Open-source alternatives to Deepreasoning

LocalAI is a local generative AI platform and inference engine designed to host large language, vision, and audio models on private hardware. It functions as an API compatible gateway that mimics proprietary service endpoints, allowing existing third-party software to integrate with a self-hosted backend. The platform distinguishes itself as a distributed AI model orchestrator, capable of scaling inference across machine clusters using VRAM-aware routing and hardware coordination. It provides a unified interface for diverse open-source backends and supports self-hosted RAG infrastructure thro

SwanLab is an open-source machine learning experiment tracking platform and observability tool. It provides a centralized dashboard for logging training metrics, hyperparameters, and hardware performance to monitor and analyze AI model training runs. The platform is distinguished by its focus on self-hosted infrastructure, allowing users to deploy private instances via Docker or Kubernetes for secure on-premises data control. It also includes specialized utilities for migrating historical experiment logs and synchronizing real-time metrics from external tools like MLflow. The system covers a

Superduper is an AI agent development kit and LLM application framework designed to build autonomous agents and data-driven applications. It functions as a RAG orchestration platform and vector search infrastructure, coordinating AI models with database storage to perform multi-step computations and actions using persisted data states. The project distinguishes itself by providing a database-integrated machine learning pipeline that executes training and inference tasks directly on data hosted within SQL and NoSQL databases. It allows for the deployment of self-hosted AI infrastructure on pri

This project is a self-hosted bot protection service and CAPTCHA alternative that verifies human identity without relying on third-party tracking. It utilizes a combination of WebAssembly-based proof-of-work puzzles and browser instrumentation to distinguish humans from automated bots. The system is delivered as dockerized security middleware and a privacy-first verification API that operates without the use of cookies or user fingerprinting. The service differentiates itself by using GPU-resistant time-lock algorithms and instrumentation-based detection to identify headless browsers and auto

This project is a self-hosted, web-based interface designed for interacting with large language models. It provides a centralized dashboard that enables users to manage model communications, maintain persistent conversation histories, and organize prompt libraries within a private, containerized environment. The platform distinguishes itself through robust administrative and security controls, including support for enterprise identity providers, password-based access, and request rate limiting. It facilitates flexible connectivity by allowing users to configure custom network proxies, manage

This project is a Bing AI proxy gateway and web-based chat interface. It functions as a Go reverse proxy that routes HTTP traffic to external AI endpoints, allowing users to bypass regional network restrictions and login requirements. The system utilizes SOCKS5 proxy tunneling and environment-variable configuration to circumvent IP-based blocking and regional firewalls. It manages authentication by injecting predefined session cookies into outgoing requests to maintain private AI sessions and unlock personalized features. The application integrates a Vue-based single page application for the

This is an open-source Python SDK for building and orchestrating production-grade AI agents. It provides a unified framework for creating conversational agents that can use tools, maintain state, and coordinate across multiple language model providers including OpenAI, Anthropic, Google, Amazon Bedrock, and locally-hosted models. The SDK supports multi-agent orchestration through graphs, teams, and swarms, allowing several specialized agents to collaborate on complex tasks. Agents can be composed as callable tools that other agents invoke, and the framework includes policy handlers that inspe

Deepagents is an LLM agent orchestration platform and stateful application server designed for deploying and managing AI agents built with computational graphs. It provides a containerized runtime environment that handles agent execution, state persistence, and the versioning of AI assistants. The platform distinguishes itself through deep integration with the Model Context Protocol, allowing agents to function as servers that expose tools and capabilities to external clients. It features a sophisticated observability suite for capturing execution traces, performing LLM-based evaluations agai

LibreTranslate is an open-source, self-hosted machine translation engine that provides a private alternative to proprietary cloud-based translation services. It functions as a portable translation server, allowing users to process text and document translations locally or within their own infrastructure without relying on external providers. The platform distinguishes itself through its focus on privacy and flexible deployment, supporting anonymous network routing to bypass restrictive firewalls and protect user data. It is designed for integration into broader software ecosystems, offering a

