Open-source alternatives to Gpt Load

pgdog is a PostgreSQL sharding proxy, distributed SQL router, and connection pooler. It is designed to enable horizontal data distribution by splitting tables and indices across multiple independent servers to scale storage and processing capacity. The project distinguishes itself through online resharding capabilities, using logical replication to move data between shards without application downtime. It supports multiple routing strategies, including hash, list, and range-based query routing, and manages distributed atomic transactions using a two-phase commit process to ensure consistency

gpt4free-ts is a TypeScript-based LLM API proxy and gateway that provides a unified interface for accessing large language models without paid subscriptions or official API keys. It functions as a containerized AI bridge that routes requests to various free third-party providers to retrieve chat completions. The project acts as an OpenAI API wrapper, translating requests and responses into the standard OpenAI chat completions format to ensure compatibility with existing AI tools. It utilizes a provider-based routing system to distribute request loads across available endpoints. The gateway s

This project is a multimodal AI proxy and content generation hub that provides a unified web interface for interacting with multiple large language models and generative AI services. It functions as a secure API access gateway, routing requests from a single dashboard to various external AI backends using configurable base URLs and API keys. The platform is delivered as a cross-platform progressive web application, allowing for installation on Linux, Windows, and MacOS. It distinguishes itself by consolidating text, image, audio, and video generative controls into a standardized interface, su

DnsServer is a recursive and authoritative DNS server that provides domain name resolution and zone hosting. It functions as both a recursive resolver, performing iterative lookups across the internet, and an authoritative manager for primary and secondary DNS zones. The system distinguishes itself through high-availability clustering and a programmable HTTP API for automating server configurations and bulk record management. It supports a wide range of encrypted transport protocols, including TLS, HTTPS, and QUIC, and allows for custom functionality via a plugin-based request interception fr

This project is an AI API gateway and proxy that translates and normalizes requests between different AI model formats to ensure compatibility across client applications. It functions as a middleware service that can transform local command-line binaries into web services, allowing them to be triggered via HTTP requests. The system is distinguished by its ability to route multimodal text and image inputs and extract internal reasoning chains from model outputs to separate the chain of thought from the final answer. It includes an authentication manager that automatically cycles through multip

OptiLLM is an AI reasoning and optimization framework that functions as an API proxy to enhance the response quality of large language models. It intercepts requests to apply inference-time reasoning logic and output refinement before returning results to the client. The project distinguishes itself through a combination of inference-time search trees for logical verification and an anonymization pipeline that removes personally identifiable information from prompts. It further extends model capabilities by orchestrating external tools, including real-time code execution and autonomous web re

This project is an artificial intelligence API gateway that centralizes connections to multiple model providers into a single, standardized interface. By acting as a proxy, it translates diverse provider protocols into a format compatible with existing clients, allowing developers to integrate various language models without managing provider-specific software development kits. The gateway distinguishes itself through a robust traffic management layer that includes intelligent request routing, weighted load balancing, and automated failover mechanisms to ensure service availability. It incorp

Helicone is an AI gateway and observability platform designed to intercept, manage, and monitor interactions with large language models. By acting as a reverse-proxy, it provides a centralized layer for routing requests across multiple AI providers, allowing developers to maintain consistent application logic while gaining deep visibility into model performance, usage, and costs. The platform distinguishes itself through a robust suite of traffic management and prompt engineering tools. It enables policy-driven control, including automatic failover between providers, rate limiting, and edge-b

Gauzy is an open business management platform and multi-tenant enterprise resource planning system. It provides a modular business framework designed to manage core organizational operations through a unified web interface or as a headless business API. The platform is distinguished by its integration with the Model Context Protocol, allowing it to act as a server that exposes business data and system functions as tools for AI assistants. It utilizes a dynamic plugin architecture and a dedicated marketplace to extend core business entities and services. The system covers a broad range of ope

Geekai is a multi-model AI platform and SaaS framework designed to deploy and manage AI agents and multimodal models through a unified interface. It serves as a multimodal AI gateway, providing centralized access to large language models and generative tools for text, image, audio, and video production. The project functions as an AI agent orchestrator, allowing for the definition of specialized personas and the import of external workflows and knowledge bases. It distinguishes itself by providing a complete commercial service layer, including credit-based billing, subscription management, an

This project is a web-based management interface designed for the administration, monitoring, and configuration of Nginx server instances. It functions as a centralized platform for managing reverse proxy settings, traffic routing, and server lifecycles, providing a visual dashboard to replace manual configuration file editing. The platform distinguishes itself through integrated infrastructure automation and observability tools. It supports distributed environments by synchronizing configuration states across multiple nodes and containerized services, while offering artificial intelligence a

Apache Dubbo Go is a Go language implementation of the Apache Dubbo framework designed for building high-performance microservices. It serves as a cross-language RPC framework and microservices communication layer that enables remote procedure calls between services written in different programming languages. The framework functions as a service governance toolset and a distributed service mesh proxy, allowing data planes to connect with external control planes in proxy or proxyless modes. It specifically provides a compatibility layer to facilitate communication between Go and Java-based ser

