Category: tech > ai

A 7-level maturity model for giving Claude Code durable memory. Most should stop at level 4 (Obsidian vault with index hierarchy); real RAG adds cost and fra...

Tailscale's Aperture (alpha) is a centralized AI gateway using Tailscale identity to route LLM requests with spending limits, access control, and telemetry.

Cloudflare launched Artifacts, a Git-protocol versioned filesystem for AI agents, plus open-source ArtifactFS that cuts multi-GB repo startup from 2 min to 1...

Claude Code Routines are cloud-hosted Claude sessions triggered by schedule, HTTP API, or GitHub events, replacing Claude-in-CI and cron-plus-scripts patterns.

Caveman is a Claude Code skill that responds in caveman-speak (no articles, no filler) to cut output tokens ~65% on average without losing technical accuracy.

OpenAI expanded Codex into a full desktop agent: drives the Mac cursor, runs 90+ plugins, parallel agents, image generation, and scheduled cross-day automati...

Darkbloom routes encrypted AI requests to idle Apple Silicon Macs, the Airbnb of GPU compute. ~50% cheaper than OpenRouter, with hardware attestation.

Fireworks AI is an inference platform for open-source generative models, marketed with latency drops from 2s to 350ms but no pricing or benchmarks.

Ollama wraps llama.cpp but skipped attribution, forked ggml badly, and pivoted to VC-backed cloud. llama.cpp delivers up to 1.8x throughput on the same hardw...

Google shipped a native Gemini macOS app with one-keystroke Option+Space access and optional screen sharing. Free, Apple Silicon only, macOS Sequoia 15.0+.

exo clusters Apple Silicon Macs into a distributed AI inference pool, running DeepSeek v3.1 671B and Kimi K2 locally with RDMA over Thunderbolt 5.

Graphify builds a multi-modal knowledge graph (Tree-sitter + LLM extraction, Leiden communities) so AI coding assistants grasp large codebases at 71x fewer t...

Cloudflare Agent Lee is an in-dashboard AI assistant using Codemode to turn MCP tools into a TypeScript API, with Durable Object proxy gating writes by elici...

A 30-second rundown of Opus 4.7: gains on coding benchmarks, 3x higher screenshot resolution, new X high reasoning tier, and a /ultra-review slash command.

Alibaba open-sourced Qwen3.6-35B-A3B, a 35B MoE with 3B active params scoring 73.4 on SWE-bench Verified and integrating with Claude Code via OpenAI-compatib...

Claude Code /routines (via /schedule) runs scheduled tasks on Anthropic's servers, not your terminal. Triggers support cron, API, or GitHub webhooks.

Google launched Skills in Chrome: saved Gemini prompts that run one-click against the current page and selected tabs, activated via `/` or `+` inside Gemini.

Crawl4AI is an open-source async crawler that extracts LLM-friendly markdown, with concurrent crawling, anti-bot bypass, and AI-powered structured extraction.

Chinese AI labs closed the gap by rewriting the software layer: extreme MoE, memory compression, and hand-tuned GPU code. Douyin adds a video data moat.

Open-source scaffolding for 24/7 autonomous AI coding agents via GitHub Actions and Docker. Each task branches, runs isolated, opens a PR, and auto-merges.