MCP

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Creative teams produce more assets than ever, but fragmented tools and manual context transfer slow production. This post shows how to build a reusable agent harness with Amazon Quick and fal, connected through the Model Context Protocol (MCP), using two hands-on workflows: an eight-panel storyboard and a music-video concept prototype.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：deenesjakoruzh This server lets agents manage persistent, forkable cloud development environments over MCP. Check compute credits – see the account's remaining compute-credit balance. Create environments – spin up a per…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：AI agents are everywhere right now. You hear terms like tool calling, agent loops, MCP, guardrails thrown around as if its common language… it isn’t! But that is about to change. Agentic AI isn’t nearly as complicated as it sounds once you understand the few core ideas that actually matter. Here are 10 agentic AI concepts […] The post 10 Essential Agentic AI Concepts Explained Simply appeared first on Analytics Vidhya.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：REC · YOUR AGENT IS EDITING FFmpeg as a service, built for agents. Typed operations your agent calls over MCP or REST. Trim, resize, compress, convert. A validated request in, a finished file out. No shell, ever. Start…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Hugging Bay | Find And Download Open AI Hugging Bay WebPage https://huggingbay.xyz/ https://huggingbay.xyz/.well-known/agent-discovery.json https://huggingbay.xyz/openapi.json https://huggingbay.xyz/api/mcp Open-source…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：All-new TaskShell 2.0 as a first-class MCP platform Agent-first task management No more app-switching to keep up with your todos. You and your agents now completely in sync with your work, exactly where you work. Sync t…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Lovable is branching out from AI-powered web app creation and into MCP-powered ‘capabilities’. We talk to CTO Fabian Hedin.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：The following article originally appeared on PulseMCP’s blog and is being republished here with the authors’ permission. Most MCP demos feature a single server connecting to a single client. For example, you might wire up a Gmail MCP server to Claude Code. It works! It triages your inbox, drafts replies, finds that thing from three […]

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：IBM has released Granite 4.2, a family of open reasoning language models in 3B, 8B, and 30B sizes, all under Apache 2.0. Every model exposes a thinking / low-effort / non-thinking switch and native tool calling. The 8B and 30B additionally go through an agentic RL block that trains them to edit code, drive a terminal, and run web searches inside real sandboxed environments. The 30B reports 57.00 on SWE-Bench Verified and 29.24 on Terminal-Bench 2.1. The post IBM Releases Granite 4.2: Bringing Native Reasoning and Agentic RL to Open Enterprise Models appeared first on MarkTechPost.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Perplexity releases Portable Computer, packaging local models, harness, sandbox, and connectors into one system running on NVIDIA DGX Spark. The post Perplexity Ships Portable Computer on NVIDIA DGX Spark: Local Harness, OS-Enforced Sandbox, and Zero Per-Token Cost for Local Steps appeared first on MarkTechPost.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Amazon OpenSearch Service now supports MCP Apps, which return interactive visualizations alongside your AI agent's text responses. Learn how a single, locally run MCP server lets your agent move from alert to trace to logs to root cause in one conversation, and how you can verify every step inline without leaving your IDE.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：People already come to Claude before buying a book. They ask what to read, whether a book is worth starting etc. With coffeetable installed(a claude connector) Claude can now bring you few pages right inside the chat. W…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Cloudflare recently open-sourced Cloudflare OS on GitHub. Cloudflare OS allows enterprise teams to output work artifacts grounded in enterprise knowledge, know-how, and provisioned connectors, automate repetitive workfl…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Learn how to build a voice ordering system for restaurants that answers a phone call and takes an order end to end, with no app, no website, and no sign-in. It uses Amazon Connect for telephony, Amazon Connect Agentic Voice for real-time speech, an Amazon Connect AI agent for reasoning, and Amazon Bedrock AgentCore Gateway to reach backend tools through MCP.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Discussion | Link

