Warp Ships Tab Groups to Tame Chaotic Multi-Agent Terminal Sessions
Warp's new tab groups let you organize terminal sessions by project in a rich sidebar, now available in preview builds on Mac, Linux, and Windows
20 stories
Warp's new tab groups let you organize terminal sessions by project in a rich sidebar, now available in preview builds on Mac, Linux, and Windows

TurboQuant+ brings Google's ICLR 2026 KV cache compression to Apple Silicon and vLLM, squeezing 4.9x more context into the same memory with near-zero quality loss
Google DeepMind's first-ever robotics accelerator gives 15 European startups access to Gemini models, AI infrastructure, and up to $350K in cloud credits — equity-free.
Moonshot AI open-sources Kimi-K2.7-Code with 21.8% coding gains and 30% fewer reasoning tokens than K2.6

Baidu's PaddleSpeech adds Whisper large-v3-turbo support and a real-time code-switching ASR model to its open-source speech toolkit
The CLI Printing Press ships 74 agent-native Go CLIs and a factory that generates new ones for any API or website in a single command
MemPalace hits 96.6% on LongMemEval with zero API calls, using verbatim storage and local vector search — no cloud, no subscription, no LLM at write time
Artificial Analysis swaps SWE-Bench Pro for DeepSWE in its coding agent index, reshuffling the leaderboard and exposing how gameable the old benchmark had become

PaddleX 3.x is Baidu's open-source all-in-one AI toolkit with 270+ models, 33 ready-to-run pipelines, and SOTA document parsing — all behind a single Python API
Reasonix is a DeepSeek-native terminal coding agent that slashes long-session API costs to ~1/5 by engineering every layer around prefix-cache stability

Codex's in-app browser gains full Chrome DevTools Protocol access, letting the agent profile JS, inspect network traffic, and debug live pages autonomously.
OpenAI's Codex now lets users pocket rate limit resets and spend them mid-sprint, not at 3am when no one's awake

Hermes Agent's new Automation Blueprints turn raw cron jobs into conversational, fillable workflows — no cron syntax needed, any platform supported.
NVIDIA's MotionBricks runs 350,000 motion skills from a single neural model at 15,000 FPS, with open-source code and robotics support out of the box

GitHub's new standalone desktop app drops the waitlist, letting paid Copilot users run parallel AI agent sessions from issue to merged PR in one place.
Replit and Databricks expand their integration with per-user data permissions in public preview, letting anyone build apps where each viewer only sees data they're authorized to access
Google Colab adds Gemini-powered Visualization Mode and one-link Fullscreen Sharing, turning notebooks into shareable dashboards without writing chart code

Cohere's first open-source coding model, North Mini Code, is a 30B MoE with only 3B active parameters — and the community already ported it everywhere in 48 hours.

NVIDIA's MatX hits v1.0.0 with CUDA JIT kernel fusion, bringing NumPy-style C++ tensor code to near-native GPU performance
Replit Agent now remembers your team's coding conventions, design systems, and integration rules across every project automatically