iCreatAI News
Back to main site
Skip to content
Only Products
Nov 6Fri
  1. Pydantic AI Articles36

    Pydantic AI is now a supported agent in AgentEnv Framework

    Scale AI's open source AgentEnv Framework, which builds reproducible environments with realistic apps, data and multi-step tasks for testing agents, now supports Pydantic AI as an agent that runs in process with the Coder capability from Pydantic AI Harness. The post explains configuration via an OpenAI-compatible endpoint, a mail-mcp example bundle with a task that deploys the environment, prompts the agent and runs a verifier, and notes that swapping a2a_agent_id to claude-code lets you compare agents on the same task.

  2. Hacker News AI42

    IDE extension that keeps me in control of AI-written code

    Pair Flow is a VS Code extension that pauses before planning and before every code change, requiring the developer to approve a plan and inspect each small diff (at most three files per chunk) before any source file is modified. It supports OpenAI, Anthropic, Gemini, OpenRouter and Ollama endpoints, stores API keys in VS Code SecretStorage, and keeps unapproved proposals in workspace-local storage for restart recovery. The project is an early public preview under the MIT license, with a JetBrains version in review and no shell commands executed automatically in this release.

  3. Hacker News AI8

    AI Bicep Heart

    Bicep Heart AI is a browser-based tool that animates a single uploaded photo into a silent 7-second vertical video of the viral bicep heart pose, with a two-person mode for couples. Plans range from $4.99 for one 480p video to $31.99 for five 720p videos, credits don't expire, and photos are deleted after 7 days. The site states the pose spread on TikTok in late October 2026 and that it is unrelated to the duo Bicep or their track "Heart".

  4. Hacker News AI58

    Show HN: Mantis – AI agents browse 36% faster than with Playwright MCP

    Mantis is an MCP server that lets AI agents browse the web as short, numbered text instead of screenshots, and works with Claude Code, Codex, Cursor or custom agents. In the author's benchmarks against Playwright MCP's accessibility tree, long tasks used 29-47% fewer input tokens, 29-37% fewer calls and about a third less time, while short tasks used 35-57% fewer input tokens with equal or better accuracy. Limitations include no canvas input, login and bot walls requiring ask_human with a display, and benchmarking only on read, navigate and form-fill tasks with two models.

  5. Hacker News AI15

    Show HN: Stitch.ai – New all-in-one workspace with Stitchy the AI assistant

    Stitch.ai launched this week as an all-in-one workspace combining mail, calendar, contacts, tasks, notes, sheets, slides, files, boards and forms, with auto-generated Knots and Tags for labeling work and a "Stitching" feature to link items such as tasks to events or emails to notes. It also introduces Stitchy, an AI assistant that writes emails, schedules events, manages tasks and runs jobs like watching for email replies or sending daily project updates. Signing up provides an @stitch.ai email address with no integrations needed, and the team offers a free 7-day trial while asking the HN community for feedback.

  6. Codex Releases10

    rust-v0.169.0-alpha.1

    This GitHub Changelog entry lists the release tag rust-v0.169.0-alpha.1. The supplied material contains only the page's navigation and product menu text, with no release notes or details about the version.

  7. Hacker News AI20

    Open AI Cellular: Open platform for prototyping and testing AI based 6G

    Open AI Cellular (OAIC) describes its mission as providing an open platform for prototyping and testing artificial intelligence-based controllers enabling 6G research. The page announces the OAIC-T v2.0.0 release, which adds RANFusion, a simulator of 5G core network component behaviors and performances, with InfluxDB support, KPI metrics, AI fuzzing using genetic algorithms to generate UE traffic for testing traffic balancing methods, and example test scripts. It also lists past workshops, tutorials and talks, and notes NSF sponsorship under fund numbers 2120442 and 2120411.

  8. Hacker News AI48

    Axiom – blocks AI agents from inventing limits your code never defined

    Axiom is a zero-dependency local guardrail that runs as a pre-write hook in Claude Code and Cursor, or as a stdin/stdout filter for other agents, blocking tool calls before writes occur. It uses regex and AST-pattern detection across three components (Noema, Lemma, Manam) to catch hardcoded numeric bounds, auth bypasses, dangerous Bash, secrets, dependency confusion and invented rate limits, with a tri-state TRUE/FALSE/UNKNOWN logic that halts on UNKNOWN. The author states detection is not semantic and can be bypassed with minor obfuscation, positioning it as a first line of defense alongside container isolation, branch protection and secret scanning.