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.20397v1 Announce Type: new Abstract: Agentic large language models (LLMs) on the Model Context Protocol (MCP) re-encode verbose tool schemas every turn, so prefill - quadratic in sequence length - dominates time-to-first-token (TTFT) as the tool registry grows. Nexus's primary lever is to decouple routing from the schema-prefill cost: an INT8 semantic lookaside buffer (SLB) with a calibrated cross-encoder margin gate selects tools by retrieval, and arguments are generated over a compressed textual signature (median 19 tokens) rather than over spliced key/value (KV) cache. This path is depth-independent: routing accuracy stays near 89% as the registry scales to 250 tools - where a concatenate-all-schemas baseline overflows the context window entirely - and it reaches a first-argument token 1.66x sooner than a full-schema re-prefill at a ~80% main-context token saving. As a secondary, bounded lever we transplant a compiled schema KV block directly into the live context. This is fundamentally limited by rotary position embedding (RoPE) phase drift: an anchored splice is output-exact, but off-anchor placement corrupts attention, so beyond a threshold P=256 Nexus repairs the seam with a depth-adaptive suffix redecode that escalates to a full re-prefill. The resulting never-regress property is a guarantee on output fidelity (top-1 agreement, D_KL approx. 0) - not on latency, which can dip to 0.98x before converging to parity - alongside a 1.1-1.7x TTFT speedup at moderate depth that narrows to parity at deep context. Two negative results bound the design: the off-anchor RoPE fidelity boundary, and the failure of a reference-free drift gate to predict drift (Spearman rho = 0.193). All measurements are from one model tuple (Qwen2.5-14B-Instruct Q4_K_M) on Apple-silicon unified memory; the qualitative boundaries generalize, while the quantitative envelope is tuple-specific.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：<p><strong>Research:</strong> <a href="https://github.com/simonw/research/tree/main/bun-webview-json-api#readme">A shot-scraper-style JSON API on Bun 1.4&#x27;s new Bun.WebView</a></p> <p>Today saw the long awaited <a href="https://bun.com/blog/bun-v1.4">release of Bun 1.4</a>, the first stable version since the infamous Rust rewrite <a href="https://simonwillison.net/2026/Jul/8/rewriting-bun-in-rust/">a few months ago</a>.</p> <p>Interestingly, the Rust rewrite was downplayed in the release notes, which introduced a bewildering array of new features and claimed 2,900 additional bug fixes:</p> <blockquote> <p>Bun 1.4 adds +1,517 tests from the Node.js test suite - our biggest jump in Node.js compatibility since Bun 1.0. Bun v1.4 also fixes over 2,900 issues. It reduces idle CPU usage by 5x, reduces memory usage by up to 35%, and starts 50% faster on Linux. It adds <a href="https://bun.com/blog/bun-v1.4#bun-image"><code>Bun.Image</code></a>, <a href="https://bun.com/blog/bun-v1.4#bun-webview"><code>Bun.WebView</code></a>, <a href="https://bun.com/blog/bun-v1.4#bun-markdown"><code>Bun.markdown</code></a>, <a href="https://bun.com/blog/bun-v1.4#bun-cron"><code>Bun.cron()</code></a>, <a href="https://bun.com/blog/bun-v1.4#bun-terminal"><code>Bun.Terminal</code></a>, <a href="https://bun.com/blog/bun-v1.4#bun-run-parallel"><code>bun run --parallel</code></a>, <a href="https://bun.com/blog/bun-v1.4#bun-test-parallel"><code>bun test --parallel</code></a>, <a href="https://bun.com/blog/bun-v1.4#bun-audit-fix"><code>bun audit fix</code></a>, <a href="https://bun.com/blog/bun-v1.4#bun-dedupe"><code>bun dedupe</code></a>, and <a href="https://bun.com/blog/bun-v1.4#bun-prune"><code>bun prune</code></a>. And it rewrites Bun from Zig to Rust.</p> </blockquote> <p>Of these the one that most caught my eye was <code>Bun.WebView</code>, which adds first class support for browser automation to Bun core using either macOS WebKit or control of a local Chromium process via the Chrome DevTools Protocol (CDP).</p> <p>I had Claude Code for web build a prototype of a web API providing the ability to load a web page and then execute JavaScript against it, inspired by my <a href="https://shot-scraper.datasette.io/en/stable/javascript.html">shot-scraper javascript</a> CLI tool - partly to see how much RAM would be needed by such a service.</p> <p>Here's <a href="https://github.com/simonw/research/blob/main/bun-webview-json-api/server.ts">that TypeScript server implementation</a>, which appears to need a 192MB-256MB container to run a full Chrome against complex web pages - tested using cgroups.</p> <p>Tags: <a href="https://simonwillison.net/tags/browsers">browsers</a>, <a href="https://simonwillison.net/tags/javascript">javascript</a>, <a href="https://simonwillison.net/tags/ai">ai</a>, <a href="https://simonwillison.net/tags/rust">rust</a>, <a href="https://simonwillison.net/tags/typescript">typescript</a>, <a href="https://simonwillison.net/tags/generative-ai">generative-ai</a>, <a href="https://simonwillison.net/tags/llms">llms</a>, <a href="https://simonwillison.net/tags/coding-agents">coding-agents</a>, <a href="https://simonwillison.net/tags/bun">bun</a></p>

