Kimi Code Changelog · Oct 21, 2026 · 6:24 PM

Kimi Code 2.3.0 switches plugin skills to qualified names and raises remote-control transfers to 100 MiB

Released Oct 21, Moonshot's coding CLI now invokes plugin skills only by their plugin:skill name so same-named skills stop shadowing each other, streams remote-control traffic up to 100 MiB, and queues /compact while the agent is busy. Heads-up: dangerous_command_guard = false now turns off every built-in confirmation guard, including sensitive-file and git control-path checks (GitHub release).

Read at moonshotai.github.io

More news

View all

VS Code 1.143 makes the Copilot harness the default and adds side-by-side model comparison

Released Oct 21, new agent sessions now run on the Copilot SDK based harness, and a preview Compare Models mode in the Agents window runs one prompt across Copilot, Claude, and Codex harnesses with an optional judge model to score and synthesize results. Experimental on device MAI Code 1.1 Flash skips AI credits but needs an NVIDIA GPU with at least 96 GB of memory (Visual Studio Magazine)…

VS Code Release Notes 48 minutes ago

OpenAI's GPT-6 models and Codex come to Google Cloud's Model Garden in private preview

Announced Oct 21, GPT 6 Astra, GPT 6.1 Sol, and GPT 6 Luna are rolling out to select enterprise customers in Model Garden, billed through Google Cloud Marketplace against existing GCP commitments, and Codex CLI and Desktop can already point at Google's platform for inference (Google Cloud Blog). General availability is planned in the coming weeks, with Antigravity and Gemini Agent support to follow…

OpenAI 2 hours ago

Glean lets you build, test, and publish its enterprise agents from Claude Code, Cursor, or Codex

Generally available as of Oct 21, the Glean plugin's /glean run command writes an agent as a spec.yaml plus instructions.md in your repo, runs and evaluates it from the coding agent, then publishes it to Glean's managed runtime with its permissions across 275+ enterprise sources. Only Auto mode agents are supported; Workflow mode still needs Glean's visual builder (docs)…

Glean Blog 4 hours ago

Mistral's Voxtral 3 adds a LiveKit-based voice agent SDK and new speech models in 50+ languages

Released Oct 20, the SDK chains Voxtral Mini Transcribe Realtime 3, a reasoning model like Mistral Small with tool calling, and Voxtral TTS 3 into one streaming pipeline that Mistral says finishes each turn in under a second, over SIP or WebRTC. Transcription starts at $0.0035/min via the API or self deployment, and Voxtral 2 callers have a migration guide since emotion moves from preset voices to inline tags…

Mistral AI News 5 hours ago

Perplexity Computer can now run fully local on Apple silicon Macs, model and agent included

Launched Oct 20 for Pro, Max, and Enterprise subscribers, the new mode runs planning, reasoning, and file work on device with Qwen 3.6 or the post trained PPLX Pro, working across local files plus Notes, Messages, Mail, and Numbers when you grant access. Perplexity recommends 36GB or more of unified memory, and you can still authorize cloud escalation for browsing, fresh info, or connected apps (9to5Mac)…

Perplexity Blog 6 hours ago

Spotted something we missed? Start a thread.