{"id":51280142,"url":"https://github.com/ruvnet/helix","last_synced_at":"2026-07-02T03:00:39.663Z","repository":{"id":367449728,"uuid":"1280870466","full_name":"ruvnet/helix","owner":"ruvnet","description":"Helix — a private, local-first, anti-hallucination Personal Health Intelligence platform on the ruvnet stack (Ruflo + RuVector + Cognitum Seed + MetaHarness/Darwin).","archived":false,"fork":false,"pushed_at":"2026-06-26T21:08:21.000Z","size":3204,"stargazers_count":21,"open_issues_count":0,"forks_count":3,"subscribers_count":2,"default_branch":"main","last_synced_at":"2026-07-01T02:21:28.059Z","etag":null,"topics":["adr","anti-hallucination","graphrag","health-intelligence","local-first","personal-health","privacy","rust","ruvnet","wasm"],"latest_commit_sha":null,"homepage":"https://ruvnet.github.io/helix/","language":"Rust","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ruvnet.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-06-26T02:40:13.000Z","updated_at":"2026-06-30T13:58:00.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/ruvnet/helix","commit_stats":null,"previous_names":["ruvnet/helix"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ruvnet/helix","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ruvnet%2Fhelix","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ruvnet%2Fhelix/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ruvnet%2Fhelix/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ruvnet%2Fhelix/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ruvnet","download_url":"https://codeload.github.com/ruvnet/helix/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ruvnet%2Fhelix/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":35030921,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-07-02T02:00:06.368Z","response_time":173,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["adr","anti-hallucination","graphrag","health-intelligence","local-first","personal-health","privacy","rust","ruvnet","wasm"],"created_at":"2026-06-30T01:02:50.796Z","updated_at":"2026-07-02T03:00:39.621Z","avatar_url":"https://github.com/ruvnet.png","language":"Rust","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Helix — Personal Health Intelligence (PHI)\n\n\u003e Your entire body — every record, signal, and result — assembled into one living dossier.\n\u003e **Private. Continual. Visual. And built so it can't make things up.**\n\n[![Helix management console](docs/ui/screenshots/dashboard.png)](https://ruvnet.github.io/helix/ui/)\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://ruvnet.github.io/helix/ui/#ask\"\u003e\u003cimg src=\"docs/ui/screenshots/answer.png\" alt=\"Grounded, cited answer — open the live demo\" width=\"49%\" /\u003e\u003c/a\u003e\n  \u003ca href=\"https://ruvnet.github.io/helix/mobile/\"\u003e\u003cimg src=\"docs/ui/screenshots/mobile.png\" alt=\"Helix mobile PWA — open the live demo\" width=\"22%\" /\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\u003csub\u003e↑ the screenshots are clickable — they open the \u003ca href=\"https://ruvnet.github.io/helix/\"\u003elive demo\u003c/a\u003e (real Rust pipeline in WebAssembly)\u003c/sub\u003e\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\u003cb\u003e\u003ca href=\"https://ruvnet.github.io/helix/\"\u003e▶ Live demo\u003c/a\u003e\u003c/b\u003e · the UI runs the real Rust pipeline compiled to WebAssembly\u003c/p\u003e\n\n\nHelix is a mobile-first *\"functional-medicine specialist in your pocket.\"* It ingests\neverything a person can know about their own body — EMR records, pharmacy history, phone\nand wearable telemetry, genome, lab panels, sleep, recovery, nutrition, subjective logs,\nand **always-on ambient sensing** — normalizes it into a single longitudinal **personal\nhealth knowledge graph**, and puts a conversational, multi-agent analyst on top of it.\n\nThe differentiator is not \"another health chatbot.\" **Every answer is grounded in the\nuser's own data, traceable to its source, graded for evidence quality, and bounded by an\nexplicit refuse-when-unknown policy.**\n\nBuilt on the **ruvnet stack**:\n\n- **RuVector** — self-learning vector + GraphRAG memory DB (the substrate of *context*).