AI Coding Live News

DeepSeek Harness Launches Creator Mode: Describe a Plugin in Chat and the Agent Builds It, With 7 Official Demo Prompts

DeepSeek Harness, DeepSeek's open-source, MIT-licensed agent app, announced Creator Mode on its official X account on November 2: users describe the plugin they want in plain language, and the agent turns it into a plugin they can use. Demos include a 3D landmark gallery, a 3D Transformer visualizer, a video editing workbench and a paper reader. DeepSeek also published seven bilingual demo prompts on cdn.deepseek.com, cautioning that some plugins took several rounds of conversation, so a single prompt may not reproduce the video exactly. The post drew about 20,000 likes and 1.69 million views. No benchmarks were published.

DeepSeek Harness Launches Creator Mode: Describe a Plugin in Chat and the Agent Builds It, With 7 Official Demo Prompts

Key Takeaways

  • Creator Mode: describe the plugin you want in natural language and the agent turns it into a usable plugin, from a design workspace to a sandbox game or a 3D LLM visualizer.
  • DeepSeek published 7 demo prompts: a 3D landmark gallery, a 3D Transformer demo, a five-style app theme switcher, a poster workbench, a video editor, a paper reader and a token-usage statistics plugin.
  • The entry point shipped in v0.2.1-rc.5 (Oct 30 pre-release): plugin management gained a "Let Agent create a plugin" button that opens Creator mode and keeps the draft.
  • The GitHub repo has about 270,000 stars under the MIT license; Harness is still in preview.
  • No benchmarks or success rates were published; the announcement drew about 20,000 likes and 1.69 million views.
Read full story
Linked Models & Agents:

Kimi launches 3D Make: K3.1 Pro drives Blender, CAD tools and Unreal, Unity and Godot to build models, scenes and games

Moonshot AI's official Kimi account announced 3D Make at 03:14 UTC on Oct 30, saying Kimi connects to tools such as Blender and CAD software to create models, assemble scenes and develop games, available now on kimi.ai and Kimi Work. The companion 3D guide says K3.1 Pro was specifically trained to drive 3D software through Python scripts, so specialized tools without MCP support can join the workflow, while meshes such as people and animals are handed to diffusion services like Tripo. Plugins that need locally installed software work only in Kimi Work.

Kimi launches 3D Make: K3.1 Pro drives Blender, CAD tools and Unreal, Unity and Godot to build models, scenes and games

Key Takeaways

  • Availability: 3D Make is live on kimi.ai and Kimi Work; plugins that need locally installed software are Kimi Work only
  • Two modeling routes: parametric models (furniture, mechanical parts, buildings) via Python scripts written by K3.1 Pro, and meshes via services such as Tripo, Meshy and Hyper3D
  • Engines: Kimi says it is adapted to Unreal Engine, Unity and Godot to import models, assemble scenes and build gameplay step by step
  • Showcase: the celestial palace in the K3.1 Pro launch video was built in Unreal Engine 5.8 from source models totaling 36 million triangles, rendered with Nanite and Lumen
  • Benchmarks: no 3D benchmarks were published; the guide admits some tasks need several rounds, and rigging and complex materials remain weak spots
Read full story

ChatGPT adds iCloud Mail and iCloud Calendar plugins on all plans, connected with an Apple app-specific password

On Oct 27 the official ChatGPT account announced that iCloud Mail and iCloud Calendar plugins are available in ChatGPT on all plans across web, desktop and iOS, rolling out globally. Users can ask ChatGPT to find an email, catch up on their inbox, check what is next or update a calendar event. The two plugins are installed separately, both connect with an Apple app-specific password, and both include read-only contact lookup; standalone Contacts and Reminders plugins are not part of this launch.

ChatGPT adds iCloud Mail and iCloud Calendar plugins on all plans, connected with an Apple app-specific password

Key Takeaways

  • Available on every ChatGPT plan, including Free, on web, desktop and iOS, rolling out globally and subject to workspace app controls
  • Found under Settings > Plugins; iCloud Mail and iCloud Calendar are installed and connected separately
  • Both connect with an Apple app-specific password, which requires two-factor authentication; never use the main Apple password or paste it into a chat
  • Mail only works with @icloud.com, @me.com and @mac.com addresses, while Calendar uses the primary Apple Account email, which may differ
  • Disconnecting in ChatGPT does not revoke the app-specific password at Apple; that has to be done separately at account.apple.com
Read full story
Linked Models & Agents:

Eagle releases EAGLE-4, a speculative-decoding drafter that adapts to batch size and hardware; it reports 961.6 tok/s on Qwen3.8-27B for a single request

On Oct 20, inference company Eagle released EAGLE-4, the fourth generation of the EAGLE speculative-decoding family. One drafter resizes its speculative tree for the batch size, hardware and workload while keeping the target model's output distribution. Eagle reports 961.6 tokens/s for one request on Qwen3.8-27B with 4x B300. The code ships as eagle-harness v0.1.0 with plugins for SGLang, vLLM and an experimental TokenSpeed backend. Many reposts call it open source, but the official license is source-available, not OSI open source.

