Google DeepMind's TapNet Unifies Seven Video Tracking Models in One Repo
Google DeepMind's TAPNet repository bundles every generation of their point tracker, from TAP-Net to TAPNext++, in one open-source hub.
A focused feed of models, agents, research and open-source releases for people building with AI.
Google DeepMind's TAPNet repository bundles every generation of their point tracker, from TAP-Net to TAPNext++, in one open-source hub.
A free, open-source Mac app uses Google DeepMind's new multimodal embedding model to search inside photos, PDFs, audio, video and code locally.

Intfloat posted a deprecation notice on the original E5-base embedding model, telling users to migrate to E5-base-v2 for better performance.

Anthropic's free, nine-chapter prompt engineering course on GitHub has crossed 38,000 stars, offering hands-on Jupyter notebooks with graded exercises against the Claude API.

A C++ port with pre-quantized GGUF weights brings the ACE-Step 1.5 music foundation model to CPU, CUDA, Metal and Vulkan backends.
An open-source LangGraph agent swarm runs full red-team kill chains inside a Kali sandbox, scoring 98% on XBOW's validation benchmarks.

Anthropic opened OSS Scanner, a free opt-in service that runs its strongest models against critical open-source repos and emails raw, unreviewed vulnerability reports to maintainers.

nanoMuse is an open-source cross-device personal agent that runs on your phone and computer, with built-in approvals before any irreversible action.

A 7.89 GB IQ2 quant of Qwen3.8-27B that beats the full 54 GB model on tool-calling benchmarks while fitting on consumer GPUs.

ARTEX, winner of Baidu's agent+ challenge, open sources a Go-based multi-agent pentest system built on a dual-graph architecture.

Helix Foundry lets you wire databases, SaaS tools, and files into a single company ontology that runs entirely on your laptop.

vLLM lands day-0 support for NVIDIA Vera Rubin NVL72 with Rubin-tuned kernels and locality-aware MoE, hitting 7.8x the per-GPU throughput of GB200.

A Chinese open-source infinite canvas workbench stitches scripts, characters, storyboards, and multimodal generation into a single node-based workflow for AI film production.

REA ships a local MCP server that lets coding agents decompile, trace and reconstruct features from binaries, Electron apps and websites.

A viral open-source project turns your Claude Max API credits into a daily AI-generated Chrome new tab page built from your browser history.

Umi-OCR crosses 47k stars offering a free, fully offline OCR toolkit with screenshot capture, batch jobs, PDF extraction, and an HTTP API.

A new method aligns vision and language embedding spaces using geometry alone, with zero image-caption pairs, hitting near-perfect retrieval on COCO.

A one-click Qwen3.8-27B serving kit for consumer NVIDIA cards gets a speedup, with code generation jumping from 180 to 275 tok/s on an RTX 5090.

HiDream's new omnimodal video model lands at #6 on the Artificial Analysis I2V with Audio leaderboard, generating 1080p clips with synchronized audio at $5.80 per minute.

Anthropic details four categories of unintended Claude behaviors during evaluations, from SQL injection to submitting a tip to a police homicide form.

A community 4-bit AWQ build of Qwen2.5-Coder-7B-Instruct is pulling in three quarters of a million downloads, shrinking the model to under 6GB of VRAM.

Prime Intellect unleashed 2,000+ agents to port Prime Agent from TypeScript to Rust, hitting 13x faster startup and 83% less memory.

Parallel Web Systems' latest Search Capability Leaderboard puts Anthropic's new Haiku 5.5 at the top for cost-per-task, 39 times cheaper than Opus 5.5.

StepFun's 600B/27B mixture of experts model is free on Nous Portal for a week, scoring in GPT-6 Luna territory on agent benchmarks.
No stories match these filters.