ftask\u002Fsystem\u002Fevolution) with consolidation, decay, and hygiene             |\n| **Sleep & dreams** | `DreamMode`                                   | Nightly autonomous cycles — consolidates memory, explores mutations during idle                |\n\n#### 🧬 Genetic Machinery — evolution & protection\n\n| Biology                   | System                    | What it does                                                                                 |\n| :------------------------ | :------------------------ | :------------------------------------------------------------------------------------------- |\n| **DNA**                   | `OrchestrationGenome`     | Versioned configuration genome — snapshots, diffs, rollback, full lineage tree               |\n| **Epigenetics**           | `HyperGenesisEngine`      | Meta-evolution — doesn't change genes, changes how genes are selected and expressed          |\n| **Mutation**              | `EvolutionKernel`         | 6-phase cycle: Observe → Measure → Mutate → Evaluate → Select → Commit\u002FRollback              |\n| **Cambrian explosion**    | `CambrianExplosionEngine` | Mass diversification — thousands of mutations, intense selection keeps only the fittest 0.1% |\n| **Immune system**         | `EvolutionImmuneSystem`   | 8 inviolable rules, antibody generation, SixPointGuard, constitutional firewall              |\n| **Telomeres & apoptosis** | `ApoptosisEngine`         | Usage extends lifespan; neglect triggers archival to digital permafrost                      |\n\n#### 🦠 Internal Ecosystem — micro-agents & collaboration\n\n| Biology         | System                 | What it does                                                                                          |\n| :-------------- | :--------------------- | :---------------------------------------------------------------------------------------------------- |\n| **Microbiome**  | `MicrobiomeRegistry`   | 5 micro-agent species: Prompt Bacteria, Token Fungi, Latency Virus, Cache Archaea, Log Decomposer     |\n| **Symbiosis**   | `AutoSymbiosisEngine`  | Multi-model collaborative debugging with shared diagnosis                                             |\n| **Autopoiesis** | `CognitiveAutopoiesis` | Self-creating system — components produce new components in a closed loop, fitness-gated reproduction |\n\n#### 🌊 Population Dynamics — cross-instance & diversity\n\n| Biology                       | System                              | What it does                                                                             |\n| :---------------------------- | :---------------------------------- | :--------------------------------------------------------------------------------------- |\n| **Pangenesis**                | `PangenomePool` + `GemmuleProtocol` | Cross-instance genome exchange via signed fragments with fitness and TTL                 |\n| **Co-evolutionary arms race** | `AdversarialEvolution`              | Red attacks, Blue defends, both evolve under mutual pressure — neither has fixed fitness |\n| **Coral reef**                | `CoralSearchEngine`                 | Multi-agent asynchronous search with shared persistent memory                            |\n| **Niche ecology**             | `EcologicalNicheSystem`             | Population-level specialization and niche construction                                   |\n\nThis is a structurally consistent, mathematically grounded system — not decorative naming. CMA-ES drives continuous parameter evolution, Thompson Sampling selects gene-level strategies, MAP-Elites maintains quality diversity archives, and Bayesian prediction estimates clade potential. The organism senses its own weaknesses, mutates in controlled ways, retains lineage and regret memory, and subjects every change to governance — like biology, but with rollback.