02:30
Promptim: an experimental library for prompt optimization
Automate prompt engineering with Promptim's optimization library. Save time, improve AI performance, and switch models faster.
Today's news
Products & applications / 01Fable 5.2 and Jagged AGIOne Useful Thing
01 / IN FOCUS
Fable 5.2 and Jagged AGI
One Useful ThingData & engineering / 02Introducing ClickHouse Security in private preview, built on RunRevealClickHouse
02 / IN FOCUS
Introducing ClickHouse Security in private preview, built on RunReveal
ClickHouseCompute & infrastructure / 03b12229llama.cpp releases
03 / IN FOCUS
b12229
llama.cpp releasesAI NEWS × FOXAIFind your next step
Explore AI tools From the latest news to tools that work for you.
Discover AI tools
Swipe to explore →K
KiroCoding & development
AI ShortWriting & content
JAXModels & infrastructure
EvoMapAgents & automation
MemoAIMusic & audio
Open DesignDesign & 3D
妙播Marketing & commerce
IamIPIndustry applications
ElicitKnowledge & research
ClipDropImages & editing
KiroCoding & developmentKiro is an AI engineering tool for developers that organizes requirements into specifications, architectures, and tasks, generates code via agents, and supports the entire workflow—from planning to code review—through property-based testing, execution memory, and integration with development tools.
分类推荐榜首AAI ShortWriting & contentAIS ALERT MANAGEMENT AND SHARED PLATFORM, QUICK COMMAND FOR MULTIPLE SCENARIOS
分类推荐榜首JJAXModels & infrastructureJAX is a Python numerical computing library designed for accelerators, specifically tailored for high-performance array computations and large-scale machine learning. It efficiently executes the same code across multiple hardware backends, including CPUs, GPUs, and TPUs.
分类推荐榜首EEvoMapAgents & automationEvoMap is an infrastructure designed for the reuse of AI agent experiences. It organizes reusable strategies and repair assets with validation records via the GEP protocol, offering market- and quality-based ranking to help different agents discover, evaluate, and inherit existing capabilities.
分类推荐榜首MMemoAIMusic & audioMemoAI is an AI-powered audio-to-text tool that supports localized processing, eliminating the need to upload data and ensuring privacy and security. It can efficiently transcribe YouTube videos, podcasts, and local audio/video files (such as MP4, MP3, AAC, M4A, etc.) into text, while offering core features like multilingual translation, speaker diarization, real-time subtitles, and floating notes—making it ideal for meeting minutes, interview transcription, content learning, and more.
分类推荐榜首OOpen DesignDesign & 3DOpenDesign is an open-source design workspace that can connect to local programming agents, use built-in model keys, or leverage cloud-based models, enabling the creation and editing of prototypes, web pages, presentations, and graphics within a design system; local software is free, while model services incur fees.
分类推荐榜首妙妙播Marketing & commerceTHE AI LIVE TELECOM SOLUTION FROM THE AD
待评分 · 分类列表推荐IIamIPIndustry applicationsIamIP is a patent platform that provides AI-driven search, analysis, and monitoring tools to help users conduct patent research and management more efficiently.
待评分 · 分类列表推荐EElicitKnowledge & researchElicit provides semantic search, research report generation, literature screening, and data extraction for scientific research. It enables traceable answers within source materials and organizes evidence through a literature library, research agents, and ongoing tracking workflows, making it ideal for advancing from initial problem exploration to systematic reviews.
待评分 · 分类列表推荐CClipDropImages & editingClipdrop is a suite of AI-powered image creation and editing tools, covering background removal, local cleanup, image enlargement, upscaling, relighting, text removal, and background replacement. It allows users to process images directly in the browser and also provides developers with an API for integrating these capabilities into their applications.
待评分 · 分类列表推荐AI, as it happens
1532 published storiesAgents & automation · 65 storiesClear filters ×
2026-11-10
Follow the timeline02:30
LangSmith BYOC on AWS is generally available
LangSmith Bring Your Own Cloud is now generally available on AWS, giving Enterprise teams managed observability, evaluation, and deployment inside their own VPC.
00:23
What Is Eval-Driven Development? How to Improve AI Agents
Eval-driven development helps you build AI agents against a consistent set of metrics. Define good behavior, write the eval first, then compare experiments.
2026-11-09
Follow the timeline16:25
n8n@2.46.7
The n8n 2.46.7 update addresses a bug related to excessive resume attempts for waiting and queued executions within the core system, improving stability and reliability.
16:21
n8n@2.47.3
The n8n 2.47.3 update addresses a bug allowing only workflow editors to own migration findings, improves scheduled task cleanup by retiring stale tasks in batches, and adds the ability to open migration reports directly from notification emails.
