QVAC SDK, a universal JavaScript SDK for building local AI applications
Hi folks, today we're launching QVAC SDK [0], a universal JavaScript/TypeScript SDK for building local AI applications across desktop and mobile.The project is fully open source under the Apache 2.0 license. Our goal is to make it easier for developers to build useful local-first AI apps without having to stitch together a lot of different engines, runtimes, and platform-specific integrations. Under the hood, the SDK is built on top of QVAC Fabric [1], our cross-platform inference and fine-tuning engine.QVAC SDK uses Bare [2], a lightweight cross-platform JavaScript runtime that is part of the Pear ecosystem [3]. It can be used as a worker pretty much anywhere, with built-in tooling for Node, Bun and React Native (Hermes).A few things it supports today: - Local inference across desktop, mobile and servers - Support for LLMs, OCR, translation, transcription, text-to-speech, and vision models - Peer-to-peer model distribution over the Holepunch stack [4], in a way that is similar to BitTorrent, where anyone can become a seeder - Plugin-based architecture, so new engines and model types can be added easily - Fully peer-to-peer delegated inference We also put a lot of effort into documentation [5]. The docs are structured to be readable by both humans and AI coding tools, so in practice you can often get pretty far with your favorite coding assistant very quickly.A few things we know still need work: - Bundle sizes are larger than we want right now because the current packaging of Bare add-ons is not as efficient as it should be yet - Plugin workflow can be simpler - Tree-shaking is already possible, but at the moment it still requires a CLI step, and we'd like to make that more automatic and better integrated into the build process This launch is only the beginning. We want to help people build local AI at a much larger scale. Any feedback is truly appreciated! Full vision is available on the official website [6].References:[0] S
FL score
out of 100
Verdict
high confidence
Competition
9
competitors found, emerging market, funded players
Trend
No signal yet
A universal JavaScript SDK for local AI, a noble and complex endeavor, is too broad, competitive, and resource-intensive for a solo builder with no clear direct monetization.
The pain
The gap
Build angle
Strengths
- Addresses a real and growing problem in local AI development.
- The market for local AI is expanding rapidly.
- Offers genuinely unique features like peer-to-peer model distribution.
- Uses a modern tech stack (JS/TS, custom runtime, plugin architecture).
- Good documentation strategy (AI-readable).
Risks
- Extreme build complexity for a solo builder; requires deep expertise in multiple domains.
- Market dominated by well-funded Big Tech players (Google, Microsoft, Vercel, LangChain).
- Core SDK is open-source and free, making direct monetization for a solo builder very challenging.
- High barriers to distribution and developer adoption in a crowded space.
- Acknowledged technical challenges (bundle size, plugin workflow, tree-shaking) indicate significant ongoing development effort.
- No clear 'narrow wedge' for immediate adoption and payment; too broad an offering.
Next steps
- Do not build as a solo founder; this is a large-scale project requiring a team and significant funding.
- If interested in the local AI space, identify a much narrower niche or application *built on top* of existing SDKs that solves a specific, paid problem for a defined audience.
- Explore if any specific complaints about existing SDKs (e.g., TF.js learning curve, ONNX model conversion) could be solved with a *small, focused utility* rather than a universal SDK.
Fly Labs Method
Is the pain real, is there a gap, is it the right time, can one person build it.
- Problem clarity
- 25
- Solution gap
- 9
- Willingness to pay
- 10
- Buildability
- 8
The idea addresses a real and growing pain in local AI development, but faces extreme competition from well-funded Big Tech players, and the product itself is a massive engineering feat for a solo builder with limited direct monetization paths for the SDK itself.
Value Equation
Dream outcome and how likely it feels, against the time and effort it costs.
This idea has strong market growth and addresses a clear pain, but is a massive undertaking with limited direct monetization potential for a solo builder in a highly competitive and well-funded space.
One-Person Business
Curiosity pull, identity fit, and a path from free value to paid for a solo creator.
While the problem is clear and the unique P2P feature offers leverage, the extreme complexity and lack of direct monetization make this a very poor fit for a solo builder.
Viral Frameworks
Hook strength, shareability, and how cheaply it can be tested.
This idea has a clear value proposition for developers in a growing market, but the lack of an inherent business model for the open-source SDK and high distribution challenges make it unviable as a micro-SaaS for a solo builder.
Builder Lens
Evidence the problem exists, timing, defensibility, and a model that fits on a napkin.
This idea addresses a clear and growing demand for local AI, but its broad scope, strong competition, and lack of initial user 'surprise' make it a challenging proposition for a new startup, especially for a solo builder.