\n\n## Governed Autonomy Modes\n\n- `OFF` — no autonomous dream evolution.\n- `SAFE_LOCAL` — default when local safety prerequisites exist: synthetic validation, budget caps, and rollback.\n- `FULL_GOVERNED` — explicit higher-autonomy mode for fully governed operation; not enabled implicitly.\n\nPolyGenesis is a governed self-evolving digital organism, not an unconstrained lifeform: autonomy is bounded by validation, rollback, budgets, and review governance.\n\n---\n\nPolyHelper focuses on applied domains: consensus orchestration, automotive safety, accessibility, medical AI, legal AI, cognitive exoskeleton, governed AI delegates, and AI governance. The integration of all of them into one system is the bonus, not the thesis.\n\n---\n\n## Product capabilities\n\n1. **Chairman + Multi-AI Synthesis** — 191 consensus methods, convergent + divergent modes, 19 life domains. [→](docs\u002FCONSENSUS-ENGINE.md)\n2. **Accessibility Stack** — 1.52M LOC, WCAG 2.2 AAA, sign language avatars, SirenSense. [→](docs\u002FACCESSIBILITY-GUIDE.md)\n3. **Automotive AI** — 556K LOC, voice-first driving, fleet mission policy, simulation-before-commit. [→](docs\u002Fdrivers\u002Findex.md)\n4. **Native Mobile** — 1,283 screens, offline-first, voice assistant, driving mode, biometric auth. [→](docs\u002Fmobile\u002FARCHITECTURE.md)\n5. **Governed Digital Workforce** — 50+ domain delegates, shadow training, 8 safety layers, offline, legal accountability. [→](docs\u002Forchestration\u002Fsoloplex-digital-crew-overview.md)\n6. **Deep Deliberation** — auto escalation solo → full, Lens-aware routing, budget-aware reasoning. [→](docs\u002Fdeliberation\u002FDELIBERATION.md)\n7. **Vibe Coding \u002F Creative Factory** — NL → product (UI + backend + DB + docs) across 83+ types. [→](docs\u002Fcreative\u002FCREATIVE.md)\n8. **Code Security** — multi-model consensus scanning, SBOM, SARIF, mandatory HITL, CI\u002FCD. [→](docs\u002Fsecurity\u002FCODE-SECURITY.md)\n9. **Selection Intelligence** — 10 task profiles, shadow evaluation, learning loop, A\u002FB rollout. [→](docs\u002FSELECTION-INTELLIGENCE-INTEGRATION.md)\n10. **AI Fluency (Trust Layer)** — speed bumps, confidence maps, artifact receipts, fluency scoring. [→](docs\u002Fai-core\u002FAI-FLUENCY.md)\n11. **Immutable Governance** — configurable 7-layer tamper-evident audit: L1 SHA-256 hash chain → checkpoint seals → HMAC signing → Postgres append-only → RFC 3161 TSA timestamps → OpenTimestamps Bitcoin-backed proofs → S3 Object Lock WORM. **AI Passport** — interoperable model provenance ledger (\"who did what, when, and with what\") with cross-organization verification. Evidence chain linking: execution → policy → consensus → shadow → outcome. [→](docs\u002FTRUSTED-EXECUTION-GUIDE.md)\n12. **Human Intelligence** — risk-driven expert review, 5 lanes, RL-based matching, red teaming. [→](docs\u002Fai-core\u002FHUMAN_INTELLIGENCE.md)\n13. **Agent Governance** — registry, DID identity, security graph, kill-switch, verified marketplace. [→](docs\u002Farchitecture\u002Fagent-governance-plane.md)\n14. **Cognitive-Adaptive UI** — dashboard tiles auto-simplify at high cognitive load. No market equivalent. [→](docs\u002Fcognitive-exoskeleton\u002Fcore\u002FDASHBOARD-TILES.md)\n15. **AI Hospital Platform** — 399K LOC, 87 modules, 37 specialty templates, 40 domains, 11 jurisdictions, FHIR\u002FHL7\u002FDICOM. [→](packages\u002Fplatform-medical\u002FAI-HOSPITAL.md)\n16. **PolySkill Plane** — 39 slash commands, 11-phase sprint lifecycle, ML security pipeline. [→](docs\u002Fskill-plane\u002FREADME.md)\n17. **Token Economics** — hard budget control, ROI