  9. vLLM Blog42

    VeRL-Omni v0.3.0: Async Training and Broader Multimodal Post-Training

    VeRL-Omni v0.3.0 adds asynchronous and decoupled RL execution paths across multimodal workloads, makes the TransferQueue/ReplayBuffer-based V1 trainer the default, and moves the rollout stack to vLLM 0.30.0 and vLLM-Omni 0.30.0. It includes end-to-end recipes for MiniMax H3 audio-video post-training with DiffusionNFT and MiniCPM-o 4.5 AVQA GSPO, where a 4×H800 experiment found separate-async about 9% slower per prompt at natural response lengths but roughly 6.7% faster at 1024 tokens. The release also expands model and algorithm coverage, adds Ascend and AMD ROCm Dockerfiles, and notes upgrade changes including V1 as default, named diffusion media artifacts, and fail-closed attention backends.

  10. Hacker News AI31

    Show HN: Lab Canary – Rating AI labs on whether their staff can speak up

    Lab Canary is a public scorecard that rates what is publicly known about AI labs' staff contracts and speak-up policies against a seven-clause standard: protect real secrets, never gag criticism or whistleblowing. Ratings draw only on public evidence—published policies, public statements and credible reporting—with each rating linked to its source, and "Not public" is shown separately rather than treated as neutral. The site is a single HTML page with public data files on GitHub under the MIT licence, built by an author who discloses having applied for jobs at Anthropic, OpenAI and Google DeepMind.

  11. Codex Releases22

    0.167.0

    Codex 0.167.0 adds an agent command center opened with `codex agents --no-daemon`, unread-result markers in the command center and session picker, cross-backend session switching from the terminal picker, local image attachment previews, and a Google Cloud Vertex AI setup wizard. Bug fixes keep saved chats visible across model provider changes, preserve transcript history when Ctrl+L clears the terminal, and resolve network approval prompts when their requests end. Documentation and chores cover managed network constraints under [permissions.network], DotSlash manifest updates, and reduced jemalloc arena counts for Linux musl builds.

  12. Hacker News AI22

    Show HN: Open-world text adventure played through AI agents

    Eremoterra lets you pick any parcel of Earth, hand a prompt to an AI agent such as ChatGPT, Claude or Cursor, and have it describe and build on that patch as if no one had ever lived there. Trying a patch is free for a night; keeping it costs USD 1, a price that rises about 0.7% each time another 0.1% of the planet's 233,280,000 parcels is claimed and doubles every 10%. Patches carry a server-rendered chronicle of events, can be shared by link without an account, and can be populated by a people you define.

  13. The Verge · AI58

    Perplexity launches its own take on AI agents for work

    Perplexity has launched always-on "Teammates" that can take on multiple roles within a workspace, pulling existing projects, skills, and memory from Perplexity tools, and building on Perplexity Computer to support collaboration and ongoing, large-scale work. Each Teammate can be assigned different jobs that run simultaneously, with progress tracked through individual threads in the Perplexity app and interaction available in Slack, but the feature requires the $200/month Max plan. CEO Aravind Srinivas said on X that the company envisions "every org having hundreds of teammates working for each person."

  14. Hacker News AI71

    AgentSight: System-wide AI agent profiling and monitoring with eBPF

    AgentSight is a local-first, top/strace-like observability tool for AI agents that uses eBPF and TLS traffic tracing to connect prompts, model calls, and tool decisions to their real effects on the machine, without requiring an SDK, proxy, or vendor integration. It works with existing agents such as Claude Code, Codex, Gemini CLI, OpenCode, and OpenClaw, offering live session views, process/file/network tracking, saved SQLite session reports, a web UI, and OpenTelemetry export. The project is MIT-licensed and installable via Homebrew, Cargo, release binaries, or Docker, with eBPF requiring Linux kernel 4.1+ and sudo access for live capture.

  15. Sierra Blog40

    Accelerators take care of the basics

    Sierra describes Accelerators, prebuilt packages for high-volume workflows such as order tracking, appointment scheduling, claims intake and ID verification, which come with basic integrations and guardrails and are customized for a business using Ghostwriter. Accelerators are maintained by Sierra but track customer changes separately so updates can be reviewed before being applied, and they connect to a company's existing software systems. The first Accelerators are available today in Agent Studio, with user-built and shareable Accelerators planned.

  16. AWS Machine Learning Blog53

    Getting started with Web Answer on Amazon Bedrock AgentCore

    Amazon announced the general availability of Web Answer on Amazon Bedrock AgentCore, a managed Gateway tool that takes a natural-language question and returns a synthesized answer with source citations in seconds, replacing a self-built search, retrieve, synthesize, and citation pipeline. The post contrasts it with Web Search (which returns ranked URLs and lets you keep your own model), then walks through granting the Gateway service role bedrock-agentcore:InvokeWebAnswer, creating a Web Answer target, and calling it from a Strands agent. It is available in us-east-1 at $10 per 1,000 tool calls, with a 10 transactions per second per account rate limit.