Eagle releases EAGLE-4, a speculative-decoding drafter that adapts to batch size and hardware; it reports 961.6 tok/s on Qwen3.8-27B for a single request

Key Takeaways

  • Vendor figure: 961.6 tokens/s on Qwen3.8-27B with TokenSpeed, BF16, 4x B300, TP4, one request, T=0 (paper Figure 1(a))
  • Repo measurements: vLLM on 4x B300 goes from 241.6 to 722.8 tok/s at concurrency 1 (2.99x) and 1.70x at concurrency 8; SGLang gets 1.91x at concurrency 8 and 1.35x at 64
  • AMD numbers too: SGLang on one MI355X gets 2.07x at concurrency 8 and 1.56x at 32 (ROCm 7.2)
  • Design: sliding-window draft layer, low-rank candidate head and append-only draft cache; the harness calibrates verify latency offline and grows the tree while gain per cost stays high
  • License: Eagle 4 Source-Available; free for noncommercial use, commercial use only under $20M trailing 12-month revenue and outside competing offerings
Read full story
ADSponsored

OpenCode 2.0 ships: one background service for TUI, web and desktop, Code Mode for all MCP servers, background subagents, and @opencode/sdk

Anomaly published the OpenCode 2.0 launch note on Oct 12: a single auto-started local service shared by the TUI, web and desktop apps; a rewritten server API with the new @opencode/client; @opencode/codemode, which turns MCP servers and OpenAPI endpoints into functions the model composes in scripts (all MCP servers opt into Code Mode by default); background subagents and background shell commands; 80+ internal features rebuilt as hot-reloadable plugins; and @opencode/sdk for embedding the same engine as a library. V1 plugins and the old server API are not compatible.

OpenCode 2.0 ships: one background service for TUI, web and desktop, Code Mode for all MCP servers, background subagents, and @opencode/sdk

Key Takeaways

  • Architecture: one auto-started local background service shared by TUI, web, desktop and @opencode/client scripts; opencode pair connects other hosts
  • Code Mode: @opencode/codemode converts MCP servers and OpenAPI endpoints into script-callable functions; every MCP server defaults to Code Mode (codemode: false opts out)
  • Orchestration: background subagents (background: true, default nesting depth 1) and background shell commands with no default timeout; Ctrl+B moves running work to the background
  • Extensibility: 80+ features implemented as internal plugins, TUI plugins now stable and hot-reloadable; @opencode/sdk is the same code as the CLI
  • Migration: three breaking areas (plugin API, server API/clients, tui.json to global cli.json); upgrade with opencode upgrade --major
Read full story
Linked Models & Agents:

DeepSeek Harness v0.2.1: desktop apps plus experimental Claude Code Mods compatibility

GitHub dsh-v0.2.1-alpha.1 (2026-10-03T06:42:19Z) adds an experimental Claude Code Mods compatibility layer to MIT DeepSeek Harness (~243k stars)—explicitly to test that Mods APIs are broadly a subset of dsh plugins, not full compatibility—continuing v0.2 desktop apps. Get it at deepseek.com/harness or npx @deepseek-ai/dsh web.

Key Takeaways

  • Sources: dsh-v0.2.1-alpha.1 (2026-10-03), deepseek-ai/deepseek-harness (~243k★), deepseek.com/harness
  • Experimental Claude Code Mods layer = subset validation, not full compatibility
  • v0.2 desktop: macOS Apple silicon + Windows x64 with bundled dsh command
  • Everything-is-a-plugin on Cordis; OpenAI-compatible providers supported
  • Developer preview with breaking changes—sandbox before production
Read full story

Claude Code 2.1.287: Mods in-process extensions; built-in You should know side agent; 1M context default on gateways

Anthropic shipped Claude Code 2.1.287 on 2026-10-01 (npm @anthropic-ai/[email protected]): Claude Mods let plugins run in-process JS/TS hooks that rewrite tool calls and UI; opt-in built-in You should know side agent; MCP URL elicitation; Opus 4.7+/Fable default to 1M context on Bedrock/Vertex/Foundry/apps gateway. Agent SDK TS 0.3.287 parity.