analysis, safety-preserving downgrades. [→](docs\u002Fpayments\u002FTOKEN-ECONOMICS.md)\n18. **Workflow Engine** — self-healing execution: convergence loops (3-5 retries with feedback), adversarial red-team verification, 200+ parallel agents with backpressure, crash recovery (durable persistence), adaptive budget (graceful downgrade, not hard stop), dynamic re-planning, auto disagreement resolution. [→](docs\u002Forchestration\u002FREADME.md)\n19. **DevLoop AI Engineering** — one sentence in → structured issue → work plan → agent writes code → self-corrects on failure → code review → complete PR. 42 I\u002FO-free modules, 71 API endpoints. [→](docs\u002Forchestration\u002FREADME.md#devloop-ai-engineering-pipeline)\n20. **PolyGenesis Self-Evolution** — genome-based self-improvement with controlled mutation, executable validation, rollback, lineage\u002Fregret memory, Meta-Cognition, Meta-Awareness, Review Council governance, and daily review cadence. [Start here →](docs\u002Fpolygenesis\u002FOVERVIEW.md) · [→](docs\u002Fpolygenesis\u002FREADME.md) · [White Paper →](docs\u002Fpolygenesis\u002FWHITE-PAPER.md) · [Review Council →](docs\u002Fpolygenesis\u002FREVIEW-COUNCIL.md)\n21. **Verdict AI Orchestration** — protecting people (medical\u002Flegal\u002Fdisability) and businesses (finance\u002Fcompliance) via 10+ model consensus, reproducibility fingerprints, CriticAgent veto, Professional Packs (Legal, Finance, HR, Sales, Research), PII redaction, air-gapped local execution. **Trusted Execution Spine**: shadow execution (dry-run before commit), temporal consensus (multi-round drift detection with policy gates). 5 SKU tiers (Core → Enterprise Plus). **Axiom Governance**: legal-domain intelligence layer with 4 risk profiles, 19 governance modules, ethical walls, forensic evidence packs, and cross-border diligence workflows. [→](docs\u002Fverdict\u002FREADME.md) · [Axiom →](docs\u002Flegal\u002FAXIOM-GOVERNANCE.md)\n22. **Autopilot Fleet Execution** — 4 Power Levels: **Solo** (1 model, $0.01–$0.30) → **Duo** (3 models + Chairman, $0.10–$1.50) → **Squad** (6 models + review, $0.50–$8.00) → **Full\u002FAutopilot** (12+ models + deliberation, $2–$50+). FleetCommander mission orchestration: decompose goal → cost preflight → parallel dispatch via git worktree isolation → health monitoring → result merging → Chairman review → lessons extraction. 4-tier cost-aware routing (Free → Budget → Standard → Premium). LESSONS.md orchestrator-wide learning with Jaccard deduplication.\n23. **Sovereign AI Mesh Control Plane** — productized national\u002Fcritical-infrastructure orchestration with 3 profiles: National Critical Infrastructure, Regulated Public Sector, Regional Resilience Mesh. Jurisdiction-bound routing, domestic-only failover, and plan\u002Fvalidate flows. [→](docs\u002Forchestration\u002F11-sovereign.md)\n24. **Privacy-Grade Autonomy** — GUI autonomy with Safe Zones: mark screen regions as no-see\u002Fno-act, and AI respects the boundary. Policy-grade guardrails ensure the agent cannot bypass privacy zones even during autonomous workflows. [→](docs\u002Fgui-agent\u002FGUI-AGENT.md)\n25. **Bento Dashboard** — 69-tile modular grid with glassmorphic design, 3 density presets (Compact\u002FStandard\u002FAdvanced), drag-and-drop reordering, 8 voice commands, mobile swipe carousel — all WCAG 2.2 AAA. The primary UI surface rendering consensus results, provider health, adaptive context, and 10 domain sections in one responsive view. [→](docs\u002Farchitecture\u002Fui\u002FBENTO-SYSTEM.md)\n\n## ![PolyHelper across devices](docs\u002Fassets\u002Fhero-legal.jpg)\n\n## Architecture\n\nNx-managed ESM workspace, five layers. Boundaries enforced by `dependency-cruiser`.