Claude Code lead Boris Cherny (@bcherny) said Claude Mods are landing now. Community demos already include a Tetris-in-Claude mod; latest updates, technical details, and more demos are on anthropics/claude-code GitHub issue #91870.
⚡ Key Takeaways
•Claude Mods are landing in Claude Code, announced by lead Boris Cherny.
•Community demos already include Tetris-in-Claude.
•Technical details and updates live on anthropics/claude-code issue #91870.
Hassan (@nutlope) launched Inspo, a design MCP server for coding agents that searches 800+ websites for relevant design inspiration. Install with npx inspo-mcp install; works with Claude Code, Codex, and OpenCode.
⚡ Key Takeaways
•Inspo is a design-inspiration MCP for Claude Code, Codex, and OpenCode.
•Searches 800+ sites for relevant design references for coding agents.
ElevenLabs launched a multimodal MCP for voice, transcripts, dubs, music, sound effects, images, and video from assistants you already use. It is live in ChatGPT, Claude, Cursor, Grok Bot, and Hermes from a single install.
⚡ Key Takeaways
•ElevenLabs MCP now generates voice, music, images, and video.
•Works inside ChatGPT, Claude, Cursor, Grok Bot, and Hermes.
•Single install covers speech, transcripts, dubs, SFX, and media.
Cline officially launched Cline Desktop (macOS/Windows beta), a native desktop UI for open-weight models via ClinePass (DeepSeek-V4.1-Flash, Musespark-1.3, and other free models) or BYOK with any provider. It can import sessions from Claude Code, Codex, and OpenCode, plus scheduled agent runs, a marketplace for plugins/MCP/skills, web search, and voice input at cline.bot/desktop.
⚡ Key Takeaways
•Official desktop beta: native UI for open-weight models on macOS/Windows.
•ClinePass free models include DeepSeek-V4.1-Flash and Musespark-1.3; BYOK supported.
•Imports Claude Code/Codex/OpenCode sessions; scheduled runs plus MCP/skills marketplace.
shadcn launched open-source shadcn/lint (GitHub: shadcn-ui/lint), an agent-first Tailwind design-system linter. You define allowed components/variants/theme contracts; when an agent breaks a rule, errors explain the violation and how to fix it with your system. Works with Oxlint and ESLint without requiring shadcn/ui. Evals claim most tasks reach zero violations in one correction round, with fixes ~10–48% cheaper than AGENTS.md-only.
⚡ Key Takeaways
•Agent-first Tailwind design-system linter driven by real components/variants/theme rules.
•Violations explain what broke and how to fix using your design system; Oxlint and ESLint supported.
•Open-source at shadcn-ui/lint; evals show one-round fixes and lower cost vs AGENTS.md-only.
bolt.new introduced Bolt Forge, an open-weight coding agent now live in the bolt.new model picker. Free until Oct 14 with up to ~50x usage and zero usage charges; lineup includes GLM 5.3 / GLM 5.3 Flash, Kimi K3, and DeepSeek v4 Pro. Opt-in builds help train a trillion-parameter-class model with Arcee; also announced $9/mo Bolt Lite (Forge included; join by Oct 14 to lock $9). Partners include Arcee, Microsoft, Vercel, Fireworks, and DigitalOcean.
⚡ Key Takeaways
•Bolt Forge is live in bolt.new’s model picker as an open-weight coding agent.
•Free through Oct 14 with up to ~50x usage and zero usage charges; GLM 5.3, Kimi, DeepSeek included.
•Also ships $9/mo Bolt Lite with Forge; opt-in builds train a trillion-param model with Arcee.
Perplexity says Portable Computer is now available on Windows PCs with NVIDIA RTX GPUs: run the harness, agents, and models locally, work with local files and apps, and fall back to frontier cloud models when needed. On-device work does not consume Computer credits; follow-ups add local MCP and scheduled tasks, and NVIDIA confirms 24GB+ VRAM.