Claude Code 2.1.287: Mods in-process extensions; built-in You should know side agent; 1M context default on gateways

Key Takeaways

  • Release v2.1.287; npm 2.1.287; GitHub ~2026-10-01T18:00:22Z
  • Mods: in-process hooks for UI + tool.call rewrite; ≥2.1.287; docs https://code.claude.com/docs/en/plugins/mods/overview
  • You should know: /plugin enable cc-plugin-you-should-know@builtin (first-party + telemetry); off by default
  • 1M context default for Opus 4.7+/Fable on Bedrock/Vertex/Foundry/apps gateway; disable via CLAUDE_CODE_DISABLE_1M_CONTEXT=1
  • Agent SDK TS 0.3.287; MCP URL elicitation / bareElicitationCapability
Read full story

JetBrains Air in IDEs EAP: Marketplace/2026.3 native, free Junie Lite, ACP for Codex·Copilot·Claude·Cursor

On 2026-10-01 JetBrains opened the Air in IDEs EAP: an agentic session workspace via Marketplace plugin #33314 or native 2026.3 EAP builds. Ships with no agents; detects local ACP-compatible agents (Codex, Copilot, Claude, Junie, Cursor, …); free Junie Lite with JetBrains Account. Not an AI provider—third-party traffic goes to your vendor.

JetBrains Air in IDEs EAP: Marketplace/2026.3 native, free Junie Lite, ACP for Codex·Copilot·Claude·Cursor

Key Takeaways

Read full story

Anthropic TS SDK 0.130 / Python 1.10: Admin analytics & plugin marketplaces; Organization API GA; MCP tunnels beta

Anthropic shipped @anthropic-ai/[email protected] and Python anthropic==1.10.0 on 2026-09-30: Admin API gains enterprise analytics, spend limits, RBAC groups/roles, Plugins/Plugin Marketplaces, and per-user usage/cost reports; Organization API endpoints go GA; MCP tunnels beta returns read-only transport plus one-time relay token on create; Managed Agents add refusal stop reason and repository error types.

Anthropic TS SDK 0.130 / Python 1.10: Admin analytics & plugin marketplaces; Organization API GA; MCP tunnels beta

Key Takeaways

  • Releases: TS sdk-v0.130.0 at 2026-09-30T18:29:28Z; Python v1.10.0 at 2026-09-30T18:28:45Z
  • Admin API: analytics, spend limits, RBAC, Plugins/Marketplaces, per-user usage/cost; compare
  • Organization API endpoints now GA; MCP tunnels beta adds read-only transport + one-time relay token
  • Managed Agents: refusal stop reason/stop_details on idle; repository error types
  • Install: npm i @anthropic-ai/[email protected] / pip install anthropic==1.10.0; docs https://docs.anthropic.com/en/api/admin-api
Read full story

Personal desktop agents compared: Grok Bot vs Meta Muse vs OpenAI Dots

After OpenAI launched Dots (GPT-6 Astra, per-dot cloud computer, 4000+ plugins) at DevDay, the personal/desktop agent space has three clear poles: Cursor/xAI Grok Bot (developer teammates + routines), Meta Muse (Secure VM consumer agent; often misheard as “Mate Muse”), and OpenAI Dots (always-on primary Dot). Feature comparison from official docs only—no invented benchmarks.

Personal desktop agents compared: Grok Bot vs Meta Muse vs OpenAI Dots

Key Takeaways

  • “Mate Muse” verifies as Meta Muse (2026-09-08): Meta news + How We Designed Muse; Muse Secure VM + Muse Spark; consumer life/goals agent.
  • OpenAI Dots (DevDay 2026-09-29): Introducing dots; GPT-6 Astra; own cloud computer; 4000+ plugins; ChatGPT Pro / Business Premium; one primary Dot at launch.
  • Grok Bot: Cursor docs — persistent cloud computer, plugins/MCP, skills/routines, multi-Bot; included with paid Cursor plans or SuperGrok / X Premium+ link (Plans).
  • No public three-way official SWE-Bench/Agent Arena bake-off; pick by job: coding/routines/multi-Bot → Grok Bot; consumer life agent → Muse; ChatGPT ecosystem always-on → Dots.
  • Shared pattern: isolated cloud computer + approval for sensitive acts; differ on developer routines/local exec (Grok Bot), WhatsApp/consumer connectors (Muse), plugin breadth + Pro bundling (Dots).
Read full story
ADSponsored

simonw/llm 0.36: GPT-6 Sol/Luna catalog + supports_conversation=False for plugins

llm 0.36 (2026-09-22) adds gpt-6-sol/gpt-6-luna, lets plugins set supports_conversation=False (raises ConversationNotSupported; first used by llm-typesafe), and wraps reasoning traces in <details> in llm logs Markdown.