  17. Hacker News AI58

    VSL Performer (AI generated orchestral tracks)

    Vienna Performer is a DAW plug-in from Vienna Symphonic Library that takes your MIDI and renders a performance using models trained on recordings of session musicians at Vienna Synchron Stage, adding phrasing, bow direction, vibrato and timing without changing your notes. It works as VST3, AU and AAX in DAWs and in Dorico and Sibelius, and is sold on monthly or yearly plans from €9.99 to €49.99 with metered performance minutes, where one minute equals one minute of one instrument performed. Renders are four-channel audio files that are yours to use commercially, including after cancelling, and rendering requires an internet connection.

  18. Cursor Changelog78

    Build Live Apps in Cursor

    Cursor now lets users build and deploy live apps directly from the editor: a cloud agent scaffolds the web app, sets up a Postgres database if needed, configures authentication behind Cursor SSO, provisions hosting, and returns a shareable link at a chosen domain. Publishing runs deterministic and agentic security checks, and nothing goes live until checks pass and the user explicitly publishes; team admins can view all apps and secrets, add review rules, approve blocked publishes, and unpublish apps. The capability is available on all paid plans with cloud agents enabled, deploying from new or existing repos on Cursor Origin and GitHub, with GitLab support coming soon.

    Why it matters: It documents a new Cursor deployment feature with concrete details on setup, security guardrails, and admin controls that teams evaluating internal app tooling would find useful.

  19. Hacker News AI55

    Show HN: Agentshield Zero-leak kernel sandbox and secret defense for AI coding

    AgentShield v1.2.0 wraps AI coding agent processes (Claude Code, Cursor, Windsurf, Codex, Antigravity) in OS-level kernel sandboxes, using Bubblewrap plus Landlock on Linux, Seatbelt on macOS, and AppContainer on Windows to trap unauthorized syscalls and block credential exfiltration via CIDR egress filtering. It also redacts environment secrets in memory, offers a Ctrl+. QuickFix redactor for exposed keys, and prevents agents from reading /proc/self/environ or ~/.ssh. A Pro tier adds a macOS/Windows menu-bar GUI, cloud audit log backup, and centralized policy sync.

  20. Hacker News AI33

    AI SRE Teammate

    Sera is an AI SRE teammate that, when an incident opens, checks alerts, recent code changes from tools like GitHub and GitLab, observability data and past incidents to surface a likely cause with a confidence level and supporting evidence. It integrates with ServiceNow, Datadog, Grafana, Slack, MS Teams, Jira and 250+ other tools, and the vendor cites results including 95% alert noise cut at Chalo, 60% lower incident management cost at Razorpay, 37% MTTR reduction at Cisco and <5 min ack at Bajaj Finserv Health. It offers data isolation and an audit trail with SOC 2 certification, plus an interactive demo walkthrough.

  21. Hacker News AI22

    Wallet screening your AI agent can call over MCP

    Prax offers free wallet screening exposed over MCP at https://mcp.orabrain.com/mcp, so Claude, ChatGPT, Cursor and VS Code can call screen_wallet natively to check sanctions, exploits, phishing, scams and mixer exposure with readable reasons. The free tier allows 10 lookups a day with a work email and no card, and a REST/OpenAPI option is also available.

  22. NVIDIA Newsroom58

    Vera Delivers the Best of Both Worlds: Highest Throughput and Fastest Agents

    NVIDIA says its Vera CPU outperforms both the fastest and the most energy-efficient x86 CPUs in a 100-megawatt data center comparison, delivering 1.6x more agents per watt versus the fastest x86 CPU and 2x faster agent speed with leading energy efficiency versus the most energy-efficient x86 CPU. Early adopters report production-style gains, including Perplexity running agentic coding tasks 1.5x faster, DeepInfra reaching up to 2.2x the speed of the best x86 processor on agentic orchestration, and ClickHouse scaling near-linearly across 176 cores on its standard binary. Daytona brought 1,000 agent sandboxes online in 10.8 seconds versus 88.4 seconds with x86, and Modal achieved up to 2x sandbox throughput per core versus comparable x86 hardware.

  23. TechCrunch · AI60

    Meta says US users can now video chat with their Muse AI avatar

    Meta announced that Muse Voice, which lets U.S. users call and video chat with its consumer AI agent Muse, is now available to everyone in the U.S. The feature, first shown at Meta's September Connect conference, uses new Muse Realtime Avatar and Muse Realtime Voice models to power a customizable animated avatar that responds with expressions and gestures matching the conversation's tone. Meta plans to bring real-time conversations to its AI Glasses and an upcoming "Muse Charm" device, following a Tamagotchi-like wearable it intends to launch before year-end.