⚡ Key Takeaways
•Portable Computer now runs on Windows with NVIDIA RTX for local harness/agents/models.
•On-device work skips Computer credits; cloud frontier models remain optional.
•Adds local MCP and scheduled tasks; NVIDIA lists GeForce/RTX PRO 24GB+ VRAM.
Shanghai AI Lab released Atria Dawn Preview, an agentic foundation model for long-horizon research/engineering tasks built on the 744B-parameter MoE GLM-5.2, with tool use and executable verification loops. Weights are on Hugging Face (internlm) and ModelScope, plus an FP8 build, 256K context, GitHub, website, and API try links.
⚡ Key Takeaways
•Atria Dawn Preview is built on 744B MoE GLM-5.2 for long-horizon research and engineering agents.
•Open weights on Hugging Face/ModelScope with FP8 and 256K context under MIT.
•Covers Discovery/Creation/Delivery/Cybersecurity end-to-end scenarios with API try access.
Reports say Google released a free Google Cloud Developer Plugin so AI coding agents can use official cloud knowledge and tools (project setup, auth, gcloud, docs) instead of guessing GCP workflows. Claude Code install: claude plugin marketplace add google/skills, then claude plugin install google-cloud-developer@google-plugins; Codex CLI and Antigravity have their own install paths. The plugin is free; normal GCP/API usage still bills separately.
⚡ Key Takeaways
•Free Google Cloud Developer Plugin targets Claude Code, Codex CLI, and Antigravity.
•Grounds agents in official cloud knowledge/tools instead of guessing GCP flows.
•Claude Code: marketplace add google/skills then install google-cloud-developer@google-plugins.
The Gemini API now lists id antigravity-preview-09-2026. It is not a new Pro/Flash model but the Antigravity managed-agent endpoint: Linux sandbox with code execution, files, and browser, defaulting to Gemini 3.8 Flash. Google-affiliated Philipp Schmid confirmed it is the Gemini API agent harness, with more details expected later this week.
⚡ Key Takeaways
•API id antigravity-preview-09-2026 is the Antigravity managed-agent endpoint, not a new Pro/Flash model.
•Endpoint offers Linux sandbox, code execution, files, and browser; default model is Gemini 3.8 Flash.
•Google confirmed it as the Gemini API agent harness, with more details later this week.
Gentleman Programming shipped gentle-ai v2.8.1–v2.9.0 and gentle-pi v2.6.1–v2.6.3. Highlights include Claude Code runtime telemetry that attributes models by public family patterns, OpenCode SDD/reviewer relay semantic decoding, and opt-in RTK as a community tool (attested install to ~/.local/bin/rtk, configures only selected agents, telemetry off by default; Windows unavailable). gentle-pi adds subagent_reconcile so a parent can reconcile uncertain acquire/settle remediations without launching an actor or exposing tokens.
⚡ Key Takeaways
•gentle-ai v2.9.0 adds opt-in RTK community tool with attested install and selected-agent-only config.
•Claude Code Stop usage telemetry is idempotent and attributes models by public family patterns.
CCXT launched the official ccxt-mcp MCP server so AI agents can reach 100+ crypto exchanges and prediction markets—read markets, check balances, and place trades. It works with Claude Code, Codex, Gemini CLI, Cursor, and any MCP client. One-line npx install; market data needs no keys; trading is off by default; OSS at github.com/ccxt/ccxt.
⚡ Key Takeaways
•Official ccxt-mcp covers 100+ exchanges and prediction markets for Claude Code, Codex, Gemini CLI, Cursor, and other MCP clients.
•Market data needs no API keys; trading is disabled by default.
•Open source at github.com/ccxt/ccxt with one-line npx install.
vLLM announced day-0 serving support for Shanghai AI Lab Intern-S2-397B. The 397B multimodal foundation model targets long-horizon scientific research and scientific agents, with strong multimodal, reasoning, coding, and agent capabilities. Developers can run it on vLLM today via the official recipe.
