Gives a text-only LLM vision capability

Give any text-only LLM the power of vision instantly

DeepSeek vision bridge for the dsh web GUI: route image attachments to a vision model (pi-ai / llama.cpp Qwen3-VL) and continue the conversation with the text description on a text-only LLM (DeepSeek)

OpenCode plugin: let a text-only LLM read browser screenshots via local Ollama with OpenCode Zen fallback.

Shared LLM utility library for text-only LLM calls across multiple providers

Give text-only LLM agents eyes: an MCP server + CLI that describes images through a vision-language model (VLM) API.

MCP server that gives any text-only LLM vision — image analysis, OCR, comparison, region zoom, and video frame analysis.

mm-vision (通感编码器) for DeepSeek Harness — give any text-only LLM the ability to see images via structured spatial text encoding. Registers the mm_vision tool.

Give text-only LLM coding agents (DeepSeek V4 Flash/Pro, Qwen, Kimi) vision via any multimodal model. One analyze_image tool — paste or drag in one or many images, analyzed in a single call, scoped to the current session. Works with Claude Code, opencode,

A generic MCP server that lets a text-only LLM agent 'see' images by sending them to any OpenAI-compatible multimodal model (e.g. gpt-4o, glm-4.6v, qwen-vl).

Shared LLM generation policy for DeepSeek Harness session-title providers

MediaPipe GenAI Tasks

Provider-neutral LLM service interface for the DeepSeek Harness

First-message LLM provider plugin for DeepSeek Harness session titles

Give your text-only LLM eyes: an MCP server that reads images via external OpenAI-compatible vision models (OpenAI, Qwen-VL, GLM, Gemini, Grok, Ollama...) with automatic provider fallback on rate-limit/errors.

Token-meter-driven compaction policy and LLM summarization backend for the DeepSeek Harness

Provider-routed LLM request retry policy for the DeepSeek Harness

DeepSeek account provider authentication and discovery

OpenTelemetry GenAI utility for standardized telemetry collection across LLM, Agent, Embedding, Tool, Retrieval, Rerank, Memory and more

Streaming colorization for Shiki, useful for highlighting LLM outputs and other text streams