Results for “self-hosted”

161 tools in this category · Updated 2 Nov 2026

“self-hosted”CodingSign up onlineShowing 161 tools

Steelby SteelCloud browser sessions for AI agents, with an open-source self-hosted option.Pay as you go
Agnoby AgnoPlatform for building, running and managing self-hosted AI agentsFreemium
SurrealDB MCP Serverby SurrealDBHosted MCP server connecting AI assistants to SurrealDB CloudFreemium
Browserlessby BrowserlessHosted managed browsers and an MCP server that give AI agents a real Chrome session.Freemium
Wallyby RunAnywhereYC W26Hosted open models behind one OpenAI-compatible API and a CLI for coding agentsPay as you go
Netlify AI Gatewayby NetlifyNetlify's built-in gateway for calling commercial and open AI models from Netlify-hosted projects.Freemium
SambaCloudby SambaNovaHosted inference API for large open-source models on SambaNova RDU hardwarePay as you go
Syntheticby SyntheticHosted access to open-source language models through a web app and compatible APIs.$9+/mo
Novita AIby NovitaAIHosted model APIs, GPU infrastructure and agent sandboxes on one platformPay as you go
SiliconFlowby SiliconFlowHosted inference API for open and commercial LLM and multimodal modelsPay as you go
Prime Intellectby Prime IntellectTrain, evaluate, and serve your own AI models on hosted RL infrastructureUnknown
Parasailby ParasailHosted inference for open and frontier models via one OpenAI-compatible APIPay as you go
DeepInfraby DeepInfraPay-per-token inference API for open-source and hosted AI modelsPay as you go
Basetenby BasetenHosted model APIs and dedicated GPU inference for production AI appsPay as you go
Base44by WixDescribe an app, website or agent in plain language and get it built and hosted.Freemium
CoreWeave Serverless RLby CoreWeaveManaged reinforcement learning training for LLM agents, with trained checkpoints hosted for inference.Unknown
Nebius Token Factoryby Nebius GroupHosted inference API for open LLMs, with playground, fine-tuning, and framework integrations.Pay as you go
Azure OpenAI in Foundry Modelsby MicrosoftAzure-hosted access to OpenAI models for building apps and agentsPay as you go
Crusoe Managed Inferenceby CrusoeManaged inference for open models with serverless, self-serve, and tailored deployment optionsPay as you go
Cerebras Inferenceby Cerebras SystemsHosted inference API for running open-weight language models on Cerebras hardware.Pay as you go
Emergentby EmergentYC S24Describe an app in conversation and get a generated, hosted web or mobile product.Freemium
Comfy Deployby Comfy DeployYC S24Hosted ComfyUI workflows, shareable with teams and deployable as APIsUnknown
RunAnywhereby RunAnywhereYC W26Hosted open models behind one OpenAI-compatible API key and CLIPay as you go
Tabstackby MozillaAdd web research, extraction and browser actions to AI applicationsPaid