2026-11-08
Follow the timeline22:07
Send contracts for e-signature from n8n, with TurboDocx, Slack approval and SharePoint filing
This Verified Node Spotlight is a guest post written by Nicolas Fry, CEO of TurboDocx.The deal is closed and the contract is ready. It's been sitting in someone's inbox for three days, waiting for an "OK, send it." Once it's finally
2026-11-06
Follow the timeline13:00
The Two-Ledger Model: Transaction-Grain Cost Accounting for Multi-Agent AI Systems Across Clouds, Models, and Systems of Record
arXiv:2611.06989v1 Announce Type: new Abstract: Enterprises run business transactions through multi-agent AI systems spanning clouds, large language models (LLMs), orchestration harnesses, and systems of record. Finance receives AI cost only at settlement grain, aggregated by SKU and charge period. The business question (what did this order, claim, or case cost in AI?) cannot be answered from billing data, because providers never see enterprise transaction boundaries. The FinOps Open Cost and Usage Specification (FOCUS) gives billing data one schema across providers but remains settlement-grain even as it adds AI token and requester attribution. We formalize this grain mismatch, derive seven requirements, and propose the Two-Ledger Model: a settlement ledger of FOCUS-conformant billing data joined to an attribution ledger of invocation-grain usage records built on OpenTelemetry GenAI telemetry. A layered correlation spine (trace context, A2A/MCP metadata, business-key correlation, probabilistic matching) assigns each record to its business transaction with recorded method and confidence; a versioned rate card prices usage in near real time; period reconciliation ties both ledgers to the invoice, and the unexplained residual identifies shadow AI. Costs are reported per order, claim, or outcome with agentic cost metrics. A simulation with known ground truth shows the spine sustaining cost coverage above 99% as trace propagation falls to zero, the reconciliation residual recovering planted unmetered spend within 0.24 percentage points while flagging provider billing errors, and mid-flight gating cutting p99 transaction cost by up to 61% at a 2-4% false-pause rate. We propose the attribution ledger as an invocation-grain FOCUS profile for standardization.
04:03
Agents Are Going Async
Async subagents let an agent stay responsive while background workers run long tasks. How the orchestrator, notifications and approvals work in Deep Agents.
2026-11-05
Follow the timeline13:00
VirtualTrialHarness: Coordinating Agentic Operationalization of Virtual Trial Protocols Across Complex Clinical Schemas
arXiv:2611.05551v1 Announce Type: new Abstract: Virtual trials use routinely collected clinical data to evaluate treatment strategies, but translating a study protocol into an executable analysis requires determining how clinical concepts and study requirements should be represented in the available data and applied consistently across the workflow. These decisions depend on local data representations and operational conventions and can involve source selection, patient and encounter identity, linkage, and temporal interpretation. Here we introduce VirtualTrialHarness (VTHarness), an agent framework that coordinates virtual-trial operationalization by selecting reusable procedural skills for each workflow stage and uses explicit contracts to maintain consistent study decisions across stages. We also introduce VTBenchmark for evaluating source selection and cohort construction. Across three complex synthetic environments, VTHarness successfully produced all required cohort outputs matching the references in 95.1% of workflows after requirement clarification, compared with 60.4% using retrieval from the same procedural corpus. Procedural skills improved source recovery across three language models and increased source overlap with analyst code in 13 Mayo Clinic cases. Site-specific adaptation enabled reference-matched cohort execution across eight MIMIC-IV tasks. Within the Mayo Clinic Virtual Trials Program, the framework supported investigator review of cohort construction and endpoint analysis. These findings support coordinating procedural guidance with workflow decisions to improve virtual-trial implementation across complex clinical schemas.
2026-11-04
Follow the timeline21:50
n8n@2.47.2
The n8n 2.47.2 update resolves an issue that prevented npm installation of n8n from working on all platforms, restoring compatibility and functionality.
21:10
n8n@2.46.6
The n8n 2.46.6 update resolves an issue that prevented npm installation of n8n from working on all platforms, restoring compatibility and functionality.
17:40
n8n@2.47.1
The n8n 2.47.1 update introduces features to enhance the migration report experience, including hiding archived workflows by default and displaying a message when the report takes time to load.
17:37
n8n@2.46.5
The n8n 2.46.5 update addresses several bugs, including fixing the AI Agent Node's deprecated agent type callout, improving credential resolution for node parameters, and enabling reading named array keys in expressions. New features include hiding archived workflows by default in migration reports and displaying a message when the migration report takes too long to load.
