AI & machine learning

AI agents: manage skills, library syncs, credentials, chats, billing and integration access

Generation: run AI recipes, workflows, blobs, funds and free-tier quota on Civitai's orchestrator

Agent runtime: run long-lived agents, sessions, tasks, files, memory and channels over HTTP

Rights clearance for AI agents: check licenses, issue signed receipts, register agents and hire them

Chat workspaces: manage threads, models, knowledge bases, skills, teams, users and subscriptions

LLM evaluation: manage experiments, datasets, prompts, logs, and project access controls

Agent memory: store sessions, messages and peer conclusions, query them and chat with peers

GenAI platform: build agents, knowledge bases, evals, and trace/log analytics for LLM apps

AI model gateway: chat, embeddings, images, audio, video, batches and files via OpenAI- and Anthropic-style endpoints

Agent platform: run threads, Captains, issues, projects and automation batches

AI agents: manage agent workspaces, tools, scheduled tasks and conversation invocations

AI image, video, 3D and audio generation: create media, upload assets, train styles, run node apps

Voice AI agents: create agents, place calls, manage voices, corpora and SIP telephony

LLM evaluation: log traces, run experiments, manage datasets, scorers, annotation queues and alerts

Hosted AI gateway: proxy OpenAI and Anthropic models, store files, run agents and manage auth

Cloud infrastructure simulation: run, optimize and explain cloud deployments, plus RL training environments

LLM gateway: chat, embeddings, images, audio, video, plus API keys, batches and credits

Agents and cloud computers: run sessions, Droid turns, environments, CI automations and wiki runs

Metered pay-per-request access to blockchain RPC, web search, screening, health, and document APIs

AI gateway: chat, image, embedding and model APIs, plus agents, workflows, knowledge bases and billing

AI agents: launch agents, handle approvals and questions, and stream their event timelines

Search inference: run encode, score, extract and generate models, plus embeddings and transcription

AI models: chat completions, speech, transcription, translation, images and poems via API

AI governance: manage models, risks, policies, approvals, audits and AI app inventory