⚡ Key Takeaways
•vLLM shipped day-0 serving for Intern-S2-397B across multimodal, reasoning, coding, and scientific-agent workloads.
•Official recipe is at recipes.vllm.ai/internlm/Intern-S2-397B for immediate deployment.
•Pairs with the same-day Intern-S2-397B weight/eval release already in the feed: open weights plus open serving stack.
OpenFang (@openfangg / RightNow-AI) open-sourced an Agent Operating System that gives agents tools, memory, automation, and an environment for research, browser tasks, scheduled workflows, and real-world automation — framed as AI that works, not just talks. Repo: github.com/RightNow-AI/openfang.
⚡ Key Takeaways
•Positioned as an open-source Agent OS: tools, memory, and an automation environment — not a chat shell.
•Targets browser tasks, scheduled workflows, and real-world automation.
ModelScope announced Shanghai AI Laboratory Intern-S2-397B weights in BF16 and FP8 under Apache-2.0. Reported scores include 87.0 on FrontierScience-Olympiad and 84.0 on SWE-bench Multilingual, with long-horizon agent RL, tool use, and thinking/non-thinking modes. Training ingests raw scientific pages (text, visuals, symbols) across 20+ domains. Collection on ModelScope.
⚡ Key Takeaways
•BF16 and FP8 weights are public under Apache-2.0 on ModelScope.
•Reported 84.0 SWE-bench Multilingual and 87.0 FrontierScience-Olympiad as comparison leaders.
•Long-horizon agent RL targets tool use and sustained execution, with thinking and non-thinking modes.
The Model Context Protocol added a Skills extension (modelcontextprotocol/ext-skills). Servers declare io.modelcontextprotocol/skills; clients discover with skills/list, fetch metadata with skills/get, then load SKILL.md and supporting files via resources/read only when needed, instead of stuffing every skill into context. Spec: modelcontextprotocol.io/extensions/skills/overview.
⚡ Key Takeaways
•Official repo modelcontextprotocol/ext-skills, maintained by the Skills Over MCP Working Group.
•Flow: skills/list then skills/get then resources/read so SKILL.md loads on demand and saves context.
•Servers must declare resources plus io.modelcontextprotocol/skills; optional directoryRead for directory listing.
Unity Technologies released an official Claude Code plugin (unity-agent-plugin, about 0.1.2-beta). Install with two commands: /plugin marketplace add Unity-Technologies/unity-agent-plugin then /plugin install unity@unity-agent-plugin. It adds Unity-specific Skills and can drive Unity CLI for editor installs, project creation, and in-place C# execution, aiming for fewer errors and better token efficiency on unfamiliar engine tasks.
⚡ Key Takeaways
•Official marketplace plugin Unity-Technologies/unity-agent-plugin; two Claude Code install commands.
•Includes Unity Skills and Unity CLI for project creation, editor installs, and in-place C#.
GitHub announced agent apps that pull common software-delivery services into pull-request context so teams need fewer side tabs. Early examples include Amplitude, Endor Labs, LaunchDarkly, and PagerDuty, bringing analytics, security, feature flags, and on-call context into the GitHub workflow UI.
⚡ Key Takeaways
•Official GitHub Blog: agent apps embed delivery-workflow services in PRs.
Community changelog: SpaceXAI Cursor updated to 3.20.21 with Computer Use on Mac, Max Mode visible in the model picker, local agents able to run tools, and windows connected over SSH to another computer. Also covers the open-agent chat box, deferred list refresh until window focus, and PR tabs that can sit in front of app tabs.
⚡ Key Takeaways
•Computer Use on Mac; local agents can run tools.
•Max Mode shows in the model picker; SSH remote work windows supported.
•Also: open-agent chat box, focus-before-refresh lists, and PR tabs over app tabs.