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

Give any text-only LLM the power of vision instantly

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,

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

MediaPipe GenAI Tasks

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

Shared LLM generation policy for DeepSeek Harness session-title providers

LLM environment configuration — single source of truth for all LLM-related env vars and defaults

First-message LLM provider plugin for DeepSeek Harness session titles

Provider-neutral LLM service interface for the DeepSeek Harness


Detox driver for Wix Pilot usage

LLM integration plugin for PostGraphile v5 — server-side text-to-vector embedding and text companion fields for pgvector columns

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

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

Provider-routed LLM request retry policy for the DeepSeek Harness

General-purpose agent with transport abstraction, state management, and attachment support

TypeScript bridge for recursive-llm: Recursive Language Models for unbounded context processing with structured outputs

Display language model outputs in your React project.

Efficient, configurable text chunking utility for LLM vectorization. Returns rich chunk metadata.