Why this verdict
Five lenses, one composite. How scoring works
The angle
This weekend
- Do not build as a solo founder; this is a large-scale project requiring a team and significant funding.
- If interested in the local AI space, identify a much narrower niche or application *built on top* of existing SDKs that solves a specific, paid problem for a defined audience.
- Explore if any specific complaints about existing SDKs (e.g., TF.js learning curve, ONNX model conversion) could be solved with a *small, focused utility* rather than a universal SDK.
Who is already there, emerging market
An open-source library developed by Google for machine learning in JavaScript, allowing models to run in the browser or Node.js.
Pricing: Free and open-source.
A JavaScript library for running ONNX models in browsers and Node.js, leveraging WebAssembly and WebGL for optimized inference.
Pricing: Free and open-source.
Microsoft's cross-platform local AI solution that enables developers to integrate AI directly into their applications with no cloud dependency.
Pricing: Not explicitly stated as paid, but positioned as a Microsoft solution. Source code is available.
An open-source TypeScript framework and platform for building, testing, and deploying AI agents and applications.
Pricing: Offers a platform with pricing, but the framework itself is open-source. Specific pricing details not found easily on their website.
A provider-agnostic TypeScript toolkit for building AI-powered applications and agents using popular UI frameworks and runtimes.
Pricing: Free and open-source.
A fully-featured JavaScript/TypeScript version of LangChain, providing abstractions for building AI agents, chains, tools, and memory.
Pricing: Free and open-source.
- ml.jsVisit
A comprehensive machine learning toolkit for JavaScript and Node.js, offering a wide range of statistical and ML algorithms.
Pricing: Free and open-source.
- ml5.jsVisit
A JavaScript machine learning library based on TensorFlow.js, focused on providing an approachable API for creative coding and interactive experiences.
Pricing: Free and open-source.
- Nexa SDKVisit
An SDK for running any AI model on any device, across any backend locally, supporting various model types and hardware.
Pricing: Not explicitly stated on the Product Hunt page, but implies a developer tool.
What they charge
Recent news
- Tether Introduces QVAC SDK, An Open-Source Framework For Scaling AI Across Computing Devices And Operating Systems
Crowdfund Insider, April 12, 2026
- Tether Releases Open-Source QVAC SDK to Enable Local AI Development on Multiple Platforms - MLQ.ai
MLQ.ai, April 10, 2026
- Microsoft has released 'Foundry Local,' an SDK that makes it easy to create apps that include local AI, allowing users to integrate the Qwen and Whisper series into their own applications.
GIGAZINE, April 13, 2026
- Tether Launches Open-Source QVAC SDK for Local AI Applications | Intellectia.AI
Intellectia.AI, April 10, 2026
- Tether Unveils QVAC SDK, Positioning It as a Universal Engine for AI Development
WEEX Crypto News, April 09, 2026
Market signals
The market for local AI applications is a rapidly growing and significant space, driven by increasing demands for data privacy, offline functionality, reduced latency, and lower cloud costs. Recent news indicates a strong push towards decentralized and edge AI, with major players like Microsoft and Tether (through QVAC SDK) entering the space. The emphasis is on enabling AI to run directly on user devices across various platforms, fostering a 'local-first' approach to intelligence.
What frustrates people
- TensorFlow.js can be slower for training large models compared to its Python counterpart due to JavaScript engine limitations.
- TensorFlow.js has a steeper learning curve for beginners and fewer specialized libraries and extensions compared to Python TensorFlow.
- ONNX Runtime Web primarily functions as an execution engine, necessitating model conversion to the ONNX format, which can add an extra development step.
- LangChain.js can be challenging to learn due to its extensive ecosystem and numerous abstractions.
- Some JavaScript ML libraries, while open-source, may have less frequent updates or a smaller community compared to more established Python alternatives.
