
Meta's TRIBE v2 Builds a Digital Twin of the Human Brain
Meta FAIR open-sources a transformer that maps video, audio, and text onto whole-brain fMRI responses across 720 subjects with several-fold accuracy gains.
20 stories

Meta FAIR open-sources a transformer that maps video, audio, and text onto whole-brain fMRI responses across 720 subjects with several-fold accuracy gains.

TinyAGI turns Claude Code and Codex CLIs into a 24/7 team of specialized agents that hand off work through a SQLite queue.

An open-source Telegram bot wires Claude Code into your chat app, letting you edit repos, run tests, and receive webhook alerts from your phone.

A scoping review finds just 12 studies applying LLMs to rare disease patient communication, revealing a field dominated by ChatGPT question-answering with critical gaps.
INSID3 uses a single frozen DINOv3 backbone to segment any object from one example, with no training, no SAM, and no decoder — beating prior work by 7.5% mIoU

Picobot is a full-featured AI agent that runs as a single 9MB Go binary — no Python, no Node, no bloat — on any hardware from a $5 VPS to a Raspberry Pi.

Peekaboo turns your Mac into a controllable target for AI agents, combining screen capture, accessibility inspection, and native UI automation behind an MCP server.

Rethinking the goodness function turns Hinton's Forward-Forward algorithm from a curiosity into something that nearly matches backprop on MNIST.
A community vLLM integration of Google's ICLR 2026 paper cuts KV cache memory in half, doubling effective context on consumer GPUs with no retraining required.

Onyx v4.5.0 lands with SSO-only login, per-chat reasoning controls, a Box connector, native Azure Blob storage, and big latency wins.

A minimalist framework that fits its entire core in 100 lines of Python, betting that graph abstractions beat vendor wrappers for building agents.

TrustGraph 2.6 ships FlashRank cross-encoder reranking, portable workspace bundles, and fine-grained enterprise IAM for graph-native agent memory

ZhuLinsen's open-source daily_stock_analysis brings LLM-powered A/H/US stock decision dashboards to anyone with a GitHub account, at zero infrastructure cost.

Deep-Live-Cam hits 83K GitHub stars: one photo is now all it takes to swap your face in real time on any webcam or video stream

A PreToolUse hook that parses command intent before letting your AI agent run it, blocking rm -rf, git reset --hard, and secret file reads across 12 coding CLIs.

Datawhale's Hello-Agents hits 31K GitHub stars with a free, 16-chapter curriculum for building AI-native agents from scratch — including a custom framework, Agentic RL, and multi-agent protocols.
G0DM0D3 is a single-file, open-source interface that races 50+ AI models in parallel with built-in red-teaming and jailbreak research tools
Meta's SAM 3.1 adds Object Multiplex, a shared-memory tracking design that hits 7x faster inference on 128 objects without losing accuracy.

Google's Gemma 4 E2B ships in LiteRT-LM format with mixed 2/4/8-bit quantization, hitting 91 tokens per second on phones with speculative decoding.

Paper2Code's open-source PaperCoder system turns any ML paper PDF into a runnable code repository using a three-stage multi-agent pipeline, for under $1 per paper.