Hoa Kỳsreenidhbonagiri/remedi
Find affordable prescription alternatives and patient assistance programs in seconds using FDA data and income eligibility checks.
Thành tựu nổi bật
Những danh hiệu mới nhất của dự án
#1 Repository Của Ngày
#1 Repository Của Ngày
#1 Repository Của Ngày
💊 Remedi: deterministic prescription savings copilot
Brand drug too expensive? Remy the copilot finds bioequivalent generics and pre-fills assistance applications in under 200ms.
Remedi is a FastAPI backend that turns public FDA registries and statutory poverty guidelines into concrete patient savings. Built by sreenidhbonagiri, it targets two gaps: unclaimed manufacturer Patient Assistance Programs and avoidable brand-name spending. A guided intake hands off to a LangGraph state machine that returns generic equivalents, net dollar savings and doctor discussion prompts.
✨ Highlights
- FDA Orange Book matching: cross-references brand queries against OpenFDA to isolate therapeutically equivalent generics with TE Code AB.
- Real cost deltas: computes out-of-pocket differences live, unlocking up to 80% direct cost reductions.
- 2026 HHS FPL math: deterministic eligibility per 42 U.S.C. § 9902(2) across Continental US, Alaska and Hawaii, with 200%-400% FPL program caps.
- Zero-hallucination guardrails: the LLM cannot do arithmetic or quote prices without relational database citations; errors fall back to a deterministic plan.
- In-memory PDFs: ReportLab streams pre-filled applications via io.BytesIO, zero disk persistence of income data.
- Tested stack: FastAPI, Pydantic v2, LangGraph, 24 pytest checks, deployed on Render with a live demo.
💡 Why it matters
Most savings tools guess. Remedi keeps the LLM on conversation duty and pushes every number through validated services, so eligibility and pricing stay deterministic. That matters when the output is a printable, pre-filled assistance form.
Fits patients, clinics and navigators comparing brand vs AB-rated generic cost, or checking PAP eligibility by household size and income.
#FastAPI #LangGraph #HealthcareAI #OpenSource #TiniX
Dự án tương tự
Khám phá các dự án và mô hình AI khác có sự tương đồng.
The most popular HTML, CSS, and JavaScript framework for developing responsive, mobile first projects on the web.
Reverse engineer anything with agents, from app behavior down to native binaries.
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
:electron: Build cross-platform desktop apps with JavaScript, HTML, and CSS
Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.
all-MiniLM-L6-v2 This is a sentence-transformers(https://www.SBERT.net) model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search. Usage (Sentence-Transformers) Using t...