This project is a ChatGPT-powered bot integrated into the Feishu chat platform, enabling conversational AI, image generation, and voice interaction within both private and group chats. It connects large language models to the team messaging environment, allowing users to engage in multi-topic conversations, generate images from text prompts, and analyze uploaded images using vision models. The bot supports persona preset switching, allowing predefined role templates to modify the AI's behavior and tone with a single command. It maintains separate conversation histories per topic using session

This project is a containerized dynamic DNS update client designed to automate the synchronization of domain records with changing public IP addresses. It functions as a multi-provider synchronization engine that monitors network connectivity and updates DNS records across various cloud platforms and custom services to ensure consistent domain resolution. The system distinguishes itself through a provider-based adapter pattern that abstracts diverse third-party APIs into a unified interface, allowing for consistent record management. It employs multi-source IP discovery to mitigate rate limit

ZenML is an extensible machine learning orchestration framework designed to manage the end-to-end lifecycle of data pipelines and AI agent workflows. It functions as a durable orchestrator that executes machine learning tasks as directed acyclic graphs, ensuring that every step is containerized for consistent performance across local, cloud, and hybrid infrastructure. By decoupling pipeline code from underlying compute and storage backends, the platform allows developers to define infrastructure-agnostic stacks that remain portable across diverse environments. The project distinguishes itself

kube-prometheus is a monitoring stack deployment and orchestration framework. It uses an operator pattern to automate the installation and lifecycle management of Prometheus and Alertmanager via custom resource definitions. The project focuses on scaling data collection through hash-based target sharding and topology-aware distribution to reduce cross-zone traffic. It implements a sidecar-based configuration reloading mechanism and utilizes consistent hashing to distribute scrape targets across multiple instances. The system covers broad observability capabilities including metric data colle

Temporal is a distributed workflow orchestration engine designed to manage fault-tolerant, stateful, and long-running background processes. It functions as a platform for coordinating complex cross-service operations, ensuring consistency and reliability in distributed environments by decoupling workflow orchestration from task execution. The platform distinguishes itself through a deterministic, event-sourced execution model that reconstructs workflow state by re-executing code from an immutable event log. This approach isolates non-deterministic side effects into managed activities, allowin

Bytebot is an LLM desktop automation framework and virtual Linux desktop environment. It enables AI agents to plan and execute mouse and keyboard actions on a virtual computer using natural language, allowing for autonomous desktop automation and the integration of legacy systems that lack native APIs. The system operates as an LLM API gateway and a Model Context Protocol server, routing requests across multiple language model providers with integrated load balancing and rate limiting. It provides isolated, containerized environments where agents use visual reasoning to interpret screenshots

This project is a containerized build automation system and self-hosted DevOps platform provided as a Docker image. It serves as a distributed build orchestrator and a Dockerized continuous integration and delivery server, ensuring consistent execution environments across different infrastructure. The system distinguishes itself through a distributed execution model that separates a primary controller from multiple remote agents connected via SSH, TCP, or web sockets. It utilizes a modular extensibility framework that allows the core system functionality to be augmented through the installati

Buildbot is a Python-based continuous integration framework and distributed build orchestrator. It functions as a build automation engine that coordinates the retrieval of source code, the execution of build steps, and the reporting of results through a central controller and a network of remote worker agents. The system is distinguished by a plugin-based extensibility architecture and a master-worker distribution model. It allows for dynamic build modification at runtime and supports a pluggable database backend for persisting system state and historical build data. The project covers a bro

Unkey is an API key management platform and gateway control plane designed for issuing, verifying, and revoking secure keys with global distribution. It provides the infrastructure necessary to authenticate requests and authorize access to protected resources with low latency. The platform distinguishes itself through edge-based request authentication and distributed rate limiting, which allow for the verification of keys and enforcement of request quotas at the network edge. It also features a usage-based billing engine and a self-service developer portal, enabling the tracking of metered AP

react-hot-loader is a developer utility for updating React components and hooks in real time. It functions as a state-preserving UI updater that wraps components in proxies, allowing the underlying logic to be replaced without unmounting the component tree. The tool maintains internal application state across hot module updates by swapping component logic while keeping the mount point constant. It includes mechanisms to intercept rendering errors during updates through temporary error boundaries and manages hook-order validation to prevent state mismatches when functional hooks change. The p

Axonhub is an AI gateway and multi-model API proxy that provides a unified interface for routing requests to multiple large language model providers. It functions as a load balancer and translation layer, converting a standardized API format into provider-specific payloads to enable communication with various AI models without provider-specific code. The system manages traffic through rule-based routing and automatic failover to maintain high availability. It differentiates its operations by providing a provider-agnostic interface that decouples client requests from specific model backends us

Llama-stack is a standardized orchestration stack and generative AI API gateway. It provides a unified communication layer and a consistent interface for deploying, managing, and interacting with various large language model providers and deployments. The system functions as an agent framework that manages tool execution and versioned skill bundles to automate complex tasks. It includes a batch processing system for handling large volumes of asynchronous requests through offline processing and a vector database interface for storing and searching documents to enable retrieval augmented genera

Wenda is a self-hosted infrastructure and gateway platform for deploying language models within internal networks to ensure data privacy and security. It functions as a centralized hub and API gateway that unifies communication between various offline model runners and online service providers through a single interface. The platform includes a workflow orchestrator that uses custom scripts and API calls to automate complex conversation flows and model settings. It also incorporates a retrieval system that augments model responses with external knowledge retrieved from vector databases and se