Open Source AI Models 180

Open-source LLM router for OpenClaw that optimizes model routing to save up to 70% costs. Manifest is an open-source LLM (Large Language Model) router specifically built for OpenClaw. It optimizes AI expenditures by intercepting queries and routing them to the most cost-effective model based on the complexity of the task, potentially saving users up to 70% on token costs. The system analyzes queries locally in less than 2ms to ensure minimal latency. It prioritizes privacy by performing query scoring on the user's machine and using a blind proxy architecture for its cloud version. Additionally, it allows users to track costs, set usage limits, and export data using the OpenTelemetry standard.

TrustGate by NeuralTrust is the only open source AI gateway with built in security for enterprises running LLMs and AI agents at scale. It sits in front of AI traffic to control access, enforce policies, and block threats like prompt injection and jailbreak attempts before they reach production. TrustGate ships with a catalogue of over 200 MCP connectors, so teams can plug in agents and tools without building custom integrations for every provider. TrustGate is an open source AI gateway built for enterprises deploying LLMs and AI agents in production. It gives security and engineering teams a single control point for AI traffic, with built in protection against prompt injection, jailbreaks, and other agent specific threats. TrustGate includes a catalogue of over 200 MCP connectors, letting teams integrate agents and tools quickly without custom work for each provider. Unlike closed, proprietary gateways, TrustGate gives teams full visibility into how their AI infrastructure works and the flexibility to adapt it to their own security and compliance requirements. It is built for enterprise scale, with the observability, governance, and reliability needed to run AI workloads in regulated industries like banking, aviation, and energy.

Open-source MoE AI video generation with cinematic control. Wan2.2 is the world's first open-source MoE (Mixture-of-Experts) video generation model developed by Alibaba Tongyi Lab. It enables users to create professional cinematic videos from text (text-to-video) or images (image-to-video) at 720P resolution with 24fps. Key features include advanced motion understanding, stable video synthesis, and fine-grained cinematic control over lighting, color, and composition. It is fully open-source with complete model weights, optimized for performance, and can run efficiently on consumer-grade GPUs.

Huawei's open-source AI framework for full-scenario deep learning. 昇思MindSpore is a full-scenario AI framework developed by Huawei. It is an open-source deep learning framework that supports automatic differentiation and parallel processing, enabling training once and deployment across multiple scenarios. It supports deep learning training and inference in edge, cloud, and device scenarios, and is mainly used in AI fields such as computer vision and natural language processing. It is designed for data scientists and algorithm engineers and features source code transformation-based automatic differentiation, automatic distributed parallel training, data processing, and a graph execution engine. The framework is open source, fostering an AI development ecosystem.

Cloud platform for open-source generative AI art and video tools. Think Diffusion is a cloud-based platform providing access to open-source generative AI tools like Stable Diffusion, ComfyUI, and more. It offers powerful cloud workspaces for AI art and video generation, accessible from any device with a browser. ThinkDiffusion also offers full-service AI art studio for brands, agencies, and universities.

Next-gen document intelligence with context optical compression and multilingual support. DeepSeek OCR is a two-stage transformer-based document AI system that utilizes context optical compression to deliver state-of-the-art document intelligence. It compresses high-resolution documents into lean vision tokens, then decodes them with a 3B-parameter mixture-of-experts model to achieve near-lossless text, layout, and diagram understanding across 100+ languages. It supports GPU-efficient throughput for complex layouts and is trained on 30 million real PDF pages plus synthetic data, preserving layout structure, tables, chemistry (SMILES strings), and geometry tasks.

Secure AI platform for companies, enabling compliant and managed AI integration. nele.ai is an AI platform designed for companies to integrate AI technologies like ChatGPT securely and in compliance with data protection regulations. It offers features for users to control communication with AI systems, manage prompts, and configure settings. For administrators, it provides tools for account setup, SSO with SAML 2.0, and access to AI models. It aims to combine user experience, security, management, and privacy in artificial intelligence.

AI-powered lead analytics and local AI knowledge base. Linkly.AI is an AI-powered lead analytics and management platform that helps you track, analyze, and streamline your leads in one place. It is also an open-source AI knowledge base that runs locally as a desktop application, allowing users to have AI conversations with documents stored on their personal computer, without limitations. It supports LLM services from any provider or local model deployments like Ollama. Users can find documents using vague descriptions and use DeepResearch tools to generate reports. It functions as an AI chatbot with an elegant interface, offering a free, open-source, and functional artificial intelligence second brain.

Access to DeepSeek R1, an open-source AI model for advanced reasoning. DeepSeek R1 Online is a platform providing access to the DeepSeek R1 AI model, an open-source AI model for advanced reasoning. It offers both free and no-login access. DeepSeek R1 is designed for complex problem-solving, multilingual understanding, and production-grade code generation. It utilizes a Mixture of Experts (MoE) architecture and advanced reinforcement learning techniques to achieve high performance in mathematics, coding, and general reasoning tasks. The platform also provides access to distilled versions of the model for various use cases.

AI code assistant for faster, safer coding with code completion and generation. Tabnine is an AI code assistant that helps developers write code faster and more safely in their favorite IDEs. It provides code completion, suggests full function completion based on function declaration, and generates blocks of code based on natural language comments. Tabnine adapts to your codebase, offering private, secure, and compliant AI assistance.

