Search Results for "http-client"

RWKV (pronounced as RwaKuv) is an RNN with GPT-level LLM performance, which can also be directly trained like a GPT transformer (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, fast training, saves VRAM, "infinite" ctxlen, and free text embedding. Moreover it's 100% attention-free. Default configs has enabled custom CUDA kernel acceleration, which is much faster and consumes much less VRAM. If you encounter possible compatibility...

AI as Workspace, short for AI as Workspace, is an open-source AI client application that provides a unified interface for interacting with multiple large language models and AI tools within a single workspace environment. The platform is designed as a lightweight yet powerful desktop or web application that organizes AI interactions through structured workspaces. Instead of managing individual chat sessions separately, users can group conversations, artifacts, and tasks within customizable workspaces that support different projects or contexts. ...

...It is designed for personal experimentation, testing, and lightweight development workflows where users want to route requests through several providers without rewriting client code for each one. The project can automatically fail over between configured providers when one is unavailable or exhausted. Its OpenAI-compatible design makes it easier to use with existing tools, SDKs, and applications that already expect that API shape. It is not positioned as an enterprise-grade service or a way to bypass provider terms, but as a local coordination layer for personally owned free-tier credentials. freellmapi is useful for developers who want a practical testing proxy for comparing models, managing limits, and improving request continuity.

...The platform provides a backend-first architecture that allows developers to create sophisticated agent systems while maintaining flexibility in model providers and infrastructure choices. It consists of two main components: a core framework that handles agent logic and orchestration, and a reference client application that demonstrates how agents can be deployed and interacted with through a web interface. Built primarily with TypeScript and modern web technologies, the framework emphasizes extensibility and predictable behavior through configurable determinism. AgentDock also supports integration with multiple large language model providers, enabling developers to combine reasoning models, APIs, and external tools within a unified automation pipeline.

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. ...

Chat with GPT is an open-source conversational interface designed to provide an enhanced user experience for interacting with ChatGPT-style language models. The application serves as a customizable alternative client that allows users to connect to language model APIs using their own credentials. Built with modern web technologies such as React and TypeScript, the platform provides a responsive chat interface with advanced features for conversation management. Users can review past chat sessions, modify system prompts, and adjust model parameters such as temperature to control response creativity. ...