Featured

Computer vision

New 2026

Local proxy that gives vision to text-only models (DeepSeek V4 Flash and any other). A vision model describes your screenshots — text, hex colors, layout — and forwards them as text to your main model. Works with Trae, Cursor, OpenCode, Codex, Claude Code and any OpenAI/Anthropic-compatible client. Dockerized.

New 2026

Open-source autonomous Tello drone interceptor using YOLO detection, Kalman tracking, visual servoing, target reacquisition, and safety-focused RC control.

New 2026

MCP server that gives text-only LLM coding agents vision — analyze images via any multimodal model (mimo, Claude, Gemini, OpenAI-compatible). Works with Claude Code, Codex, Kimi, opencode, PI.

New 2026

Unofficial phone-controlled spray-paint reveal and 3D web experiment

New 2026

CLI toolkit for AI agents — converts images into structured JSON evidence (OCR, layout, semantics), bridging the vision gap for text-only LLMs.

New 2026

n8n workflow: Telegram → GPT-4o Vision → Flux → WordPress. Publishes news articles with copyright-safe AI-generated featured images

New 2026

Give your self-hosted DeepSeek eyes 👀 — vision for DeepSeek-V4-Flash on 2× DGX Spark

New 2026

Codex skill for local MediaPipe hand tracking and AM-style double-sided vector video effects

New 2026

Explore computer vision one notebook at a time. GANs · Autoencoders · Style Transfer.

New 2026

DeepSight: vision-session proxy for text-only LLMs — sketch + targeted tool calls (look/zoom/ocr) with content-addressed caching. OpenAI-compatible.

New 2026

Give non-vision opencode models the ability to see images by routing them to a vision-capable model.

New 2026

Synesthesia Encoder (通感编码器) — give any text-only LLM (DeepSeek, etc.) the ability to see images via structured spatial text encoding. A Pi agent extension.

New 2026

An advanced Computer Vision & AI application in Python that allows you to play Subway Surfers by controlling your character directly with real-time body movements and hand gestures captured via your webcam.

New 2026

Give a text-only coding agent a pair of eyes. Portable Agent Skill that reads images through the Codex CLI.

New 2026

Agent skill: 本地 macOS OCR/classify/saliency via Apple Vision — 不上云、零费用、隐私安全

New 2026

High-fidelity, bare-metal industrial simulation environment written in Nim to generate Data Matrix (ECC200) datasets with real-world physical defects for YOLO-OBB training