A desktop, mobile and web app for chatting with GPT, Claude, Gemini, DeepSeek and other models using your own API keys or hosted plans.
CATEGORY
SDK & Integrations
Connect AI applications to the services and tools they need. Explore SDKs and integrations for adding model capabilities and external actions.
- products
- 38
- related topics
- 5
Explore products38
Showing 1–24 of 38 projects
A free, open-source tool for fine-tuning open models such as Llama, Qwen, Gemma and Mistral from configuration files.
A reactive, open-source Python notebook stored as plain Python files, with built-in SQL and AI assistance, that can run as a script or deploy as an app.
A desktop AI app for chatting with local and online models side by side, with workspaces, personas and knowledge stacks.
An open-source serving framework for fast inference of large language and multimodal models on NVIDIA, AMD, TPU and other hardware.
A private AI workspace that runs on your device, with chat over your documents and agents, plus a self-hosted or hosted team version.
A free, open-source AI desktop client for Windows, macOS and Linux with chat, agents, image generation and a knowledge base, storing data locally.
An open-source, self-hosted AI chat platform that brings many model providers, agents and tools into one interface; part of ClickHouse since 2025.
A high-throughput, memory-efficient open-source engine for serving large language models.
An open-source C/C++ engine for running language models locally on CPUs and GPUs, and the basis of many local AI apps.
Open-source tools for fine-tuning and running open models faster with less GPU memory, plus a local Studio app.
Enterprise AI models for generation, embeddings, reranking and speech, plus North, a secure workspace for agents and search.
Google Cloud's platform for building, scaling, governing and optimizing agents and AI applications, formerly Vertex AI.
Microsoft's platform for building AI apps and agents with Azure OpenAI and other models, formerly Azure AI Foundry.
AWS's platform for building generative AI applications and agents with foundation models from several providers.
A cloud for AI developers with on-demand GPUs and serverless compute for training, inference and batch jobs.
Cloudflare's serverless inference for running open models on GPUs across its global network, from Workers or a REST API.
An inference platform for serving open-source and custom models in production, with per-token Model APIs and dedicated GPU deployments.
A cloud API for running open-source and custom machine learning models, now part of Cloudflare.
A platform for stateful agents with long-term memory that learn and improve over time, from the team behind MemGPT.
An AI cloud for running open models through serverless APIs, dedicated endpoints, fine-tuning and GPU clusters.
A free, open-source desktop app for chatting with local open models or cloud models, with MCP connectors and a local API server.
Serverless cloud infrastructure for running AI inference, training, sandboxes and batch jobs from Python code, billed per second.
A training and inference platform for open models, with serverless per-token APIs, fine-tuning and on-demand GPU deployments.