Search Results for "application to store code"

aiac is a command line tool to generate IaC (Infrastructure as Code) templates, configurations, utilities, queries and more via OpenAI's API. The CLI allows you to ask the model to generate templates for different scenarios (e.g. "get terraform for AWS EC2"). It will make the request, and store the resulting code to a file, or simply print it to standard output. By default, aiac uses the same model used by ChatGPT, but allows using different models.

AxonHub is an open-source AI gateway platform designed to simplify the process of integrating and switching between different large language model providers. The system acts as a compatibility layer that allows developers to use the same SDK interface while routing requests to various AI services behind the scenes. Instead of rewriting code when switching providers such as OpenAI or Anthropic, developers can simply change configuration settings within the gateway. AxonHub translates requests...

csghub-server is the backend component of the CSGHub platform, an open-source infrastructure designed to manage and operate large language models, datasets, and AI development workflows within a private deployment environment. The server acts as a centralized management layer that allows teams to store, organize, and operate AI assets such as models, datasets, and machine learning applications in a manner similar to artifact repositories used in software engineering. Built primarily in the...

AWS Copilot is an open-source command-line interface that makes it easy for developers to build, release, and operate production-ready containerized applications on AWS App Runner, Amazon ECS, and AWS Fargate. Run a single command to quickly get started with a containerized application using best practices on AWS from a Dockerfile. Instead of modeling individual resources, Copilot provides common cloud architectures, request-driven web service, load-balanced web service, backend service,...

ChatGPTProxy is an open-source project that creates a lightweight proxy server to intermediate between client applications and the ChatGPT web endpoints, allowing developers to integrate ChatGPT-style functionality into their software without using an official API or embedding web UI code directly. This tool works by accepting requests in a defined format, forwarding them through the proxy to ChatGPT’s backend services, and returning responses to the caller, abstracting away direct browser automation or scraping concerns from the application layer. By consolidating the traffic through a proxy, developers can centralize logging, throttling, authentication, and caching in one place, making it easier to build consistent and controlled AI workflows. ...

llama.go is like llama.cpp in pure Golang. The code of the project is based on the legendary ggml.cpp framework of Georgi Gerganov written in C++ with the same attitude to performance and elegance. Both models store FP32 weights, so you'll needs at least 32Gb of RAM (not VRAM or GPU RAM) for LLaMA-7B. Double to 64Gb for LLaMA-13B.