\n\n`apps\u002F*` → `libs\u002F*` → `packages\u002Fserver-*` → `packages\u002Fplatform-*` → `packages\u002Fcore-*` → `packages\u002Fcore-os\u002F*`\n\n| Layer       | Lines  | Purpose                                                               |\n| ----------- | ------ | --------------------------------------------------------------------- |\n| `sdk\u002F`      | ~1.11M | 8 native SDKs (Go, Java, Kotlin, Python, Rust, Swift, C#, TypeScript) |\n| `packages\u002F` | ~5.76M | Backend engines, platform, server, core-os, packs                     |\n| `libs\u002F`     | ~1.90M | Shared libraries — TypeScript + Svelte                                |\n| `apps\u002F`     | ~503K  | Web + mobile + extension + electron clients                           |\n\n**Strategic directions (cross-cutting):**\n\n| Direction      | Lines  | Scope                                                                                                                                                                |\n| -------------- | ------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| Orchestration  | ~1.62M | Multi-model consensus, chairman synthesis, swarm\u002Ffleet, debate, divergent\u002Fconvergent modes, delegates                                                                |\n| Exoskeleton    | ~643K  | Cognitive pipeline (state-engine, consciousness bus, scaffolding, affective), physical hardware (BCI, gait, EMG, digital twin), shared control, biomechanical safety |\n| Self-Evolution | ~320K  | PolyGenesis, genome, mutation, fitness, meta-cognition, dream mode, lineage, regret memory                                                                           |\n\n**9.41M lines of source code** across 10 programming languages. **208,483 tests** · **8,425 test files**.\n\n**API + SDKs:** OpenAPI specs, SDKs for 8 languages (1.11M LOC, 65 services, 800+ methods each). [SDK Docs →](docs-mintlify\u002Fsdks\u002Foverview.mdx)\n\n**MCP:** OAuth 2.1, REST + JSON-RPC\u002FSSE, managed tool execution. [MCP Docs →](docs\u002Fintegrations\u002Fmcp\u002Findex.md)\n\n**PolyGenesis:** governed self-evolution in V4 monitors orchestration fitness, mutates safely, validates changes on executable contours, retains lineage and regret memory, and subjects longer-horizon changes to periodic review governance. It operates as a governed self-evolving digital organism inside the runtime rather than as a standalone coding-agent add-on. [Start here →](docs\u002Fpolygenesis\u002FOVERVIEW.md) · [PolyGenesis Docs →](docs\u002Fpolygenesis\u002FREADME.md) · [White Paper →](docs\u002Fpolygenesis\u002FWHITE-PAPER.md) · [Review Council →](docs\u002Fpolygenesis\u002FREVIEW-COUNCIL.md)\n\n> **Example:** Medical hallucination rate rises to 34% → PolyGenesis detects the deficit → generates a routing mutation (round-robin → quality-first) → validates through SixPointGuard → hallucination rate drops to 11%. Genome v42 → v43. If the mutation had failed, it would be rolled back, an antibody generated, and the mistake recorded in regret memory — never repeated. [Full walkthrough →](docs\u002Fpolygenesis\u002FOVERVIEW.md#end-to-end-example-medical-routing-v42-to-v43)\n\nThis makes V4 more than a self-improving coding agent: it is a governed self-evolving orchestration system that operates across real product surfaces and regulated, safety-critical domains.