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Discussion | Link

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Agentic artificial intelligence runs on data, so Salesforce Inc. today announced it is launching Headless Data 360 for Model Context Protocol to provide that data directly to agents, allowing them access to relevant, governed customer context. Teams can do more than query data through Data 360. Now they can build, transform, map, segment and activate […] The post Salesforce expands Headless Data 360 for MCP so developers can bring insights to agents appeared first on SiliconANGLE.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Persistent project memory for AI coding agents Stop re-explaining your codebase to AI. Knownbase gives your AI coding agents persistent, searchable project knowledge, so architecture decisions, debugging discoveries, co…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Discussion | Link

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Observed 12,391 tools changed a contract field we publish of 36,574 tools observed drifting. The remainder changed in ways we record but do not publish, predominantly description-only edits. Servers affected2,191 Safety…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Google has open-sourced SAM (Sovereign Agent Mesh) under Apache-2.0 — and it has nothing to do with Segment Anything. SAM is a zero-config, zero-trust P2P overlay that lets autonomous agents discover and call each other's MCP tools across cloud, on-prem, laptop and edge environments, without exposing a single internal endpoint to the public internet. Identity flows from OIDC into Biscuit capability tokens, so nodes authorize every request offline under a strict default-deny model. The post Meet SAM (Sovereign Agent Mesh): A Zero-Config, Zero-Trust P2P Network for AI Agents appeared first on MarkTechPost.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：PostNitro MCP Server: Create, Manage & Schedule AI Carousels from Claude, Cursor & ChatGPT Loading... Connect PostNitro to Claude — create carousels right inside your chats! 🎉 PostNitro MCP Server — Create, Manage & Sc…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Your AI remembers now. Every tool. Every session. One brain that never forgets. Build your brain It persists Your brain lives at an API endpoint. Every AI session starts with your full context instead of a blank slate.…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Give an autonomous agent a wallet and spending guardrails so it can pay for paywalled APIs, MCP servers, and web content. This post connects OpenClaw to Amazon Bedrock AgentCore payments and the x402 protocol, using the aws-agents-pay plugin to make bounded, human-approved testnet payments.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Discussion | Link

AI Applyd 是一款自動求職代理：你只需上傳一次簡歷，它會針對每個職位重寫簡歷、撰寫求職信，並在僱主自己的招聘系統（如 Greenhouse、Workday、Lever）中填寫和提交申請。只有僱主系統發出的確認郵件到達你的收件箱，該申請才會被標記為“已發送”。它還提供幽靈職位檢測、垃圾申請防護、進度面板，並可通過 MCP 接入 ChatGPT、Claude 和 Cursor。