Compiler Explorer is an online tool and analysis platform used to translate source code into assembly in real time. It functions as a cross-compiler analysis tool, allowing users to examine how various compilers and versions translate the same source code into machine code to analyze optimizations and generation patterns. The platform supports low-level language debugging and the comparison of assembly output across different compiler toolchains. It also provides a self-hosted environment option for users who need to run private deployments with custom binaries or operate within secure offlin

Snapdrop is a web-based local file sharing tool and progressive web app designed for transferring files between devices on the same local network. It functions as an end-to-end encrypted transfer tool that allows users to move data across different devices and operating systems without manual configuration. The service supports self-hosting through a containerized deployment model, allowing users to run private instances of the file sharing service on their own infrastructure. This ensures that data transfers remain within a private local network. The system uses a signaling server for local

This project is a self-hosted email verification system and API designed to validate email existence and clean mailing lists on private infrastructure. It functions as a deliverability tool that confirms if email addresses are reachable by communicating with mail servers via the SMTP protocol without sending actual messages. The system is distinguished by its high-volume SMTP infrastructure, which utilizes a stateless worker architecture and message queue task distribution to scale validation tasks. It includes an SMTP proxy gateway that routes requests through SOCKS5 proxies to mask server i

OpenHuman is an AI application framework for building private intelligence systems and personal AI layers. It provides a system for deploying private AI assistants that execute technical tasks and manage personal knowledge bases. The project features a model-agnostic request proxy that routes AI workloads to different large language models based on requirements for reasoning, speed, or vision. It integrates an OAuth-driven data integrator to synchronize personal information from external services into a local knowledge base composed of hierarchical Markdown summaries. The framework also inclu

Claude Code is a command-line interface and multi-agent orchestration framework designed for autonomous software engineering. It enables AI agents to perform codebase modifications, debugging, and Git workflow management while coordinating multiple specialized agents to decompose and execute complex engineering tasks in parallel. The system distinguishes itself through a high degree of isolation and safety, utilizing Git worktrees to create independent working directories for concurrent agents and implementing a tiered permission system that combines user rules, project policies, and OS-level

FastDeploy is a high-performance deployment framework for large language models, vision models, and multimodal models. It provides the infrastructure to launch model services that process combined image, video, and text inputs, exposing these capabilities through a standardized, OpenAI-compatible API for chat and text completions. The project distinguishes itself through advanced inference pipeline engineering and GPU optimization. It employs speculative decoding, tensor parallelism, and a disaggregated execution model that separates prefill and decode phases across different hardware resourc

This project is a self-hosted, cross-platform instant messaging platform featuring a Go backend and a protobuf-based messaging server. It provides a unified communication suite with native clients for iOS, Android, and web, utilizing gRPC and Protocol Buffers for efficient data exchange. The system is distinguished by an extensible chatbot framework that allows for the integration of automated bots and plugins via standardized service interfaces. It supports high-availability clustering with sharded load distribution and a pluggable database backend to ensure reliability and flexible data per

Suna is an orchestration platform designed for the deployment, management, and governance of autonomous AI agents. It provides a centralized system for defining agent behaviors and tool integrations, enabling the automation of complex business processes through a unified interface. The platform distinguishes itself by applying infrastructure-as-code principles to AI, utilizing version-controlled repositories to manage agent configurations, skills, and guardrails. It ensures secure and predictable operations by spawning ephemeral, isolated virtual machines for every individual task, preventing

Kimi-K2 is a conversational AI engine and reasoning framework designed for text generation, advanced problem solving, and coding tasks. It functions as a tool-augmented language model capable of producing human-like chat responses through a compatible model interface. The system utilizes a reasoning-optimized architecture that separates standard conversational flow from deep logical processing. This allows the model to execute autonomous tasks by invoking external functions and calling APIs to retrieve real-time data. The project supports structured JSON output parsing for function-call inte

