Keyword: multimodal
- trvl-mcpReleased14h agoVersion1.18.0
Travel MCP server + CLI for flights, hotels, trains, cars, ferries, and door-to-door multimodal trips — no API keys required, single Go binary, works with any MCP client (Claude, Cursor, Windsurf, Codex). 1 smart travel MCP tool, natural language; legacy
- @hmanlab/hl-pluginsReleased2d agoVersion0.5.3
One-command installer for curated OpenCode plugins. Adds image, video, music, and speech generation to your coding agent without leaving the chat. MIT, no telemetry.
- @neta-art/generationReleased2h agoVersion0.1.10
A lightweight multimodal generation SDK with built-in model presets and adapter-based provider calls.
- @sogni-ai/sogni-clientReleasedyesterdayVersion5.0.0
Sogni SDK - AI image, video & audio generation plus LLM chat with vision via the Sogni Supernet (Stable Diffusion, Flux, WAN 2.2, LTX-2, Seedance, Qwen VLM)
- @fre4x/geminiReleasedyesterdayVersion1.1.6
A Gemini MCP server providing multimodal analysis and image/video generation.
- @space3-npm/cybersoul-clientReleased5d agoVersion1.4.29
Cyber-Soul multimodal character interaction SDK by Space3 Digital Media Tech Studio
- opencode-multimodalReleased4d agoVersion0.1.6
Give every opencode model multimodal capabilities by routing attachments to a fallback multimodal model. Configure everything via the /multimodal command.
- otto-agent-cliReleased3d agoVersion3.260626.2
The first multimodal, multi-model AI coding agent for your terminal — pair Claude + Codex on every turn and take the same session to WhatsApp or Telegram. Local-first and open source.
- @mixpeek/n8n-nodes-mixpeekReleased4d agoVersion1.0.27
n8n community node for Mixpeek - multimodal data processing and semantic search API
- pi-vision-toolReleased6d agoVersion1.3.7
Pi Agent extension that adds a describe_image tool, letting non-multimodal models delegate image analysis to a vision-capable model (like Qwen VL)
- @joezm/seed-vizReleasedyesterdayVersion0.3.0
Vision analysis CLI + MCP server backed by Seed 2.0 via Volcano Ark or any OpenAI-compatible endpoint
- n8n-nodes-openrouter-cleanReleasedyesterdayVersion1.0.3
n8n community nodes for OpenRouter — full API support including reasoning control, multimodal content (images, video URLs), provider preferences, plugins (web search, web fetch), structured outputs, TTS, STT, and model listing.
- n8n-nodes-siliconflow-aiReleased1h agoVersion0.6.0
n8n community node for SiliconFlow (硅基流动). Zero runtime dependencies. Provides a SiliconFlow action node (Chat / Vision / Embeddings / Image / Rerank / Audio TTS+ASR / Video) and a LangChain-compatible Chat Model node for AI Agents. Installs cleanly witho
- visual-explanation-engineReleasedyesterdayVersion0.1.1
A Codex skill that turns explanations into visual, interactive, multimodal learning experiences.
- @miragari/ai-media-routerReleased3d agoVersion0.2.1
Unified AI media generation SDK with built-in providers and one API for image, video, audio, and 3D workflows.
- @llm-ports/adapter-googleReleased4d agoVersion0.1.0-alpha.24
Google Gemini adapter for llm-ports — native @google/genai SDK integration with bundled pricing, content-block translation, validation repair, and image-size + URL validation.
- @mastra/voyageaiReleased2d agoVersion0.3.0
VoyageAI embeddings integration for Mastra - text, multimodal, and contextualized chunk embeddings
- openaijsonwrapperReleased5d agoVersion0.2.1
JSON wrapper for OpenAI-style multi-modal API with structured output
- @smoose/pi-visionReleased5d agoVersion0.1.2
Pi image recognition tool: lets text-only models see images via local CLI providers (Codex or Agy).
- @ajmalaksar/multimodal-mcpReleased4d agoVersion0.1.5
MCP server and CLI exposing Google's multimodal models (Gemini AI Studio and Vertex AI) for image, video, and audio analysis plus image generation — for Claude Code and other agents.