Semble – Code search for agents that uses 98% fewer tokens than grep
Hey HN! We (Stephan and Thomas) recently open-sourced Semble. We kept running into the same problem while using Claude Code on large codebases: when the agent can't find something directly, it falls back to grep, reading full files or launching subagents. This uses a lot of tokens, and often still misses the relevant code. There are existing tools for this, but they were either too slow to index on demand, needed API keys, or had poor retrieval quality.Semble is our solution for this. It combines static Model2Vec embeddings (using our latest static model: potion-code-16M) with BM25, fused via RRF and reranked with code-aware signals. Everything runs on CPU since there's no transformers involved. On our benchmark of ~1250 query/document pairs across 63 repos and 19 languages, it uses 98% fewer tokens than grep+read and reaches 99% of the retrieval quality of a 137M-parameter code-trained transformer, while being ~200x faster.Main features:- Token-efficient: 98% fewer tokens than grep+read- Fast: ~250ms to index a typical repo on our benchmark, ~1.5ms per query on CPU (very large repos may take longer)- Accurate: 0.854 NDCG@10, 99% of the best transformer setup we tested- MCP server: drop-in for Claude Code, Cursor, Codex, OpenCode- Zero config: no API keys, no GPU, no external servicesInstall in Claude Code with: claude mcp add semble -s user -- uvx --from "semble[mcp]" sembleOr check our README for other installation instructions, benchmarks, and methodology:Semble: https://github.com/MinishLab/sembleBenchmarks: https://github.com/MinishLab/semble/tree/main/benchmarksModel: https://huggingface.co/minishlab/potion-code-16MLet us know if you have any feedback or questions!
AI
Postgres extension for BM25 relevance-ranked full-text search
Last summer we faced a conundrum at my company, Tiger Data, a Postgres cloud vendor whose main business is in timeseries data. We were trying to grow our business towards emerging AI-centric workloads and wanted to provide a state-of-the-art hybrid search stack in Postgres. We'd already built pgvectorscale in house with the goal of scaling semantic search beyond pgvector's main memory limitations. We just needed a scalable ranked keyword search solution too.The problem: core Postgres doesn't provide this; the leading Postgres BM25 extension, ParadeDB, is guarded behind AGPL; developing our own extension appeared daunting. We'd need a small team of sharp engineers and 6-12 months, I figured. And we'd probably still fall short of the performance of a mature system like Parade/Tantivy.Or would we? I'd be experimenting long enough with AI-boosted development at that point to realize that with the latest tools (Claude Code + Opus) and an experienced hand (I've been working in database systems internals for 25 years now), the old time estimates pretty much go out the window.I told our CTO I thought I could solo the project in one quarter. This raised some eyebrows.It did take a little more time than that (two quarters), and we got some real help from the community (amazing!) after open-sourcing the pre-release. But I'm thrilled/exhausted today to share that pg_textsearch v1.0 is freely available via open source (Postgres license), on Tiger Data cloud, and hopefully soon, a hyperscalar near you:https://github.com/timescale/pg_textsearchIn the blog post accompanying the release, I overview the architecture and present benchmark results using MS-MARCO. To my surprise, we were not only able to meet Parade/Tantivy's query performance, but exceed it substantially, measuring a 4.7x advantage on query throughput at scale:https://www.tigerdata.com/blog/pg-textsearch-bm25-fu
AI
Consus (YC F24) – LLM gateway for companies handling sensitive data
Hey Hacker News! I'm Eric, the founder of Consus. We route all AI requests to ITAR restricted and controlled unclassified information (CUI) compliant infrastructure. Consus itself satisfies ITAR restrictions, and we recently completed our FedRAMP equivalency audit against the 410 FedRAMP High controls. FedRAMP High is the U.S. government’s strictest security baseline for cloud services handling sensitive unclassified data. A breach of this data could cause severe or catastrophic harm. Achieving FedRAMP equivalency, or authorization, is required before processing CUI information.Demo: https://youtu.be/6MYxJe6P4oYAerospace and defense is experiencing rapid growth. Unfortunately, most companies are struggling to use AI because of necessary data protections & compliance risk. These companies can move even faster if they could use the AI tools that most other industries take for granted.I spent most of my career prior to Consus in aerospace & defense. I launched national security payloads at SpaceX, and was an early employee at Castelion. I’ve watched first hand how compliance red-tape makes it difficult for companies to adopt new technologies and trust vendors that touch their sensitive data. For example, I worked with a satellite manufacturer that doesn’t allow any AI tools, even for non-sensitive work.Even as AI has become extremely useful over the past 9-12 months, I was surprised by how many aerospace & defense companies refused to touch it. They could see how it could be helpful, but they were scared about model providers training on their data, violating an ITAR rule, or risk losing new business because of a failed cyber assessment. These are all rational fears.There were a lot of ways to solve some/all of these problems, but we focused on building a compliant AI inference layer that can "plug" into any AI tool or workflow. Just as OpenRouter integrates with most tools, Consus can connect to tools like ChatGPT or Clau
AI
Questions about this idea?
FlyBot reads the scoring and gives you a second opinion on “QVAC SDK, a universal JavaScript SDK for building local AI applications”.