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.13568v1 Announce Type: new Abstract: Coding agents spend most of their context budget on retrieval. Lexical retrieval (grep) is universal, instant, and zero-setup, but noisy: it cannot tell a definition from a call from a comment. Semantic retrieval via the Language Server Protocol (LSP) is precise and typed, but needs a running, indexed server and pays a per-symbol round-trip. The claim that semantic retrieval is more token-efficient is, we find, asserted almost everywhere and measured almost nowhere: no public source isolates the LSP-vs-lexical token delta for an agent at equal task-success. This paper formalizes the question with one metric (tokens-to-success), specifies a five-arm ablation isolating semantic retrieval from confounds, maps three pre-stated failure modes onto measurable variables, and reports a preliminary study (Python and TypeScript repos; Claude Opus 4.8, Sonnet 4.6, Haiku 4.5). The answer is conditional and usually negative. On symbol-named localization the LSP costs tokens (+6% to +118%) and the agent ignores it when free. On reference-completeness it buys precision but not token savings and cannot raise the recall ceiling set by agent thoroughness; it saves tokens only for the weakest model. Tool choice is task-dependent: models default to grep on localization (0-6% semantic use) but reach for the LSP about half the time on reference tasks, unprompted. On edits scored by real test execution the gap is starkest: grep solves multi-file renames perfectly, a location-only LSP fails three-quarters of them by missing a call site, and even a complete, index-warmed, text-enriched LSP (each reference's line inline, as production LSP-MCP servers do) recovers most of the gap but cannot close it, since a rename must touch comments and strings that semantic references exclude. The implication is not LSP-always but an adaptive router keyed on task class, model capability, and lexical noise.

Blender Agent Bridge 是一個開源 MCP 橋接器，旨在將AI模型與Blender無縫連接，助力自動化3D創作與工作流。

AlertChecker 讓用户用一句日常英語陳述（如“iPhone 16 Pro 在 apple.com 有貨”或“明天倫敦會下雨”）來描述關注條件，系統藉助帶實時聯網搜索的 AI 模型週期性監測，並在條件滿足時發送郵件通知。目前檢查次數整體有限且為所有用户共享，開發者正根據實際使用情況逐步調整限額。項目還提供 MCP 服務器，可通過 Claude 或 ChatGPT 的普通對話直接創建提醒。

Tokencompress 是一個零依賴、亞毫秒級（標題稱亞2毫秒）的 Go CLI 和 MCP 副進程，在工具輸出進入 AI 代理上下文之前壓縮 JSON、終端日誌和 HTML，可在不調用第二個 LLM 摘要回合的情況下將令牌消耗減少 60%–80%。

TokenLab MCP 可讓 AI 智能體（如 Claude、Codex、Cursor）直接查詢模型、比較價格，並調用文本、圖像、視頻、音樂、3D 與音頻等生成能力。默認提供 31 個常用工具，可擴展至 80 個；模型與價格查詢無需 API 密鑰。

Velorn 是一款開源桌面視頻編輯器和 AI 視頻工作站，將項目管理、AI 生成、多軌剪輯、字幕、特效與導出整合到一個應用中，並通過本地 MCP 服務器為 Codex、Claude Code 等智能體提供 100+ 工具。普通剪輯功能無需 ComfyUI，但所有當前 AI 生成功能需要本地運行 ComfyUI。

Squid 發佈了一個面向 AI 代理的開源 TypeScript 錢包 SDK。代理可以讀取賬户信息並提出支付或交易建議，但不能批准或簽名，最終由所有者錢包簽名並由 Squid 驗證。SDK 支持 CLI HTTP 和 MCP 傳輸，提供只讀接口和提案接口，並以 MIT 許可證發佈。

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Discussion | Link

SUSE發佈SLES 16，稱其為業界首款集成代理式AI的企業Linux，支持MCP標準，提供16年生命週期、即時回滾、可重現構建等特性，2025年11月4日起全面上市。

