Mike Hutu

2/2 For anyone tired of brittle OCR pipelines, this is a game‑changer – the model ingests the image and produces structured text in one go. github.com/X-PLUG/mPLUG-D…

🧵 1/2 The new mPLUG‑DocOwl repo is turning heads: a modular multimodal LLM that reads PDFs, scans, and charts without any OCR pre‑step. The codebase is pure Python, Apache‑2.0, and already has 2,378 stars on GitHub.

2/2 No more cobbling together fragile pipelines or paying for custom training—just pull the repo, load the model, and you’re ready for Mandarin, regional dialects, English, and even karaoke‑style input. github.com/FireRedTeam/Fi…

🧵 1/2 The FireRedTeam just dropped FireRedASR, an Apache‑2.0 Python stack that hits SOTA on public Mandarin benchmarks and, weirdly enough, can transcribe singing lyrics.

2/2 Drop in your model, pick your target (GPU, VPU, CPU) and the code swaps the right runtime under the hood. No more per‑backend forks, no more mysterious crashes. github.com/ankandrew/fast

🧵 1/2 Tired of juggling TensorRT, OpenVINO, and custom ONNX tweaks just to read a license plate? A new open‑source repo bundles a fully‑customizable ONNX pipeline that abstracts away the backend pain.

2/2 The new ai‑performance‑engineering repo from cfregly does the heavy lifting automatically – it profiles, rewrites, and tunes kernels on the fly, delivering reproducible speedups across both training and inference. github.com/cfregly/ai-per…

🧵 1/2 If you’re still hand‑crafting CUDA kernels to squeeze out a few percent on PyTorch, you’ve just wasted a lot of time.

2/2 No more manual prompt engineering—just type a comment, watch the code appear. github.com/breschio/drawb…

🧵 1/2 Ever wish you could skip the copy‑paste dance between design notes and LLM prompts? Drawbridge does exactly that. It watches your browser UI comments, turns them into Claude Code prompts on the fly, and feeds them straight into your coding agent.

2/2 No more Python loops, no more waiting for hours – you get results in seconds, and you can iterate fast enough to stay ahead of the curve. github.com/polakowo/vecto…

🧵 1/2 If you’re still looping over each strategy one‑by‑one, you’re losing money before the market even opens. The new vectorbt engine lets you backtest thousands of ideas in a single pass, thanks to pure‑NumPy vectorization.

2/2 The new getAsterisk/claudia repo flips the script: a dedicated GUI plus a pluggable agent framework that lets you spin up Claude sessions, swap providers, and keep your workflow in one place. github.com/getAsterisk/cl…

🧵 1/2 If you’re still juggling copy‑paste, fragile CLI flags, and manual session juggling to run Claude Code, you’re not alone.

2/2 No data ever leaves your network, which means zero leakage risk and near‑zero latency for fast‑moving teams. github.com/Zackriya-Solut…

🧵 1/2 If you’ve ever cringed at sending raw audio to a cloud service, you’ll love what Zackriya‑Solutions just shipped. Their new "meeting‑minutes" repo runs entirely locally: capture, transcribe, diarize speakers, and summarize—all on‑device.

3/3 github.com/hehehai/voxt

2/3 The repo just hit v1.11.0 (released May 8) and already boasts 584 ⭐ on GitHub, 43 forks, and a clean NOASSERTION license. It’s pure Swift, so you can drop it into your own workflow or fork it for custom models without wrestling with heavy dependencies.

🧵 1/3 Developers, meet Voxt – a Swift menu‑bar app that captures your spoken words, runs a rule‑based AI transcription, and drops the translated result straight onto the clipboard. No more copy‑paste‑fix loops when you need multilingual input on the fly. 🎤

2/2 3,621 github stars, 494 forks, mit license, javascript. the repo ships an op cli, not just a browser demo. github.com/badrisnarayana…

🧵 1/2 antigravity-claude-proxy: an open-source proxy that exposes antigravity provided claude / gemini models, so we can use them in claude code and openclaw (clawdbot).