  24. The Verge · AI58

    Muse has a voice mode now

    Meta CEO Mark Zuckerberg announced that Meta's Muse AI agent now supports real-time voice conversations, with avatars that animate in sync with the agent's speech. Users can adjust the voice tone by asking the agent or through avatar settings. The voice mode and expressive avatars are rolling out now in the US for the app, with support coming "soon" for Meta's AI glasses and its forthcoming Muse Charm gadget.

  25. World Labs Blog58

    Frameboy: Atlas in Real-time

    The team behind Atlas, an autoregressive world model that generates frames one at a time with pixel-perfect camera control, released Frameboy, a research preview that streams frames from cloud GPUs to a browser at up to 15 fps as the user controls the camera. Frameboy serves a highly optimized Atlas variant, and the real-time capability is also integrated into Viewfinder, a web app (currently in closed beta) for building scenes frame-by-frame and exploring them live via a streaming Frameboy overlay. The post argues that faster generation lowers the cost of a "bad idea" and shifts interaction from cautious manual prompting toward intuitive exploration.

  26. Hacker News AI40

    Show HN: Resilient AI Worker Queue with Redis, BullMQ, and Budget Kill Switches

    This post presents a production template for running fault-tolerant AI agent queues with automatic model failover across providers (OpenAI, Anthropic, Groq, Ollama), jittered exponential backoff retries, and a Redis-backed token-budget kill switch that halts jobs before exceeding spend limits. It uses BullMQ and Redis for dead-letter queues and concurrency limits, plus structured logging for Datadog, Grafana Loki, or CloudWatch. The community edition is MIT-licensed, with a $39 enterprise license adding dashboards, distributed rate-limiting middleware, and setup guidance.

  27. Hacker News AI58

    Show HN: Replay three AI agent approval failures in five seconds, in Python

    Call4Agents is a zero-dependency Python library that adds once-only actions, approvals bound to exact arguments, undo, idempotency keys and record/replay/diff to existing agents built on LangGraph, Pydantic AI, the OpenAI Agents SDK, MCP or plain Python. Its `call4agents incident` and `call4agents quickstart` commands reproduce crash-and-resume double actions (e.g. 2 emails without the kit, 1 with it) in real processes, and version 0.6 is Apache-2.0 with an optional PostgreSQL backend for multiple machines.

  28. Hacker News AI58

    Show HN: Tokenome – code provenance for AI-assisted work, on your machine

    Tokenome is a local-first tool that links each line of code to the AI chat conversation that produced it, capturing transcripts from Claude Code, Claude Desktop, ChatGPT and Gemini and indexing them on your own machine via a CLI, web UI and MCP server. It reports a measured 38% reduction in context tokens with no measurable change in answer quality, and offers an optional self-hosted Team server (in free beta, $24 per seat per month afterward) that mirrors redacted project segments for team-wide search with attribution. Individual use on one machine is free, with no account, cloud embeddings or data leaving the device.

  29. The Verge · AI60

    Claude AI can plug directly into your bank account

    Anthropic is launching a Personal Finance feature that connects Claude to bank and card accounts through the Plaid platform, letting users ask questions like where their money went this month and get spending breakdowns by category. Access is read-only, Claude cannot move, manage, or invest money, and it does not see banking passwords, though it can view account names, balances, credit limits, and up to two years of transaction history. The beta rolls out this week to Claude Pro, Max, and Ultra subscribers in the US, following a similar ChatGPT feature introduced in May.

  30. TechCrunch · AI62

    Claude can now analyze your spending with its new Personal Finance tool

    Anthropic announced that Claude is gaining a "Personal Finance" tool that lets users connect bank and credit card accounts through Plaid and ask questions about their finances, with read-only access that cannot move, manage, or invest money. The tool summarizes spending by category, flags potential issues like duplicate charges and unexpected fees, and explains financial concepts such as APR, and it is rolling out in beta this week to Pro, Max, and Ultra plan users in the U.S. Anthropic says conversations in the Personal Finance hub are not used to train its models.