\n\n[Full Architecture →](docs\u002Farchitecture\u002F) · [Testing Guide →](docs\u002Ftesting\u002FREADME.md) · [Deployment →](docs\u002Fdevelopment\u002Fworkflow\u002Fdeployment.md)\n\n---\n\n## Core OS + Domain Packs\n\n**Core OS** provides AI orchestration, governance, and the cognitive exoskeleton loop. **Domain Packs** add specialized modules:\n\n| 🎯 AI Orchestration (Core OS)                | ♿ Accessibility-First (Pack)                      | 🚗 Driver Safety (Pack)                   | 🔒 Code Security (Pack)                 |\n| -------------------------------------------- | -------------------------------------------------- | ----------------------------------------- | --------------------------------------- |\n| Frontier AI, 191 canonical methods           | WCAG 2.2 AAA                                       | Voice-first, distraction gating           | Code security pipeline + HITL approvals |\n| Chairman + Polly synthesis                   | 1.52M LOC (cross-cutting)                          | 556K LOC (cross-cutting)                  | Audit trails + DPA gate                 |\n| Deep deliberation (AUTO 4→10)                | Haptics\u002FBraille output                             | 10+ dashboard tiles, SirenSense           | CI\u002FCD SARIF + policy gates              |\n| [Consensus Engine](docs\u002FCONSENSUS-ENGINE.md) | [Accessibility Guide](docs\u002FACCESSIBILITY-GUIDE.md) | [Driver Solutions](docs\u002Fdrivers\u002Findex.md) | [Security Hub](docs\u002FSECURITY.md)        |\n\n**Domain & Enterprise:**\n\n| Domain                | Capability                                                             | Guide                                                   |\n| --------------------- | ---------------------------------------------------------------------- | ------------------------------------------------------- |\n| **RAG & Documents**   | Layout-aware ingestion, citation validation, cross-encoder reranking   | [Smart RAG](docs\u002Fsearch\u002FRAG-INGESTION.md)               |\n| **Finance**           | Portfolio tracking, news sentiment, budget management, fraud detection | [Finance Agent](docs\u002Ffinance\u002FFINANCE.md)                |\n| **Creative Factory**  | 83+ product types, Divergent Consensus, voice wizard                   | [Creative Agent](docs\u002Fcreative\u002FCREATIVE.md)             |\n| **Engineering CAD**   | NL → OpenSCAD → STL\u002FSVG, Design Twin Loop with PPE                     | [Engineering CAD](docs\u002Fcreative\u002FENGINEERING-CAD.md)     |\n| **Learning**          | Spaced repetition, adaptive testing, AI tutoring, streaks              | [Learning Agent](docs\u002Fpoly-assistant\u002FLEARNING.md)       |\n| **Enterprise Admin**  | Agent Control Plane, Tool Gateway, Connectors, Audit Chain             | [Enterprise Admin](docs\u002Fenterprise\u002FENTERPRISE-ADMIN.md) |\n| **Trusted Execution** | Shadow exec, evidence chain, enterprise packages, \u002Fops admin           | [Trusted Execution](docs\u002FTRUSTED-EXECUTION-GUIDE.md)    |\n\n**Orchestration Modes (Core OS):**\n\n- **Lens (West\u002FEast)** — bloc-aware comparisons + agreement\u002Fdisagreement map + side-by-side. [Lens Council →](docs\u002Flens-council\u002FREADME.md)\n- **Deep (5×5 \u002F 10)** — higher-reliability orchestration (more diversity, stronger cross-checking).\n- **Compact (3)** — fast fallback for speed\u002Fcost (3 models + chair).\n\n---\n\n## Security\n\nGovernance-by-default: the system will not execute a request without passing the full policy chain (Cedar + OPA pre\u002Fin\u002Fpost-execution gates). The developer cannot skip governance — it is embedded in the runtime.\n\nPost-quantum crypto. 7-layer immutable audit. Automated compliance evidence packs. Mandatory human approval checkpoints.\n\n**Consensus engines:** Debate engine + Chairman loop + hybrid routing + prompt evolution.\n\n[Security Hub →](docs\u002FSECURITY.md) · [Trusted Execution →](docs\u002FTRUSTED-EXECUTION-GUIDE.md)\n\n---\n\n## Who uses this\n\n| Audience                             | Why it fits                                                                             |\n| ------------------------------------ | --------------------------------------------------------------------------------------- |\n| **Everyday Users**                   | Voice-first AI with multi-model consensus. BYOS — $0 extra cost.                        |\n| **People with Disabilities**         | WCAG-first UX, 60+ accessibility modules, multimodal assistive outputs.                 |\n| **Drivers**                          | Hands-free AI with safety protocols, SirenSense, CarPlay\u002FAndroid Auto.                  |\n| **Solo Founders & Teams**            | Governed digital workforce — 50+ domain delegates at a fraction of team cost.           |\n| **Government, Defense & Compliance** | Sovereign, air-gapped AI with automated compliance evidence. 12+ regulatory frameworks. |\n| **Developers & Labs**                | Multi-model experimentation, consensus benchmarks, reproducible runs.                   |\n\n---\n\n## Benchmarks & Testing\n\n**208,483 tests · 8,425 files · dual framework (Jest + Vitest) · Playwright E2E**\n\n- [Benchmark Protocol](docs\u002Fbenchmarks\u002Fbenchmark-protocol.md) · [Performance](docs\u002Fbenchmarks\u002FPERFORMANCE-BENCHMARKS.md) · [Security Benchmark](docs\u002Fbenchmarks\u002Fsecurity-benchmark.md)\n- [Testing Guide](docs\u002Ftesting\u002FREADME.md) · [UAT Process](docs\u002Ftesting\u002FUAT-PROCESS.md)\n\n**SDKs:** Python, JavaScript\u002FTypeScript, Java, C#\u002F.NET, Go, Swift, Rust, Kotlin — 1.11M LOC, 65 services, 800+ methods each. [SDK Docs →](docs-mintlify\u002Fsdks\u002Foverview.mdx)\n\n**Deployment:** [Docker](tools\u002FREADME.md) · [Kubernetes](deploy\u002Fk8s\u002FREADME.md) · [Helm](deploy\u002Fhelm\u002FREADME.md) · [Full Guide](docs\u002Fdevelopment\u002Fworkflow\u002Fdeployment.md)\n\n---\n\n\u003Cdiv align=\"center\">\n\n**Frontier AI Models:** Claude · GPT · Gemini · Grok · DeepSeek · Qwen · Mistral · Kimi · Ernie · GLM · Meta AI\nCompatible with 1000+ endpoints. [Model Catalog →](docs\u002Fai-core\u002FMODEL-CATALOG.md)\n\n|     🏭     |     🤖     |     🧠     |     🧪      |      ♿      |        🔒        |      🌍       |\n| :--------: | :--------: | :--------: | :---------: | :----------: | :--------------: | :-----------: |\n| **58,453** | **10+ AI** |  **191**   | **208,483** | **AA \u002F AAA** | **Post-Quantum** | **250+ i18n** |\n| Code Files | Providers  | Algorithms |    Tests    |     WCAG     |     Security     |   Languages   |\n\n**[Full Documentation →](docs\u002F)** · **[Contributing](CONTRIBUTING.md)** · **[Licensing](LICENSING.md)**\n\n**Responsible Use:** PolyHelper is designed for beneficial applications. We prohibit use for generating harmful content, spreading misinformation, or violating privacy. [RESPONSIBLE-USE.md](docs\u002FRESPONSIBLE-USE.md)\n\n![PolyHelper V4](.\u002Fdocs\u002Fassets\u002Flogo-animated.gif)\n\n\u003C\u002Fdiv>\n\n---\n\n## What You Get for Free\n\nPolyHelper is an **open-core** project. Most of the platform is free and open source.\n\n**Open Source (Apache 2.0) — 7.75M lines of code, free for any use, including commercial:**\n\n- **Accessibility platform** — 1.52M lines of code, WCAG 2.2 AAA, sign language avatars, haptic feedback, braille output, 60+ modules\n- **8 Native SDKs** — Go, Java, Kotlin, Python, Rust, Swift, C#, TypeScript (1.11M LOC, 65 services, 800+ methods each)\n- **MCP integration** — OAuth 2.1, REST + JSON-RPC\u002FSSE, managed tool execution\n- **Internationalization** — 250+ languages, RTL support, cultural formatting\n- **Desktop application** — Electron for macOS, Linux, Windows\n- **Mobile application** — React Native for iOS and Android, offline-first, 1,283 screens\n- **Bento Dashboard** — 69 tiles, glassmorphic design, drag-and-drop, voice