l0ng-ai
Featured
tty7
tty7 is a fast, GPU-accelerated terminal workbench with persistent sessions, built-in input tools, SSH support, and coding agent awareness.
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It differentiates by grounding every answer in the user's own data with explicit evidence grading and a refuse-when-unknown policy, built on a Rust/WebAssembly core with real anti-hallucination mechanisms.
Who it is for
- Individuals who want to centralize and analyze their own health records and wearable data
- Developers building privacy-focused health analytics or personal knowledge graph applications
- Researchers or clinicians exploring trustworthy AI for personal health data
Use cases
- Aggregating and querying personal health records, lab results, and wearable telemetry in one place
- Getting cited, evidence-graded answers about one's own health history without hallucination
- Monitoring medication interactions or pharmacogenomic insights from genomic data
Strengths
- Anti-hallucination design with provenance grounding, verifier consensus, and red-flag escalation
- Fully implemented Rust core with 22 crates, 153 tests, and a live WebAssembly demo
- Privacy-preserving architecture: local-first vault, on-device inference, PII-gated federation
- Extensive architecture decisions (30 ADRs) covering clinical safety, data ownership, and evidence tiering
Considerations
- Not yet reviewed by regulatory counsel or a clinical advisory board
- Live partner API authentication and physical sensing hardware are out of scope for the current workspace
- Explicitly not medical advice; requires regulatory and clinical governance before diagnostic use
README quick start
Helix — Personal Health Intelligence (PHI)
Your entire body — every record, signal, and result — assembled into one living dossier. Private. Continual. Visual. And built so it can't make things up.
↑ the screenshots are clickable — they open the live demo (real Rust pipeline in WebAssembly)
▶ Live demo · the UI runs the real Rust pipeline compiled to WebAssembly
Helix is a mobile-first "functional-medicine specialist in your pocket." It ingests everything a person can know about their own body — EMR records, pharmacy history, phone and wearable telemetry, genome, lab panels, sleep, recovery, nutrition, subjective logs, and always-on ambient sensing — normalizes it into a single longitudinal personal health knowledge graph, and puts a conversational, multi-agent analyst on top of it.
The differentiator is not "another health chatbot." Every answer is grounded in the user's own data, traceable to its source, graded for evidence quality, and bounded by an explicit refuse-when-unknown policy.
Built on the ruvnet stack:
- RuVector — self-learning vector + GraphRAG memory DB (the substrate of context).
- Ruflo — multi-agent meta-harness with PII-gating, learning loops, and audit trails (the substrate of reasoning).
- Cognitum Seed — always-on, contactless mmWave edge sensing (the continuous signal).
- MetaHarness / Darwin Mode — the whole stack is minted as a branded harness that self-optimizes toward faithfulness while the underlying model stays frozen.
Repository layout
helix/
├── README.md ← this file
└── docs/
├── Helix-PHI-ADR-Product-Spec.md ← the full product spec (v1.0.0, with diagrams)
└── adr/
├── README.md ← ADR index
└── ADR-001 … ADR-019 ← 19 detailed Architecture Decision Records
Start here
- The product spec — vision, capability wish list, reference architecture, anti-hallucination design, roadmap, and the differentiation vs. ChatGPT Health.
- The ADR index — the 19 load-bearing architecture decisions, each researched and evidence-graded.
The three decisions that make or break a product in this space: anti-hallucination / data-grounding ([ADR-005](docs/adr/ADR-005
Description
Helix — a private, local-first, anti-hallucination Personal Health Intelligence platform on the ruvnet stack (Ruflo + RuVector + Cognitum Seed + MetaHarness/Darwin).
Related repositories
Similar projects matched by category, topics, and programming language.
steelbrain
Featured
reims-vgpu
reims-vgpu is an experimental virtual GPU for macOS guests that uses QEMU to decode the guest's GPU command stream and execute it through Metal or Vulkan, leveraging the built-in AppleParavirtGPU driver without requiring custom kexts.
m-novotny
Featured
memguard-rs
A Rust library that provides secure memory handling primitives including zeroization on drop, memory locking, constant-time comparison, and compile-time guarded regions, with zero dependencies and no_std support.