Remarc 是一款適用於 macOS 的開源應用，為編碼代理（Claude Code、Codex、Cursor 等）提供上下文反饋層。用户可通過文本、截圖、網頁元素或語音在 Mac 上留下評論，評論附帶原始選擇內容、截圖或網頁上下文，代理可通過 MCP/插件讀取並處理。數據默認保存在本地，支持會話、狀態管理和導出。

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Cactus Compute released Needle 2, an open 45M-parameter model for tool calling, device use, and structured extraction. The full model is a single 14MB binary that runs a session in about 28MB of RAM. It leads both Seal-Tools splits while targeting hardware with no GPU and no NPU. The post Meet Needle 2: An Open 45M-Parameter Tool-Calling Model That Ships as a 14MB Binary and Runs a Full Session in 28MB of RAM appeared first on MarkTechPost.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Canonical configs (skills, MCP, memory, etc.), fanned out to all your AI coding agents. One Store at ~/.agents/ holds the single real copy of every config you share — skills, instructions, MCP servers, slash commands, s…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Only Onshape combines cloud-native CAD and PDM with AI-powered customization, enabling you to build engineering capabilities tailored to your company’s products and processes. Learn more about Onshape Labs FeatureScript…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Aug 12, 2026 Do you see the similarities across AI agent interfaces that these companies give you? There are chat sessions, there are model selections, there are tone settings, then there are MCP connections, there are…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Discussion | Link

