vibehacker
News
GitHub (softcane/codex-session-operator) ·

Codex Session Operator runs OpenAI Agents API sessions against Git repos in your own Kubernetes cluster

Shown on HN Nov 2 under Apache-2.0, the alpha operator lets OpenAI run the agent loop while codex exec-server executes commands in a Kubernetes Agent Sandbox workspace, with a gateway saving messages, results and approvals in PostgreSQL so follow-ups reuse the same workspace. Agents, Environments and Profiles are CRDs, and a Profile can set an optional per-session dollar cap; real tasks need Agents API beta access and incur API charges.

Read at github.com
Codex
AI coding agent for features, refactors, reviews, and releases

More news

View all

Spielerando is an MCP game workbench that gives Claude Code and Cursor tested game recipes and story checks

Shown on HN Nov 2, one pasted line connects your coding assistant to 3,257 wiki entries, 113 blueprints and 45 code recipes for things like jump feel, loot odds and saves, plus checkers that walk every story path to find dead ends and stuck quests while it versions your project. It's free to start with a Google or email sign in, in English and German, and the site gives no pricing beyond that…

Spielerando (Show HN)

KVARK Sparkle 1.0 is an Apache-2.0 Qwen3.8-27B tune that thinks up to 67% less for about the same accuracy

Egzakta AI Lab's first open weight model, posted Nov 2 in BF16, FP8 and GGUF with an MTP head for speculative decoding, cuts median reasoning tokens 34–67% across five benchmarks and answers in 13.7s versus 28.1s for Qwen3.8 27B on one H200, with accuracy within a point except a +5.3 on a 50 problem LiveCodeBench subset. All numbers are the lab's own, and the GGUF runs locally via llama server hf Egzakta/Kvark Sparkle 1.0 27B GGUF:Q4 K M…

Hugging Face (Egzakta)

vLLM 0.33 release notes drop CUDA 12.9 builds and remove draft-slot reservation for DFlash/DSpark speculative decoding

Posted Nov 2 with 927 commits, the notes move vLLM to PyTorch 2.14 with CUDA 13.0 only wheels and images, and say DFlash/DSpark drafters no longer reserve token budget slots, lifting DeepSeek V4.1 Flash on GB300 from 1,373 to 3,390 output tok/s in the PR's own benchmark. The GitHub tag is still v0.33.0rc3 , and Medusa, the MLP speculator and the Ray compiled graph executor are removed, so check your setup before upgrading…

GitHub (vllm-project/vllm)

Maat lets AI agents diagnose Ubuntu from a no-network strict snap, with fixes you approve through polkit

Shown on HN Nov 2 under GPL 3.0, the MCP server reads the journal, units, processes and disks from a strictly confined snap where AppArmor blocks writes and internet sockets, and the model can only propose typed plans like restarting one failed service, which you apply with maatctl and a polkit prompt into a hash chained audit trail. It's a developer preview tested only on Ubuntu 24.04 arm64, and the author's first local model runs ( gpt oss:20b found the root cause 28 of 30 times) cover ten admittedly easy scenarios (Show HN)…

GitHub (bolesawny7/maat)

Spotted something we missed? Start a thread.