Open-source database for comparing AI models, providers, specifications, and pricing Models.dev is a comprehensive open-source database of AI model specifications, pricing, providers, capabilities, context limits, output limits, release dates, and update dates. It provides provider-agnostic model metadata, lists the providers serving each model, and organizes canonical models by laboratory or author. Users can compare models such as GPT-6 Astra across multiple providers, review features including reasoning, tool calling, structured output, temperature support, and weights availability, and access the data through JSON APIs or a type-safe SDK.

Browser-based hardware analyzer to check local AI model compatibility. CanIRun.ai is a specialized web-based tool designed to help users determine if their local machine's hardware is capable of running various AI models. By utilizing browser APIs like WebGPU, the site analyzes the user's GPU, CPU, and RAM to provide compatibility scores and VRAM requirements for a vast library of models including Llama, Qwen, DeepSeek, and Phi. It offers detailed technical breakdowns for each model, such as architecture type, context window, and memory requirements across different quantization levels (from Q2_K to F16).

Open-source vector database and search engine for similarity search in AI applications. Qdrant is an open-source vector database and vector search engine written in Rust. It provides fast and scalable vector similarity search service with convenient API. It blends vector similarity with custom logic using Score Boosting Reranker. Qdrant integrates with all leading embeddings and frameworks, turning embeddings or neural network encoders into full-fledged applications for matching, searching, recommending, and more.

AI-first automation platform; open-source alternative to Zapier and Workato for team workflows. Activepieces is an AI-first automation platform designed for every team, offering enterprise automation solutions and open-source business automation. It serves as an open-source alternative to Zapier and Workato, enabling users to build self-driven AI cultures across various departments like HR, finance, marketing, and sales, all under the supervision of IT professionals. The platform provides no-code automation, AI-assisted code, and collaboration features to empower teams and ensure governance and compliance.

All-in-one platform for AI development, from prototyping to production. Lightning AI is an all-in-one platform for AI development, offering tools to build models and full-stack AI applications quickly. It provides cloud GPUs, DevBoxes, training, deployment, and more with zero setup. From prototype to production AI, Lightning AI supports data platforms, training, GPU clusters, development, and deployment, enabling users to code together, prototype, train, scale, and serve AI models from their browser.

LiteLLM: LLM Gateway for managing and accessing 100+ LLMs in OpenAI format. LiteLLM is an LLM Gateway (OpenAI Proxy) designed to manage authentication, load balancing, and spend tracking across 100+ LLMs, all while maintaining the OpenAI format. It simplifies the process of using LLM APIs from various providers like OpenAI, Azure, Cohere, Anthropic, Replicate, and Google. LiteLLM offers consistent outputs and exceptions for all LLM APIs, along with logging and error tracking for all models. It provides features like cost tracking, batches API, guardrails, model access, budgets, LLM observability, rate limiting, prompt management, S3 logging, and pass-through endpoints.

A platform for fast inference of generative AI models, including fine-tuning and deployment. Fireworks AI is a platform designed to provide the fastest inference for generative AI models. It allows users to utilize state-of-the-art, open-source LLMs and image models at high speeds. Users can fine-tune and deploy their own models at no additional cost. The platform offers a range of tools and infrastructure to build and deploy generative AI applications, including model APIs, customization options, and compound AI systems.

Open-source AI platform for LLM chatbot management, observability, and evaluation. Lunary is an open-source observability and evaluation toolkit for AI developers, providing log queries and tools to improve app quality. It's an AI developer platform designed to manage and improve LLM chatbots, offering chatbot analytics, internal knowledge management, customer support solutions, and autonomous agent deployment.

Open-source autonomous observability tool that instruments code and automatically fixes bugs. Superlog is an open-source autonomous observability tool that automatically installs itself, instruments repositories with OpenTelemetry, and monitors codebases without manual setup or vendor lock-in. When anomalies or system failures occur, it fingerprints and groups noisy repeated logs into a single clear incident. It then performs a root-cause analysis, provides severity scores, assesses the impact, and creates automated resolution pull requests directly in Slack to help engineering teams fix bugs immediately.

Platform for creating, discovering, and chatting with virtual AI characters. Charstar is a platform where users can create, discover, and chat with virtual AI characters. It leverages the latest advancements in open-source AI to provide an unfiltered virtual character experience. Users can explore various characters, including NSFW options, and engage in conversations with them.

Web-based platform for software development and version control using Git. GitHub is a web-based platform and service that provides hosting for software development and version control using Git. It offers distributed version control and source code management (SCM) functionality of Git, plus adding its own features. It provides access control and several collaboration features such as bug tracking, feature requests, task management, and wikis for every project.

AI-powered tool for generating pixel art images with a prompt builder. Pixelfy is an open-source AI-powered tool that generates pixel art images. It includes an AI-powered prompt builder to simplify image generation. Users can start for free with 12 image generations.

SAM is a promptable AI segmentation system for zero-shot generalization to objects and images. Segment Anything (SAM) is a promptable segmentation system developed by Meta AI that offers zero-shot generalization to unfamiliar objects and images without requiring additional training. It allows users to "cut out" any object in any image with a single click. SAM uses a variety of input prompts to perform a wide range of segmentation tasks. The model was trained on millions of images and masks collected through a model-in-the-loop "data engine."

AI-powered betting strategy generator with analytics and predictions. Betsync is a fully open-source AI-powered answer engine with a generative UI designed to help users make smarter betting decisions. It provides live analytics, predictions, player profile spotlights, and AI-powered insights to generate betting strategies. The platform aims to reduce reliance on luck by offering advanced algorithms that analyze player performance and identify high-value betting opportunities. It also offers real-time stats and trend analysis to inform betting decisions.