simonw/llm 0.36: GPT-6 Sol/Luna catalog + supports_conversation=False for plugins

Key Takeaways

  • Built-in gpt-6-sol and gpt-6-luna (#1702)
  • Plugins may set supports_conversation=False → ConversationNotSupported (#1692)
  • First consumer: llm-typesafe for Jev/TypeSafe models
  • llm logs wraps reasoning in HTML details (#1701)
  • Upgrade: pip install -U llm==0.36
Read full story

Anthropic launches Claude Marketplace: 2,000+ connectors; spend commit on Cursor and partner agents

Claude (@claudeai) launched Claude Marketplace—one place for connectors/plugins, agents/products, and service partners. Customers get 2,000+ connectors (Atlassian, Google, Microsoft, Notion, Salesforce, …), can apply Anthropic committed spend to Claude-powered software from CrowdStrike, Cursor, Harvey, Legora, Lovable, Snowflake, and engage Accenture/BCG/Deloitte-style partners. Builders can list to reach Claude teams.

Anthropic launches Claude Marketplace: 2,000+ connectors; spend commit on Cursor and partner agents

Key Takeaways

  • Announcement: three shelves—connectors/plugins, agents/products, service partners.
  • Over 2,000 connectors/plugins (Google Drive, Gmail, Microsoft 365, Notion, Figma, Slack, …).
  • Apply Anthropic committed spend to partner software like CrowdStrike, Cursor, Harvey, Legora, Lovable, Snowflake.
  • Service partners via Claude Partner Network (Accenture, BCG, Deloitte); builders can apply to list.
Read full story

Hermes Agent official plugin: Claude SDK restores Claude Code subscriptions inside Hermes

@Teknium (Nous Research) shipped a new official Hermes Agent plugin that uses the Claude SDK without prior tradeoffs so Claude Code subscriptions work inside Hermes Agent again; install docs at hermes-agent.nousresearch.com/docs/plugins/claude-subscription-directsdk.

Hermes Agent official plugin: Claude SDK restores Claude Code subscriptions inside Hermes

Key Takeaways

  • Official plugin: Claude SDK integration without prior tradeoffs.
  • Restores Claude Code subscription use inside Hermes Agent.
  • Install via Hermes docs: claude-subscription-directsdk plugin page.
Read full story

skill-audit scans agent skills, plugins, and MCP configs for supply-chain risk

@AverageAiBro highlighted ondrej-merkun/skill-audit, a local scanner for prompt-injection and malware patterns across Claude Code, Codex, Copilot, Cursor, Gemini CLI, Windsurf, Cline, AGENTS.md, installed skills, plugins, and MCP configs. It ships 46 rules with no cloud upload, optional deeper review through localhost OpenAI-compatible models, CI support via --fail-on REVIEW, and a GitHub Action under the @ondrej-merkun/skill-audit npm package.

Key Takeaways

  • Scans skills, plugins, MCP configs, and AGENTS.md locally across major coding-agent clients.
  • Forty-six rules detect prompt injection and malware patterns without uploading configs to the cloud.
  • Supports --fail-on REVIEW, a GitHub Action, and optional localhost model review for install and CI gates.
Read full story

Grok Build adds /learn to mine reusable Skills from agent chats

@iml1s covered xAI coding tool Grok Build adding /learn: it analyzes your agent chats, proposes new or updated Skills from repeated instructions, and flags stale rules, rarely used Skills, plugins, and MCP. Choose report-only or step-through apply. This is workflow-rule curation, not chat memory—akin to Claude Code /insights.

Key Takeaways

  • /learn mines reusable Skills from chat so you stop retyping the same agent rules.
  • Flags stale rules and cold Skills/plugins/MCP; report-only or step-through apply.
  • Rule curation, not memory—Grok Build's take on Claude Code /insights.
Read full story