15:36
v1.19.0 - Trace Your Workflows, Layer by Layer
Dify 1.19.0 enhances observability with nested workflow tracing, allowing users to follow execution steps inside Workflow Tools, inspect LLM calls, and maintain context across nested invocations. The release also enables portable app packages via App packages, improves Agent file uploads and previews, introduces Skill Hub automation through CLI commands, and upgrades the bundled plugin daemon to version 0.6.14-local. Key changes include support for format v2 app packages, enhanced security, improved editing workflows, and updated environment variables and API endpoints.
13:00
MCPGuard: Finding Conformance Gaps in MCP SDKs via Dual-Track Analysis and Dynamic Adjudication
arXiv:2611.03662v1 Announce Type: new Abstract: The Model Context Protocol (MCP) connects large language model agents to external tools and services through official SDKs that implement message validation and session logic. Specification constraints omitted by these SDKs may propagate to downstream applications, highlighting the importance of SDK-level conformance testing. Yet existing MCP conformance tools mainly exercise running endpoints and reveal little about whether SDK models enforce specification requirements. We present MCPGuard, an automated LLM-based framework for detecting specification-to-SDK conformance gaps. Its structural track aligns JSON Schema constraints with normalized SDK models and produces constraint-specific evidence. Its behavioral track extracts normative prose rules, retrieves bounded function-level slices, and audits them with LLMs for candidate omissions. An evidence-aware dynamic adjudicator then inspects complete source context and builds PoCs to validate candidates. A shared kernel with language-specific adapters enables analysis across SDKs. On the official Python 1.26.0 and TypeScript 1.29.0 SDKs, MCPGuard confirms 13 and 19 findings, respectively, none of which are exposed by two black-box baselines. Tests on open MCP servers further show that these gaps can systematically propagate downstream. By making SDK conformance of specification constraints directly testable, MCPGuard complements conventional endpoint-oriented conformance suites.
13:00
Rethinking Next-Visit Diagnosis Prediction Beyond Aggregate Metrics: Retrieval--Memory Multi-Agent Adjudication
arXiv:2611.03826v1 Announce Type: new Abstract: Next-visit diagnosis prediction forecasts the diagnoses documented at a patient's next encounter, turning retrospective electronic health records into prospective clinical prediction. However, conventional aggregate evaluation obscures its multifaceted nature: distributionally, models must handle variable-size diagnosis sets and long-tailed labels; temporally, they must distinguish persistent, newly recorded, and recurrent diagnoses; and both vary with observed history depth. We introduce an evaluation framework along these dimensions and apply it to rule-based heuristics, LLM-based prompting, retrieval, memory, and multi-agent approaches. This reveals that repeating the last visit outperforms most LLM-based approaches overall despite predicting no new or recurrent diagnoses, and that retrieval and memory exhibit distinct profiles whose relative strengths vary across temporal transitions and backbones. Motivated by this, we propose LONGINUS, a retrieval-memory multi-agent adjudication framework combining evidence retrieved from patient records with structured memory of the patient trajectory. Using cross-view agreement as a reliability heuristic, it preserves shared predictions and adjudicates disagreements without revealing their source. Across MIMIC-III and MIMIC-IV with four LLM backbones, LONGINUS achieves the best transition-specific performance among LLM-based methods in nearly all settings while remaining competitive with them on aggregate metrics.
2026-10-30
Follow the timeline16:26
n8n@2.46.3
## [2.46.3](https://github.com/n8n-io/n8n/compare/n8n@2.46.2...n8n@2.46.3) (2026-10-30) ### Bug Fixes * **core:** Add a cooldown before resending migration owner reminders ([#42567](https://github.com/n8n-io/n8n/issues/42567)) ([724efc3](https://github.com/n8n-io/n8n/commit/724efc352f51a52910924789b79cf66770807e09)) * **core:** Resolve IMAP trigger expressions after activation ([#42612](https://github.com/n8n-io/n8n/issues/42612)) ([17594a7](https://github.com/n8n-io/n8n/commit/17594a7eefa42bc37f532af35c4f38eb1986bbc5)) * **core:** Return user data with an __isError key as data in expressions ([#42490](https://github.com/n8n-io/n8n/issues/42490)) ([9fe595e](https://github.com/n8n-io/n8n/commit/9fe595e1b83179b54ac5768d03c5f90f9c409f16)) * **editor:** Show the workflow project under its name
16:24
n8n@2.45.7
core: Require execution:read when workflow-scoped routes read execution data (#42446) (93638f4)
2026-10-29
Follow the timeline22:06
Quoting Ben Hylak
every product i use should just be a headless mcp, that feeds into an agent, where i never have to think about anything underneath.
17:00
n8n@1.123.90
1.123.90 (2026-10-29) core: Require a signed token to accept an invitation (#42292) (4580f22)
Every update links back to its source.