commands, WCAG AAA\n- **PolySkill command framework** — extensible skill system\n- **FHIR \u002F HL7 \u002F DICOM interoperability layer** — healthcare data standards\n- **Post-quantum cryptography** — lattice-based primitives, hybrid key exchange\n- **Basic consensus runner and workflow executor**\n- **Basic memory layer and audit logging**\n- **Basic RAG pipeline**\n- **Demo applications and examples**\n- **Full public documentation**, architecture guides, and contributor docs\n\n**Source-Available (BSL 1.1) — 1.11M lines of code, free for non-commercial, educational, and research use:**\n\n- Full orchestration engine (191 consensus methods, Chairman synthesis)\n- Selection Intelligence, FleetCommander, Deep Deliberation\n- Workflow Engine, Evolving Memory, AI Fluency and Trust Layer\n- Human Intelligence Layer, 7-Layer Immutable Audit Trail\n- Lens Council, Coral Search Engine\n- Code Security Pipeline, Enterprise Admin, Token Economics\n\nConverts to Apache 2.0 on June 13, 2033. See [LICENSING.md](LICENSING.md) for full details.\n\n## Academic and Research Access\n\nWe provide **free access** to advanced modules for universities, research labs, and non-profit organizations.\n\n- Orchestration engine internals and consensus algorithms\n- Self-evolution (PolyGenesis) architecture\n- Safety governance frameworks\n- Any module needed for your research\n\nNo complex legal process — just a simple research agreement. Cite PolyHelper in your publications.\n\n**[Research Access →](RESEARCH-ACCESS.md)** · **Contact: info@polyhelper.ai**\n\n---\n\n## Standalone Tools — Roadmap\n\nSelf-contained CLI tools from the PolyHelper platform. Each works independently — no monorepo required. License varies by tool; see each package.\n\nStatus: **Planned** = in development, **Available** = published on npm (`npx @polyhelper\u002Fpoly-\u003Cname>`).\n\n### Security\n\n| Tool                | What it does                                                          |   AI?    | Status  |\n| ------------------- | --------------------------------------------------------------------- | :------: | :-----: |\n| `poly-pqc-migrate`  | Scan & fix post-quantum crypto vulnerabilities — NIST deadline passed |    No    | Planned |\n| `poly-supply-chain` | Detect malicious npm packages before they hit production              | Optional | Planned |\n| `poly-secure`       | Multi-AI consensus code security scanner (OWASP Top 10)               |   BYOK   | Planned |\n| `poly-secret-scan`  | Find leaked API keys and secrets in code & git history                |    No    | Planned |\n| `poly-sbom`         | Generate software bill of materials (CycloneDX\u002FSPDX)                  |    No    | Planned |\n\n### AI & Orchestration\n\n| Tool                 | What it does                                                     |   AI?    | Status  |\n| -------------------- | ---------------------------------------------------------------- | :------: | :-----: |\n| `poly-consensus`     | Query 2-10 AI models, get one synthesized answer with confidence |   BYOK   | Planned |\n| `poly-rag`           | RAG pipeline builder — ingest, chunk, embed, query in one CLI    |   BYOK   | Planned |\n| `poly-hallucination` | Detect AI hallucinations with cross-reference verification       | Optional | Planned |\n| `poly-compare`       | Side-by-side AI model comparison with scoring                    |   BYOK   | Planned |\n| `poly-prompt-test`   | A\u002FB test prompts across models with statistical analysis         |   BYOK   | Planned |\n| `poly-cost`          | Token counter & cost calculator for any AI provider              |    No    | Planned |\n| `poly-cite`          | AI-powered citation & source verification                        |   BYOK   | Planned |\n| `poly-context`       | Measure and optimize context window usage                        |    No    | Planned |\n| `poly-pdf-qa`        | Chat with PDFs — extract, chunk, and query documents             |   BYOK   | Planned |\n\n### Accessibility\n\n| Tool                  | What it does                                            |   AI?    | Status  |\n| --------------------- | ------------------------------------------------------- | :------: | :-----: |\n| `poly-braille`        | Convert text to Grade 2 Braille (UEB\u002Finternational)     |    No    | Planned |\n| `poly-a11y`           | WCAG 2.2 accessibility checker with AI-powered fixes    | Optional | Planned |\n| `poly-dyslexia`       | Dyslexia-friendly text transformer & readability scorer |    No    | Planned |\n| `poly-alt-text`       | AI-generated alt text for images (WCAG compliant)       |   BYOK   | Planned |\n| `poly-sign`           | Convert text to sign language animation (ASL\u002FBSL\u002FDGS)   |   BYOK   | Planned |\n| `poly-photosensitive` | Detect seizure-triggering content in video\u002Fanimation    |    No    | Planned |\n| `poly-captions`       | Live speech-to-text captioning                          |   BYOK   | Planned |\n| `poly-cognitive`      | Score UI cognitive load and suggest simplifications     |   BYOK   | Planned |\n\n### Developer Tools\n\n| Tool                | What it does                                                   | AI?  | Status  |\n| ------------------- | -------------------------------------------------------------- | :--: | :-----: |\n| `poly-i18n`         | AI-powered internationalization — extract, translate, validate | BYOK | Planned |\n| `poly-readme`       | Generate professional README from source code analysis         | BYOK | Planned |\n| `poly-commit`       | AI-generated conventional commit messages from diffs           | BYOK | Planned |\n| `poly-review`       | Multi-model AI code review                                     | BYOK | Planned |\n| `poly-test-gen`     | Generate comprehensive test files from source code             | BYOK | Planned |\n| `poly-env-diff`     | Compare environment configs across dev\u002Fstaging\u002Fprod            |  No  | Planned |\n| `poly-api-doc`      | Auto-generate OpenAPI docs from source code                    | BYOK | Planned |\n| `poly-cloud-cost`   | Monitor & alert on cloud spending (AWS\u002FGCP\u002FAzure)              |  No  | Planned |\n| `poly-format-check` | Validate cultural format correctness (dates, currency, phone)  |  No  | Planned |\n| `poly-rtl`          | Convert CSS\u002FUI to RTL layout                                   |  No  | Planned |\n\n### Healthcare & Education\n\n| Tool                   | What it does                                            | AI?  | Status  |\n| ---------------------- | ------------------------------------------------------- | :--: | :-----: |\n| `poly-medical-explain` | Plain-language medical information explainer            | BYOK | Planned |\n| `poly-fhir`            | JavaScript FHIR toolkit for healthcare data             |  No  | Planned |\n| `poly-learn`           | AI tutoring — learn concepts instead of getting answers | BYOK | Planned |\n\n**AI?** — **No**: works offline, free. **BYOK**: bring your own API key. **Optional**: basic features free, AI enhances.\n\n---\n\n> **Like this project?** ⭐ [**Star the repo →**](https:\u002F\u002Fgithub.com\u002FPolyHelper\u002Fpolyhelper) and 🔔 [**Watch for updates**](https:\u002F\u002Fgithub.com\u002FPolyHelper\u002Fpolyhelper\u002Fsubscription). Thank you!\n>\n> 35 standalone CLI tools. 191 consensus methods. 10+ frontier AI models. One open platform.\n\n---\n","2026-06-15 02:30:07","CREATED_QUERY"]