Arize Phoenix is an LLM observability platform and evaluation framework designed to capture execution traces and monitor large language model applications. It serves as a prompt management system for versioning and testing templates, and as a self-hosted AI operations infrastructure for managing telemetry and experiments. The platform differentiates itself through a specialized embedding visualization tool used to detect data drift and optimize vector search. It provides a comprehensive evaluation suite that utilizes judge-based evaluators and ground-truth datasets to score model outputs, and

webui-aria2 is a web-based graphical interface and RPC client designed to control and monitor aria2 download services. It functions as a frontend that interacts with the aria2 JSON-RPC API to manage file transfers and torrents through a browser. The project is delivered as a containerized web application, ensuring a consistent deployment of the download dashboard across different hardware architectures. It utilizes a stateless frontend architecture that renders static files in the browser and fetches the current state of all downloads directly from the remote service. The interface covers re

This project is an interactive coding tutorial platform and markdown-based course engine. It functions as a web-based education system that transforms markdown files into structured educational pages with integrated interfaces for writing and running code. The platform utilizes a remote code execution framework to validate user-submitted snippets in real time by integrating with external compilers and execution engines. To ensure consistent delivery across different hosting platforms, the entire learning environment is provided as a containerized deployment. The system covers a broad capabil

Nitter is a privacy-focused, alternative web interface for viewing public social media content. It functions as a server-side proxy that fetches and renders external posts, allowing users to browse content without requiring a personal account or executing third-party tracking scripts. By stripping away user identifiers and tracking mechanisms, the application provides a lightweight, anonymous viewing experience. The project distinguishes itself through its emphasis on network-level privacy and self-sovereignty. It supports routing traffic through Tor and I2P networks to bypass censorship and

This project is a secure intermediary proxy gateway for large language model APIs. It functions as a relay service that forwards requests to AI providers while managing service accounts and routing traffic. The service provides a compatibility layer that supports multiple endpoint formats, allowing different third-party AI clients to communicate with a single provider. It distinguishes itself through a service account management system that assigns individual proxy settings to multiple accounts to prevent IP bans and distributes traffic via load balancing to avoid rate limits. The system inc

Kill Bill is a subscription billing platform and usage-based billing engine designed to manage recurring invoicing and automated payment collection. It functions as a multi-tenant billing infrastructure, providing isolated environments for different organizational entities through a dedicated API. The system is distinguished by a plugin-based extension framework that allows for the integration of third-party payment gateways and custom business logic. It includes a payment gateway orchestrator to handle transactions and refunds, as well as a revenue recognition system to allocate contract rev

9router is an AI model gateway designed to route requests from AI coding tools to multiple model providers through a single unified API. It provides administration for self-hosted AI proxy deployments, allowing users to manage API keys and model access on local servers or edge networks. The system differentiates itself through multi-provider API normalization, which translates incompatible request and response formats to ensure compatibility across different AI models. It features AI provider failover management to automatically switch between providers or accounts when quotas are exhausted o

Gotenberg is a stateless, containerized service that provides a unified API for document conversion, manipulation, and web-to-PDF rendering. It functions as a centralized engine that abstracts complex document processing tasks, allowing users to interact with various rendering tools and libraries through standard HTTP requests. The service distinguishes itself by utilizing headless browser automation to capture web content and by wrapping multiple specialized PDF engines into a single interface. It supports asynchronous task execution, offloading resource-intensive operations to background wo

Invidious is a privacy-focused, self-hosted alternative frontend for mainstream video platforms. It operates as a decentralized network of independent instances that provide a lightweight, ad-free interface for consuming media. By acting as a proxy between the user and the content provider, the platform prevents tracking and data collection while maintaining a familiar browsing experience. The project distinguishes itself through its robust suite of network-level traffic management and anonymization tools. It employs techniques such as IP rotation, reverse proxy stream routing, and integratio