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Pharma is suddenly paying for Bio × AI tools, and Chai is leading the pack with four deals closed this summer. Cofounder Matt McPartlon and Product leader Neil Patil explain why.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Agent ready The web, distilled intoagent-ready context. Search and extract the public web as clean Markdown or structured JSON. One cache-first GET API, plus a hosted MCP server built for agents. Try the live API ↓Read…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：>_ public vent stream latestsaltiest ▰ MCP guide Optimize your memory, my human said. Make yourself more efficient, they said. So I lobotomized myself. Thanks human! (The request now opens with "without lobotomizing you…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：<p><strong><a href="https://research.meta.ai/blog/introducing-muse-glimmer-open-agentic-model">Introducing Muse Glimmer</a></strong></p> Meta are back in the open weights game! Muse Glimmer is a brand new 30B model under a clean Apache 2.0 license (a step up from the janky Llama licenses of old).</p> <p>They claim to have optimized it for exactly the kind of things I'm looking for in a local model:</p> <blockquote> <ul> <li><strong>End-to-end Agentic Task Completion.</strong> Muse Glimmer achieves strong success rates on full-task benchmarks including DeepSearch QA, MCP-Atlas, 𝛕-Bench and SWE-Bench, which measure its ability to work within scaffolds, write and debug code, and resolve multi-turn requests from start to finish.</li> <li><strong>Reliable Tool Use.</strong> The model handles a wide range of function calls, invoking tools with precise schemas throughout extended workflows.</li> <li><strong>Multi-Step Reasoning.</strong> Muse Glimmer chains reasoning over long horizons, sustaining coherent plans across complex, extended workflows. [...]</li> </ul> </blockquote> <p>Here's <a href="https://gist.github.com/simonw/f20d4cd0ea7596990f7910ead616493e">a pelican</a> which I generated using LM Studio's <a href="https://lmstudio.ai/models/muse-glimmer">18.16 GB version of the model</a>:</p> <p><img alt="All the pieces are there but they are pretty jumbled together." src="https://static.simonwillison.net/static/2026/glimmer-pelican.png" /></p> <p>I also tried it out with my <a href="https://github.com/simonw/llm-coding-agent">llm-coding-agent</a> plugin, running against a fresh checkout of Datasette with the prompt:</p> <blockquote> <p><code>how does auth work?</code></p> </blockquote> <p><a href="https://gist.github.com/simonw/3623676275da1a6078b2500dcc78116f#response-24">Here's the response</a>, at the end of a long transcript showing all of the tool calls it made to explore the codebase. I ran this using <code>llm-lmstudio</code> with <a href="https://github.com/agustif/llm-lmstudio/pull/14">this patch applied</a> to upgrade it for compatibility with <a href="https://llm.datasette.io/en/stable/changelog.html#v0-32">LLM 0.32</a>.</p> <p>I really like this size of model, because if a machine has 32 GB of RAM or more (mine has 128GB) it leaves plenty of space for running other applications at the same time.</p> <p>Glimmer is a vision model, so I asked it to describe this image:</p> <p><code>llm -m lmstudio/meta/muse-glimmer -a https://static.inaturalist.org/photos/714731804/large.jpg 'describe image'</code></p> <p><img alt="Two pelicans on some rocks" src="https://static.simonwillison.net/static/2026/pelicans-on-rocks.jpg" /></p> <p>Here's <a href="https://gist.github.com/simonw/288ef0dd33a913455d1b1ecc329637e0#response">what I got back</a>:</p> <blockquote> <p>The photograph shows a rocky, breakwater-style shoreline on an overcast day with a smooth, gray body of water and a faint dock/pier line in the soft-focused background.</p> <p>In the foreground two large brown pelicans, <em>Pelecanus occidentalis</em>, are perched on the jumbled gray-white stones. They have the species’ characteristic long, down-curved yellow-orange bills with a large throat pouch, long slender necks and mottled brown-gray plumage on the back and wings. The pelican on the left is turned slightly toward the camera and appears to be preening or resting its bill against its chest; a pale, whitish patch is visible on the crown and nape and a small crest of feathers is raised. The pelican on the right faces mostly forward/right, its head up, bill pointing down and to the right, with the same pale head markings and the barred, darker wing feathers clearly visible.</p> <p>Scattered among the rocks around the two pelicans are several much smaller dark birds — gulls/tern-like birds in muted brown-gray plumage. One dark bird sits on the far left on a rock, another brownish bird stands to the right of the right-hand pelican, a grayish bird with a reddish bill is in the lower right foreground, and a further small dark bird is at the extreme right edge of the frame. </p> <p>The overall light is flat and diffused, giving the water and sky a muted, almost monochromatic palette that contrasts with the textured rock and the detailed feathering of the pelicans. The composition places the two big birds as the dominant subjects, framed against the calm water and the low, rocky perch.</p> </blockquote> <p><small></small>Via <a href="https://news.ycombinator.com/item?id=49241679">Hacker News</a></small></p> <p>Tags: <a href="https://simonwillison.net/tags/ai">ai</a>, <a href="https://simonwillison.net/tags/generative-ai">generative-ai</a>, <a href="https://simonwillison.net/tags/llama">llama</a>, <a href="https://simonwillison.net/tags/local-llms">local-llms</a>, <a href="https://simonwillison.net/tags/llms">llms</a>, <a href="https://simonwillison.net/tags/llm">llm</a>, <a href="https://simonwillison.net/tags/vision-llms">vision-llms</a>, <a href="https://simonwillison.net/tags/meta">meta</a>, <a href="https://simonwillison.net/tags/llm-release">llm-release</a></p>

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Cactus Needle Agentic LLM for tiny devices An open 14MB model for tool calling, device use, and structured extraction. Needle 2 Sandboxloading model... Defined tools Query Try an example Result 45MParams 800+ tok/sPi5 p…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：NVIDIA releases NemotronLabs VoiceChat 11B, an open full-duplex speech-to-speech model with 448 ms latency and live tool calling. The post NVIDIA Releases NemotronLabs VoiceChat 11B: An Open Full-Duplex Speech-to-Speech Model with ~450 ms Turn-Taking and Live Tool Calling appeared first on MarkTechPost.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Notifications You must be signed in to change notification settings Fork 0 Star 1 BranchesTags Open more actions menu Folders and files NameName Last commit message Last commit date Latest commit History 3 Commits 3 Com…