Point at a lamp. It turns on. Point at the TV. It changes the channel. No remote, no voice, no cloud. Project GAIUS by @KatusDavid: multi-camera 3D triangulation, arm raycasting, gesture recognition on Metis M.2. Fully offline, fully open source. Code + docs:
https://eu1.hubs.ly/H0vmv_j0
OPEN SOURCE
-
Project GAIUS: Gesture Control Without the Cloud
By
–
-
Challenges in building agent-as-a-service platforms on OpenClaw
By
–
our full deep-dive on trying to launch an agent-as-a-service platform built on openclaw! my two bigs ones: 1. OpenClaw is awesome but it's EXTREMELY hard to build on it as a platform. it moves super fast, there are tons of regressions, it's not great to be the layer in between
-
Tolaria: LLM Wiki as a Mac App
By
–
@Karpathy
's LLM wiki concept just became a real Mac app. It is called Tolaria, a free desktop app for Mac and Linux. The goal is simple: give humans and AI agents a shared, native environment to build knowledge. It writes like a modern block editor, but saves everything as -
Supertonic: High-Speed Open-Source On-Device TTS Engine
By
–
this TTS model generates speech 167x faster than you can hear it. Supertonic is an on-device TTS engine that runs via ONNX for cross-platform inference. – no GPU
– 31 languages
– captures every emotion
– beats ElevenLabs on speed
– runs even on a Raspberry Pi 100% open-source. -
CodexBar 0.26.0 introduces Kiro, Antigravity, OpenRouter, Kimi and improvements
By
–
CodexBar 0.26.0 is live Kiro, Antigravity, OpenRouter, Kimi calmer menus + keyboard nav better Codex/Claude limits and cost scoping named macOS assets, CLI + Homebrew fixes
-
Effective scaling laws for time series foundation models
By
–
Are scaling laws finally effective for time series foundation models? Today, @datadoghq is releasing Toto 2.0 weights under Apache 2.0 on @huggingface. It's a family of open-weights TSFMs ranging from 4M to 2.5B parameters, where each size outperforms the previous one from a single hyperparameter configuration.
-
AGI Alpha: A Public Proof Layer for Self-Improving AI
By
–
Recursive validated self-improving AI at $ 4.65B. AGI ALPHA is building the public proof layer. Not just AI that improves—
AI that proves, replays, audits, archives & compounds. Proof-bound. Enterprise-ready. Built in public. https://
github.com/MontrealAI/agi
alpha-first-real-loop
… #AGIALPHA #MontrealAI -
AGI ALPHA: public proof-layer for recursive self‑improving AI
By
–
Recursive validated self-improving AI at $4.65B. AGI ALPHA is building the public proof layer. Not just AI that improves—
AI that proves, replays, audits, archives & compounds. Proof-bound. Enterprise-ready. Built in public. https://
github.com/MontrealAI/agi
alpha-first-real-loop
… #AGIALPHA #MontrealAI -
Building AI Products with Open-Source Models and Sovereign Infrastructure
By
–
Sydney showed up Huge thanks to the founders, devs, builders, & partners who joined us for SambaHouse with Equinix & SCX. Great convos, live demos, & a room full of people building real AI products with open-source models & sovereign infrastructure.
-
Optimizing Claude Code Tool Calls
By
–
You can cut Claude Code's tool calls by 94% with one command.
— AlphaSignal AI (@AlphaSignalAI) 14 mai 2026
When Claude Code explores a repo, it spawns agents to scan files.
Each scan burns tokens on every tool call.
CodeGraph is an open-source MCP server that fixes this.
It pre-indexes your codebase into a local… pic.twitter.com/W8SMYr0RJlYou can reduce Claude Code's tool calls by 94% with a single command. When Claude Code analyzes a repository, it launches agents to scan files. Each scan consumes tokens with every tool call. CodeGraph is an open-source MCP server that solves this issue. It pre-indexes your codebase locally.