Search Results for "inference" - Page 3
Sort By:
Showing 63 open source projects for "inference"
View related business solutions-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
Veeam Data Platform v13.1Try Veeam Data Platform today. Experience the unified platform that's secure by design, portable by default, and proven to recover clean, fast, and anywhere.
-
1
RestorePhotos.io
Restoring old and blurry face photos with AI
...The project is production-oriented, not just a toy: it uses Bytescale for storage and image processing, Vercel for hosting and serverless functions, Auth.js + Neon for authentication and database, and Upstash Redis for rate limiting. This combination makes it a good blueprint for building real-world AI apps that must deal with authentication, quotas, and storage as well as inference. -
2
TypeScript Deep Dive
The definitive guide to TypeScript
...It begins with language fundamentals and progresses through project configuration, modules, declarations, and migration from JavaScript. Detailed chapters explain interfaces, generics, inference, unions, type guards, JSX, React, and strict compiler options. The book also covers testing, npm workflows, formatting, linting, and practical coding patterns. Advanced readers can study the TypeScript compiler architecture, including its scanner, parser, binder, checker, and emitter. Examples, community-informed explanations, translations, and downloadable ebook formats make it useful as both a structured course and a long-term reference. -
3
Secret Llama
Fully private LLM chatbot that runs entirely with a browser
Secret Llama is a privacy-first large-language-model chatbot that runs entirely inside your web browser, meaning no server is required and your conversation data never leaves your device. It focuses on open-source model support, letting you load families like Llama and Mistral directly in the client for fully local inference. Because everything happens in-browser, it can work offline once models are cached, which is helpful for air-gapped environments or travel. The interface mirrors the modern chat UX you’d expect—streaming responses, markdown, and a clean layout—so there’s no usability tradeoff to gain privacy. Under the hood it uses a web-native inference engine to accelerate model execution with GPU/WebGPU when available, keeping responses responsive even without a backend. ... -
4
OpenPipe
Turn expensive prompts into cheap fine-tuned models
...One of its core components, the Agent Reinforcement Trainer, allows developers to train multi-step agents using reinforcement learning techniques such as GRPO, enhancing their ability to perform complex, sequential tasks. OpenPipe emphasizes cost reduction by enabling organizations to distill high-cost inference workflows into smaller, specialized models that can run more efficiently at scale. -
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
5
ModelFusion
The TypeScript library for building AI applications
ModelFusion is an open-source TypeScript library designed to simplify the development of AI-powered applications by providing a unified abstraction layer for interacting with different AI model providers. The framework allows developers to integrate large language models and other generative systems into JavaScript and TypeScript applications through a consistent and standardized API. Instead of writing separate integration logic for each provider, developers can use ModelFusion to handle... -
6
Prem AI
Prem provides a unified environment to develop AI applications
An intuitive desktop application designed to effortlessly deploy and self-host Open-Source AI models without exposing sensitive data to third-party. Prem provides a unified environment to develop AI applications and deploy AI models on your infrastructure. Abstracting away all technical complexities for AI deployment and ushering in a new era of privacy-centric AI applications - users can finally retain control and ownership of their models. The AI services expose an HTTP API interface,... -
7
Mitt
Tiny 200 byte functional event emitter / pubsub
...Then with a module bundler like rollup or webpack, use as you would anything else. The UMD build is also available on unpkg. Set "strict": true in your tsconfig.json to get improved type inference for mitt instance methods. Alternatively, you can use the provided Emitter type. Remove an event handler for the given type. If handler is omitted, all handlers of the given type are removed. Invoke all handlers for the given type. If present, '*' handlers are invoked after type-matched handlers. -
8
Spartan Schema
Ultra-minimal JSON schemas with Typescript inference
An ultra-minimal, Typescript-compatible alternative to JSON Schema, designed as part of Osmosis. -
9
Yoha
A practical hand tracking engine
Yoha is a browser-based hand tracking engine designed to enable real-time gesture recognition and interaction using standard webcams, making it accessible for web applications without specialized hardware. Built using JavaScript and TensorFlow.js, it runs directly in the browser and performs inference on-device, eliminating the need for server-side processing. The engine is capable of detecting 21 two-dimensional hand landmarks, allowing developers to build applications that respond to gestures such as pinching or forming a fist. Its design focuses on practical usability, meaning it prioritizes common and meaningful gestures that can be easily integrated into interactive experiences like drawing tools, games, or accessibility interfaces. ... -
Earn up to 16% annual interest with Nexo.Generate interest, borrow against your crypto, and trade a range of cryptocurrencies — all in one platform. Geographic restrictions, eligibility, and terms apply.
-
10
typera
Type-safe routes for Express and Koa
Typera helps you build backends in a type-safe manner by leveraging io-ts and some TypeScript type inference magic. It works with both Express and Koa. -
11
Nexus
Code-First, Type-Safe, GraphQL Schema Construction
...Automatically generates and infers types based on the schema. No need to manually add annotations, Nexus can automatically infer them in TypeScript using global declaration merging and conditional type inference. For association type fields, you can either import types you've created, or supply their names as strings, with free autocomplete. -
12
ThinkTs
Based on koa and typeorm,asynchronous non blocking reactive coding
Based on koa and Typeform, asynchronous nonblocking reactive coding, and a real MVC web framework, inspired by [ThinkPHP + Nestjs + FastAPI], it is also the fastest development speed and fastest performance. -
13
typesafe-actions
Typesafe utilities for "action-creators" in Redux / Flux Architecture
typesafe-actions is a TypeScript utility library designed to reduce type verbosity and boilerplate in Redux architectures. It provides strongly typed helpers for creating synchronous and asynchronous Redux actions. Its reducer utilities infer state and action types while validating handlers at compile time. Helper types can derive action and state types directly from existing implementations. The library supports integrations with common asynchronous approaches such as redux-observable and...