\n- **Ruflo** — multi-agent meta-harness with PII-gating, learning loops, and audit trails\n  (the substrate of *reasoning*).\n- **Cognitum Seed** — always-on, contactless mmWave edge sensing (the *continuous signal*).\n- **MetaHarness / Darwin Mode** — the whole stack is minted as a branded harness that\n  self-optimizes toward *faithfulness* while the underlying model stays frozen.\n\n## Repository layout\n\n```\nhelix/\n├── README.md                          ← this file\n└── docs/\n    ├── Helix-PHI-ADR-Product-Spec.md  ← the full product spec (v1.0.0, with diagrams)\n    └── adr/\n        ├── README.md                  ← ADR index\n        └── ADR-001 … ADR-019          ← 19 detailed Architecture Decision Records\n```\n\n## Start here\n\n1. **[The product spec](docs/Helix-PHI-ADR-Product-Spec.md)** — vision, capability wish\n   list, reference architecture, anti-hallucination design, roadmap, and the\n   differentiation vs. ChatGPT Health.\n2. **[The ADR index](docs/adr/README.md)** — the 19 load-bearing architecture decisions,\n   each researched and evidence-graded.\n\nThe three decisions that make or break a product in this space:\n**anti-hallucination / data-grounding** ([ADR-005](docs/adr/ADR-005-retrieval-grounded-provenance-answering.md)–[008](docs/adr/ADR-008-verifier-critic-swarm-consensus.md)),\n**privacy \u0026 data ownership** ([ADR-001](docs/adr/ADR-001-user-owned-local-first-vault.md), [011](docs/adr/ADR-011-federation-pii-stripped-cohort.md), [013](docs/adr/ADR-013-on-device-inference.md)),\nand **clinical safety** ([ADR-009](docs/adr/ADR-009-red-flag-escalation-clinician-in-loop.md), [010](docs/adr/ADR-010-wellness-vs-samd-boundary.md)).\n\n## What's built\n\nThis is no longer just a spec — the testable core is implemented in Rust and validated.\n\n- **22 crates · 153 tests · 30 ADRs** · clippy/fmt clean · `cargo audit` clean.\n- **Anti-hallucination core**: provenance grounding (`helix-provenance`), deterministic\n  numerics (`helix-numeric`), evidence tiering (`helix-evidence`), red-flag escalation\n  (`helix-escalation`), verifier (`helix-verifier`), the grounded-answer pipeline\n  (`helix-pipeline`), and a real AEAD vault (`helix-vault`).\n- **On-device AI on the local GPU** (Rust, never Python): the LLM analyst narrates grounded\n  facts via **ruvLLM** with a number-guard (`helix-llm`), real **MiniLM** text embeddings\n  (`helix-embed`), and a **layout-only** visual encoder (`helix-vision`) — each GPU-validated.\n- **ruvnet-ecosystem integrations**: WiFi-CSI sensing (`helix-sensing`/RuView), genome +\n  pharmacogenomics (`helix-genome`/rvDNA), OCR ingestion (`helix-ocr`), semantic retrieval\n  (`helix-retrieval`), visual RAG (`helix-visual`/rupixel), privacy-preserving cohort\n  (`helix-cohort`), FHIR connectors (`helix-connect`), and federation transport (`helix-fed`).\n- **Web console + WASM mobile app** running the real pipeline in-browser — **[live demo](https://ruvnet.github.io/helix/)**.\n\nEvery integration keeps the discipline: the LLM narrates (never reasons), embeddings/visual\nare recall (not grounding), genomics/cohort data is privacy-gated, and nothing diagnoses.\n\n## Status\n\n**v0.1.0 — implemented core, Proposed ADRs.** The Rust core is built, tested, and\nGUI/GPU-validated. The ADRs are grounded by multi-source research but have not been\nratified by regulatory counsel or a clinical advisory board. Genuinely out of scope for\nthis workspace (and flagged in [`docs/COVERAGE.md`](docs/COVERAGE.md)): live partner-API\nauth, the federation aggregator network, physical sensing hardware, the 3D WebGL twin, and\nclinical/regulatory sign-off.\n\n---\n\n*Prepared by ISO Vision LLC. This repository provides architectural and product guidance,\n**not** legal, regulatory, or medical advice. Engage regulatory counsel and clinical\ngovernance before building any diagnostic or treatment-recommending features.*\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fruvnet%2Fhelix","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fruvnet%2Fhelix","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fruvnet%2Fhelix/lists"}