A focused feed of models, agents, research and open-source releases for people building with AI.
A new divisive clustering algorithm chops up mutual reachability spanning trees to detect clusters of varying densities, shapes, and sizes while beating HDBSCAN and Genie on benchmarks.
Tencent Hunyuan open-sourced Hy-Nomas , an 8B interactive video world model under Apache 2.0. Supports free-form multi-turn text prompts and continuous camera control across autoregressive video segments. Outputs 720p at 24 fps, up to 60 seconds, distilled to eight denoising steps.
A Rust-based agentic operating system where agents rewrite their own harness mid-task, built atop Codex with a 45k-line kernel.
Tencent open-sourced a 30B MoE model for live Chinese-English speech interpretation, hitting roughly 3-second latency with real-time voice cloning.
Pomerado, a YC F26 startup, open-sources an MIT-licensed harness that mints deterministic MCP integrations for any website, including sites behind logins and 2FA.
Slotstream streams a 125B mixture-of-experts model from SSD on Apple Silicon, letting 16 to 64 GB Macs run a 105 GB model locally.
A community photorealism checkpoint built on SDXL crosses 859k downloads, delivering lifelike portraits and scenes without a custom pipeline.
Nous Research consolidates eighteen first-party Hermes Agent plugins into a single repo, each one install away from the plugin catalog.
CopilotKit's OpenMuse ships an MIT-licensed personal agent template with a persistent browser, Linux terminal, Gmail integration, and durable task plans.
Pi Pocket turns the Pi coding agent into a phone-friendly, multiplayer web app with durable sessions that survive server restarts mid-run.
DeepBeepMeep's repack of MiniMax's open-weight H3 video+audio model lands with GGUF quants and new 3-step accelerator LoRAs that make it run on modest GPUs.
NVIDIA's new 30B hybrid Mamba-Transformer MoE activates just 3B parameters, runs on a single H100, and handles up to 1M tokens of context.
InclusionAI drops five Ming-3.0 speech models under MIT, led by a 7.9B MoE TTS that tops open-weight controlled voice leaderboards.
Black Forest Labs' smallest Flux.2 model lands in ComfyUI as a single 7.75GB file, generating images in under a second on an RTX 3090.
Comfy-Org bundles FLUX.1-dev and its control variants into single-file safetensors with built-in text encoders, cutting setup friction for ComfyUI users under 24GB VRAM.
Huihui-ai ships uncensored GGUF builds of DeepSeek V4.1 Flash 1017, including sub-2-bit Strata quantizations that make a 763B MoE runnable from an SSD.
Black Forest Labs' 32B open-weight image model lands in ComfyUI with FP8 weights, a 24B Mistral text encoder, and 10-image multi-reference editing.
vLLM matches DeepSeek's own inference engine on V4.1-Flash and scales to 954K tokens/s per GPU on a GB300 NVL72 rack.
Comfy-Org's drop-in bundle of repackaged Qwen-Image-Edit checkpoints for ComfyUI crossed 1.68M downloads, now covering the 2511 refresh and five LoRAs.
A community-published merge for MiniMax-H3's Ref2VA video model uses SVD denoising and geodesic interpolation to fuse a quality finetune with an 8-step turbo variant.
Comfy-Org has published a repackaged archive of Stable Diffusion v1.5 on Hugging Face, preserving the original weights after RunwayML pulled its page.
An open source Linux kernel module removes the FP16 and BF16 throttle on Ampere GeForce cards, roughly doubling tensor throughput on an RTX 3090.
Comfy-Org maintains drop-in single-file safetensors for Alibaba's Qwen-Image family, bundling the base model, the 2512 refresh, and a distilled variant for ComfyUI.
Black Forest Labs drops a 5.6B open-weights image model that runs on 8GB VRAM, tops open benchmarks, and generates 1MP images in 4 seconds.
No stories match these filters.
