Agents & Integrations
Autonomous API Keys
Mint API keys from a staked VVV wallet.
OpenClaw
Connect Venice to WhatsApp, Telegram, Discord, iMessage, Slack, and more.
Hermes Agent
Self-hosted agents with memory, skills, and Venice models.
NanoClaw
Lightweight WhatsApp and Telegram assistant powered by Venice.
Crypto RPC for Agents
Give agents inference and on-chain access through one credential.
x402 Wallet Auth
Let agents pay for Venice with Base or Solana USDC.
Jan AI
Use Venice models inside Jan’s local AI assistant.
Brave Leo
Connect Brave Leo to the Venice API for private, browser-native AI chat, page summaries, and optional web search.
Community projects
These community-built integrations make it easier to use the Venice API.llm-venice
Use Venice models through the
llm command-line tool.Unofficial PHP SDK for Venice
Call the Venice API from PHP with this community SDK.
Third-party compatible applications
JanitorAI
Third-party AI chat application compatible with Venice.
1Claw
Secure agent infrastructure that routes private inference to Venice through the Shroud TEE proxy.
Msty
Desktop AI client compatible with Venice.
Open WebUI
Self-hosted AI interface compatible with Venice.
LibreChat
Open-source AI chat interface compatible with Venice.
ScreenSnapAI
Screenshot-focused AI application compatible with Venice.
Coding Tools
Claude Code
Use Claude Code with Venice-hosted Claude models.
Cursor
Add Venice models to Cursor with the
venice- model prefix.Cline
Configure the Cline coding assistant in VS Code to use private Venice models through an OpenAI-compatible API provider.
Kilo Code
Use Venice through Kilo’s native provider in VS Code or the CLI.
OpenCode
Add Venice as an OpenAI-compatible custom provider.
Codex CLI
Point Codex CLI at Venice’s OpenAI-compatible endpoint.
Aider
Pair-program in your terminal with Venice via OpenAI-compatible settings.
Agent Tooling
Venice MCP Server
Expose chat, image, video, audio, music, embeddings, and more as MCP tools.
Venice Skills
Give agents endpoint-specific instructions synced to the API spec.
Video Harness
Use agent playbooks for repeatable Venice video production.
SDKs & Frameworks
LangChain
Build chains and agents on Venice models.
LlamaIndex
Build RAG pipelines, agents, and query engines with LlamaIndex using Venice’s private, OpenAI-compatible chat models and embeddings via the OpenAILike client.
Vercel AI SDK
Stream Venice models through the AI SDK.
Mastra
Build TypeScript AI agents, tools, and workflows with Mastra using Venice’s private, uncensored, OpenAI-compatible chat models as the LLM provider.
CrewAI
Run multi-agent crews with Venice as the model provider.
PydanticAI
Build typed Python agents with PydanticAI using Venice’s private, OpenAI-compatible chat models for tools, structured output, and streaming.
LiveKit Agents
Build realtime voice agents with LiveKit Agents and Venice, wiring Venice STT, LLM, and TTS through the OpenAI-compatible plugin in an STT-LLM-TTS pipeline.