Cloud platform to deploy, test, evaluate and monitor MCP servers and MCP Apps for ChatGPT and Claude, built by the team behind the MIT-licensed mcp-use framework.
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
- 109
- related topics
- 5
Explore products109
Showing 1–24 of 109 projects
Cloud sandboxes (Devboxes) for AI coding agents with blueprints, snapshots that can be branched, repo connections and agent, object and secret stores, on x86 and arm64.
Open-source, Kubernetes-native stack for distributed LLM inference that runs vLLM, SGLang and other engines across a cluster with prefix-cache-aware routing, prefill/decode disaggregation, wide expert parallelism and autoscaling.
Computer vision platform for labeling image datasets, training detection and segmentation models, and deploying them to a hosted API or edge devices.
Multimodal data platform for annotating, curating and evaluating training data for computer vision, physical AI and LLM teams.
GPU marketplace where independent hosts and data centers rent out GPUs, with on-demand, interruptible and reserved instances, serverless endpoints and clusters controlled from a console, CLI, Python SDK or REST API.
Inference API for coding agents with specialized models: Fast Apply to merge LLM code edits into files, WarpGrep agentic code search, verbatim context compaction and a difficulty-based model router, plus hosted open-weight models.
GPU cloud offering self-serve NVIDIA B200, H100, A100 and GH200 instances, reservable 1-Click Clusters of 16 to 2,000+ GPUs, and larger private superclusters for training and inference.
Inference cloud for open models with an OpenAI-compatible API, offering per-token serverless endpoints, elastic endpoints, dedicated GPU deployments and discounted batch jobs.
An open-source platform for training, evaluating and deploying custom language models, with a hosted platform that automates data synthesis, fine-tuning and deployment.
SambaCloud is SambaNova's inference API for large open models such as DeepSeek, MiniMax, Gemma and gpt-oss, served on the company's own RDU chips through OpenAI-compatible and Anthropic Messages API endpoints.
Hugging Face's Python library for post-training transformer language models with SFT, GRPO, DPO, reward modelling and related trainers.
A memory API for AI agents and apps that extracts facts and user profiles from chats, files and URLs, stores them in a vector-graph database and injects relevant memories back into the model context.
Cloud infrastructure for AI agents that gives each agent an isolated microVM sandbox which suspends when idle and resumes in about 25 ms, plus batch jobs, MCP server hosting, persistent storage and egress controls.
An open-source GPU cluster manager that deploys models on vLLM, SGLang, TensorRT-LLM or other engines and serves them through OpenAI- and Anthropic-compatible APIs.
An open-source orchestration layer that provisions GPU fleets and runs training jobs, dev environments and inference services on GPU clouds, Kubernetes, VMs or bare-metal servers.
AI cloud for renting NVIDIA H100, H200, B200 and B300 GPUs on demand or reserved, with managed Kubernetes and a pay-per-token OpenAI-compatible API for open text models.
A serverless cloud for AI agents and GPU workloads that offers pausable microVMs, sandboxes for untrusted code, autoscaling GPU inference endpoints and task queues, driven from a Python SDK, CLI or MCP server.
Python framework, powered by a Rust engine, for building streaming ETL, real-time analytics and live LLM/RAG pipelines that stay in sync with 300+ data sources.
SIE (Superlinked Inference Engine), an open-source server and hosted API that runs small open models for embeddings, reranking, OCR, extraction, classification, guardrails and chat behind one API.
A memory operating system from MemTensor that gives LLM apps and agents long-term memory through a hosted cloud API, an open-source framework, a local-only Lite version and agent plugins.
An open-source system for running and managing AI training, inference and batch jobs across Kubernetes, Slurm, on-prem machines and more than 20 clouds from one interface, with a managed SkyPilot Platform for teams.
The maker of the Ultralytics YOLO computer-vision models and Python package for object detection, segmentation, classification, pose estimation and tracking, plus a hosted platform for annotating data, training on cloud GPUs and deploying models.
Open-source orchestration engine for background tasks, AI agents and durable workflows, with retries, scheduling, rate limits and built-in observability.