Excited to share that mm-ctx is now live on @huggingface Spaces! Try it in the browser via an interactive terminal without installing anything: vlm-run-mm-ctx.hf.space mm-ctx – fast, multimodal context for agents. LLM-based agents handle text fine, but as soon as a directory contains images, videos, or PDFs with visual content, they struggle to understand the full context. mm-ctx is meant to feel familiar: the Unix tools we already love (find/cat/grep/wc), rebuilt for file types LLMs can't read natively and designed to work with agents via the CLI. - mm grep "invoice #1234" ~/Downloads searches across PDFs and returns line-numbered matches - mm cat <document>.pdf returns a metadata description of the file - mm cat <photo>.jpg returns a caption of the photo - mm cat <video>.mp4 returns a caption of the video A few things we obsessed over: ⚡ Speed: Rust core for the hot paths 🏠 Local-first, BYO model: Uses any OpenAI-compatible endpoint: Ollama, vLLM/SGLang, LMStudio with any multimodal LLM (Gemma4, Qwen3.5, GLM-4.6V). 🔗 Composable: stdin + structured outputs 🤖 Drops into any agent via mm-cli-skills: Claude Code, Codex, Gemini CLI, OpenClaw. We’d love to hear your feedback! Especially on the CLI and what file types and workflows you would like to see next.

New Publication Alert Accepted at WACV'26- From Lightweight CNNs to SpikeNets: Benchmarking Accuracy-Energy Tradeoffs with Pruned Spiking SqueezeNet

Virtual Try-On is getting scary good... I think I just found my new favorite tool 📷 I was experimenting with VLM Run today to see if I could virtually "try on" a dress from a product photo onto an existing picture. Is this the future of online shopping?

AI can produce cute videos, commercials...Damn!!!

Amazing to see how (chat.vlm.run) is transforming advertisement industry.

Bring image to life using (chat.vlm.run). It doesn't just "see" video, it understands texture, movement, and minute details at a granular level.

Been testing tons of CV tools (Roboflow, SuperAnnotate, HF Spaces, etc.), but VLM Run (vlm.run) genuinely surprised me. Their new chat feature turned a simple factory blueprint into a full, realistic manufacturing workflow. Vision-driven execution at its best.