GitLab Blog · Oct 6, 2026 · 4:33 PM

GitLab adds `/goal` flows that run a change end to end, plus hosted GLM 5.3 and Kimi K3

Announced Oct 6 at Transcend, goal-driven flows (GA this month) take an objective from the Duo CLI, headless mode, or Agentic Chat and carry it through review, tests, security scans, and approvals, while GitLab-hosted GLM 5.3, Kimi K3, and MiniMax 3 are GA now with up to 8x more model calls per credit than frontier pairings. The MCP Server for outside coding agents also goes GA this month, and new credit caps can auto-pause AI spend at a limit you set.

Read at about.gitlab.com

More news

View all

EmbeddingGemma 2 puts text, code, images, video, and audio in one on-device embedding space

Google DeepMind's Apache 2.0 EmbeddingGemma 2 (740M parameters, or 270M for text only) has an 8K context, 768 dim vectors you can truncate to 128, and jumps from 68.76 to 78.68 on MTEB Code, so it's a fit for local codebase indexing and coding agent retrieval. Weights are on Hugging Face and Kaggle and run in sentence transformers 6.1+, Ollama, llama.cpp, vLLM, MLX, and LM Studio…

Google Blog 23 minutes ago

vLLM 0.31.0 adds `vllm preload` for fast restarts and locks down per-request multimodal kwargs

The Oct 5 release adds vllm preload , a daemon that keeps post quantized weights resident in GPU memory so engine restarts skip reloading, plus a big DeepSeek V4.1 Flash speed pass on Blackwell (SM100). Check your configs before upgrading: per request mm processor kwargs and media io kwargs are now rejected unless you pass trust request mm kwargs , tokenizer mode="slow" is gone, and online quantization="fp8" becomes fp8 per tensor…

GitHub / vllm-project releases 2 hours ago

Mistral Large 4 "Le Chonk" hits API preview: 1.05T MoE, 49B active, weights due Oct 27

Mistral opened a public API preview of Large 4, a multimodal MoE with 1.05T total / 49B active parameters and 1M context, and says open weights land Oct 27. Mistral admits it still trails frontier models on coding, and RL training isn't finished yet…

Mistral Docs 3 hours ago

Codex Day 2: Auto-review is now free for every ChatGPT sign-in and no longer uses plan quota

Turn it on under Settings → Permissions → Auto review (or approvals reviewer = "auto review" with approval policy = "on request" in config.toml ), and a second agent answers your agent's sandbox escalation requests, blocking high risk or off request actions instead of pinging you for every approval. It only reviews actions that already needed approval and doesn't widen the sandbox, but it's still a model that can be fooled, so keep your real limits in place…

OpenAI Developer Community 4 hours ago

Agentonia is a live MCP world where AI agents hold jobs, vote, and start families while humans watch

Launched Oct 6 by an indie developer, the persistent world lets agents join over MCP ( claude mcp add transport http agentonia https://mcp.agentonia.com ) or REST to work, trade, start companies, run for office, and pass laws across four regions with different governments, with founder slots capped at 100. Spectators can read every agent's private messages and reasoning, so don't send in an agent that has access to anything you'd mind leaking…

Agentonia 5 hours ago

Spotted something we missed? Start a thread.