I built Mix – an opensource, local agent for multimodal tasks
Mix is an open-source, local agent for multimodal claude code. Claude code users will feel at home. - Uses ffmpeg and local apps like blender instead of clunky cloud based editors - All project data is stored plain text and native media files - absolutely no lock-in. - The backend is an HTTP server, meaning that the frontend is just one of possible clients. - - Our SDK with stdio interface (similar to claude code SDK) is launching soon.
Does the same job
all alternatives →- MOMix – Open-source multimodal agents SDKOct 2025 · github.com · ▲6
Why we built it: • Claude Code: great for coding, but no video/audio support, localhost only • OpenAI SDK: single-model, no native multimedia tools • Both: no integrated DevTools for debugging agent reasoning So, we built Mix as an alternative for multimodal applications. • Native video/audio/PDF analysis tools (via Gemini for vision, Claude for reasoning) • Multi-model routing instead of single-provider lock-in • One-command Supabase setup for cloud deployment (vs localhost-only) • HTTP architecture that enables visual DevTools alongside agent workflows • Go backend: 50-80%…
- WBWe Built Mix, a Multimodal Agents SDKSep 2025 · github.com · ▲7
Mix is a multimodal agents SDK. It comes with a GUI playground for testing and debugging SDK workflows. • Built for multimodal workflows instead of code based workflows • The GUI playground is built from the typescript SDK • All project data is stored plain text and native media files - absolutely no lock-in. • The backend is an HTTP server, check out our python and typescript SDK's
- OAOpen-agent-SDK – Claude Code's internals, extracted and open-sourcedApr 2026 · github.com · ▲7
Claude Code's source map leaked last month. Instead of just reading it, I fed the entire source into Claude Code itself and asked it to extract the core agent loop logic. The result: open-agent-sdk — a drop-in replacement for claude-agent-sdk that's fully open source and doesn't spawn a CLI subprocess. Why this matters if you've built with claude-agent-sdk: claude-agent-sdk is just a thin wrapper around the Claude Code binary. It works, but it's a black box — when something breaks, you're stuck. Every query creates a new Claude Code process. That's fine on a laptop, not fine when you're…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, August 2025
the whole month →
- IS
I built the world's most impractical 1000-pixel display and anyone in the world can draw on it. It draws a single pixel at a time and takes 30-60 minutes to complete a single image. Anyone can participate in the project by voting for the next image to be drawn, and submitting images. https://kilopx.com/
Work · 2025 · benholmen.com
- KT
Kitten TTS is an open-source series of tiny and expressive text-to-speech models for on-device applications. We are excited to launch a preview of our smallest model, which is less than 25 MB. This model has 15M parameters. This release supports English text-to-speech applications in eight voices: four male and four female. The model is quantized to int8 + fp16, and it uses onnx for runtime. The model is designed to run literally anywhere eg. raspberry pi, low-end smartphones, wearables, browsers etc. No GPU required! We're releasing this to give early users a sense of the latency and voices…
Dev tools · 2025 · github.com
- IW
I was wondering how I can arrange objects along a spherical helix path, and read some articles on it. I ended up learning about parametric equations again, and make this visualization to document what I learned: https://visualrambling.space/moving-objects-in-3d/ feel free to visit and let me know what you think!
Life & fun · 2025 · visualrambling.space
- TC
For HTML Day 2025 [1], I made a web service that displays the current sky at your approximate location as a CSS gradient. Colours are simulated on-demand using atmospheric absorption and scattering coefficients. Updates every minute, without the use of client-side JavaScript. Source code and additional information is available on GitHub: https://github.com/dnlzro/horizon [1] https://html.energy/html-day/2025/index.html
Dev tools · 2025 · sky.dlazaro.ca