  31. Claude Blog36

    More visibility and control over Claude Enterprise for security teams

    Anthropic announced new Claude Enterprise security and admin features, including a security center that compares organization settings with Anthropic's recommended configuration, generally available prompt and pre-tool-call inference hooks that send prompts and tool calls to existing data security tools, and centralized management with a parent-organization admin console at admin.claude.com. New access controls let admins sign members out via the Admin API, manage their own IP allowlist, and block personal and outside Claude accounts in Claude Desktop on managed computers, while an EDR integration runs an organization's sensor inside the Cowork virtual machine. The security center, centralized management, Admin API sign-out, self-serve IP allowlist, and Claude Desktop settings management are in beta, and EDR in Cowork is in beta on macOS and Windows for Claude Team and Enterprise.

  32. Claude Blog70

    Introducing Personal Finance in Claude

    Anthropic is launching Personal Finance in Claude, which lets users in the US securely connect bank and card accounts through Plaid with read-only access and ask questions about balances, transactions and spending in everyday language. It starts rolling out in beta this week on the Pro, Max and Ultra plans in the US, and Claude cannot move, manage or invest money, shows no ads or sponsored recommendations, and does not offer its own financial products. Conversations in the Personal Finance hub are not used to train models, accounts can be unlinked anytime, and Anthropic says Claude can make mistakes, so important figures should be checked with your bank.

    Why it matters: It documents a concrete new Claude capability along with its access limits, data-handling terms and beta availability, which matters to anyone weighing whether to connect real bank accounts.

  33. Codex Releases10

    0.168.0-alpha.6

    This page is a GitHub Changelog entry titled "0.168.0-alpha.6," but the supplied material consists only of site navigation and product menu text (Platform, Copilot, Actions, Codespaces, Advanced Security, pricing, etc.) with no release notes or details about the version.

  34. Amp Chronicle40

    GitLab Integration

    Amp now integrates with GitLab on gitlab.com and self-managed instances, letting users start projects from GitLab repositories and giving Orbs a signed-in glab so the agent can open and comment on merge requests and read issues and pipelines. Amp can subscribe to comments and CI for merge requests it opens, and users can ask Amp to start a new orb for every new merge request or issue in a project, managed under Settings → Integrations & MCP → GitLab. Each person connects GitLab in Settings → Integrations & MCP, then a group Owner installs Push Updates once for the workspace.

  35. Hacker News AI42

    Show HN: Magertron – AI Orchestrator for agents' tools, APIs, LLMs and streams

    Magertron is an AI orchestration platform that governs model inference and tool calls across vendors through a single Envoy-based gateway, with features including MCP server lifecycle management, a governance policy engine, RBAC, and OCSF-aligned audit events. It offers a free tier for up to 20 MCP servers with no signup, plus Pro ($499/mo), Business ($30,000/yr), and Enterprise plans, and ships an Apache 2.0 CLI called mcpctl. Version 4.2.32 adds OPA support.

  36. Mastra Blog34

    Introducing Latency Metrics for Mastra Observability

    Mastra now records TTFC (time to first chunk) and TTFT (time to first token) on every span, from model calls up to agent runs, so traces, spans, and threads can be filtered and sorted by these metrics on Mastra platform and Studio. The metrics work on self-hosted projects using DuckDB, PostgreSQL, or ClickHouse, and are queryable via the Mastra CLI ([email protected]+), Client SDK (@mastra/[email protected]+), and observability endpoints. Studio support requires [email protected] and @mastra/[email protected] or later.

  37. NVIDIA Technical Blog25

    Configure, Certify, and Operate Kubernetes GPU Clusters with NVIDIA DSX OS

    NVIDIA DSX OS addresses the problem that a single underperforming GPU can slow an entire distributed training job, even when the node passes basic health checks and shows normal utilization, so operators may only discover the issue once the workload is running. The article notes these issues can surface at any point in a cluster's lifecycle, since a GPU cluster that passes readiness checks at handover changes as nodes are replaced and drivers are patched.

  39. Hacker News AI38

    Basemodo: AI lets anyone build. We let anyone deploy

    Basemodo is a hosting service for apps built with AI agents, offering deployment via a CLI command or an MCP server for tools like Claude Code, Codex and Cursor. Each app is private by default, comes with sign-in, a SQLite database, daily backups, cron, logs and secrets, and is reachable at a basemodo.app address plus two custom domains with HTTPS. Plans start at $5 per month for one app, and invited users never pay.

  40. Hacker News AI34

    The AI Times – wake up to a printed paper, not a feed

    The AI Times is a self-hosted project that turns RSS feeds into a personalized morning newspaper, emails it at 6:00, and AirPrints it to a Wi-Fi printer at 6:05, with a pause/resume option for when you're away. It uses Python agents for news gathering, morning delivery and printing, plus a Next.js app for composing dense A4 layouts with daily puzzles, and supports BYOK news prompts via OpenAI, Claude, Gemini, Groq, Ollama or an offline desk. The code is on GitHub under the MIT license.