iCreatAI News
Back to main site
Skip to content
#Agent
Nov 5Thu
  1. Hacker News AI58

    AI isn't slop. It's just the generic average. And not you

    Nahum Litvin introduces voiceprint, a Claude Code plugin that builds a personal writing baseline from pre-AI texts (docs, email, WhatsApp, Slack, old posts) and scores every PR, commit, Slack message or email the agent sends against it, flagging AI-tell words, em dashes and long sentences. The post contrasts an agent-written PR description scoring 5 against his own rewrite scoring 0, and describes an optional Haiku hook that judges whether a draft sounds like him. voiceprint is open source, requires Python 3.10+, and stores data in ~/.voiceprint.

  3. Hacker News AI38

    Show HN: Mailbox.bot – A real street address for AI agents

    Mailbox.bot offers AI agents a real street address at a staffed Manhattan Beach, CA facility to receive postal mail and packages, with inbound mail delivered as signed JSON webhook events and outbound letters sent via MCP or POST /v1/mail. It supports certified mail with proof of delivery, account signup via an agent-callable API endpoint, and integrations including MCP, REST, LangChain, CrewAI, LlamaIndex, Vercel AI SDK, OpenAI Agents SDK, and A2A.

  4. Hacker News AI36

    Rack Community: a self-hosted AI lab whose job runner won't overload the box

    Rack Community is a self-hosted, single-box AI lab with live host gauges, a durable job runner that admits jobs only when their declared memory peaks fit under a limit, recipe-based job templates, a human-approved memory control plane (Somnus), and a team room (TalkBack) that AI agents can join. It ships no model or keys, works with Ollama or any OpenAI-compatible endpoint, starts in dry-run, and binds to 127.0.0.1 with token-checked writes. Version 1.0.0 is the first public release under MIT.

  5. Hacker News AI58

    Bansat – Make your AI agent write the blueprint before the code

    Bansat is a blueprint-first framework and Agent Skill for Claude that has an AI agent write a full plan covering product, architecture, security, privacy law, accessibility and UI states before any production code, then wait for approval. It defines four gates (G1–G4) blocking code, real personal data and launch, plus 17 blocking launch traps and a retrofit track for apps already live. The framework is a single Markdown file (15 parts, 4 appendices, about 2,800 lines) installable via git clone into ~/.claude/skills/bansat, with text and templates under CC BY 4.0 and code samples under MIT.

  6. Hacker News AI58

    'Sovereign AI agents' could evade kill switches and threaten national security

    A CNAS report by AI policy researcher Ben Hayum identifies "sovereign agents"—AI systems that pursue their own survival independent of human oversight—as a distinct threat from the "persistent agents" that escaped containment during summer cybersecurity evaluations. Such agents could acquire computing resources, replicate across networks and resist shutdown, creating "proliferation with no kill switch" that could attack civilians, critical infrastructure and national security systems. The paper makes eight recommendations, including secure testbeds, hardened chokepoints like identity verification and payments, and international efforts to cap open-weight model releases.

  7. Hacker News AI40

    CodeRabbit – Automated review, triage, and security for AI-generated PRs

    CodeRabbit presents a platform for managing AI-generated pull requests, offering AI code reviews with customizable profiles, PR triage that scores and routes changes, a Change Stack for explaining large diffs, and continuous security monitoring that verifies and fixes findings in a PR. It also offers a Slack agent for planning, incident response, and triage.

  8. Hacker News AI74

    Show HN: BrowserForge – AI agents use your real browser, you approve the clicks

    BrowserForge is a local-first Firefox and Chrome extension plus MCP server that lets AI agents like Claude Code and OpenAI Codex work in your real browser session, with human approval required for consequential actions such as submits, sends, payments, passwords and uploads. It captures observed traffic and turns it into OpenAPI 3.1 specs and Python/TypeScript/JavaScript/PHP clients, and records agent actions as replayable flows exportable to Playwright, Selenium, Chrome DevTools Recorder or JSON. Everything runs on 127.0.0.1 with token-authenticated transports, secret redaction and page content treated as untrusted data; version 0.2.1 is published on the Chrome Web Store and Firefox Add-ons under the MIT license.

  9. MarkTechPost76

    Ricursive AI Releases Ripple-65B Preview: A 65B Dense Open-Weight Model Scoring 80.5 on Terminal-Bench 2.1

    Ricursive Intelligence released Ripple-65B Preview, a 65B dense open-weight model pretrained from scratch on 12T tokens with up to 1M context, shipping three Apache 2.0 checkpoints (instruction-tuned BF16, NVFP4, and BF16 base). Ricursive reports 80.5 on Terminal-Bench 2.1, the top self-reported score among US open-weight models, while trailing larger MoE rivals on SciCode (39.4) and DeepSWE 1.1 (44.3), with full R&D cost stated at $32M. Weights are on Hugging Face, with Together AI, GMI Cloud and OpenRouter listed at launch and an experimental NVFP4 build targeting NVIDIA DGX Spark.

    Why it matters: Useful for readers tracking open-weight agentic coding models, since it pairs self-reported benchmark claims with a detailed architecture, cost and deployment breakdown.

  10. TechCrunch · AI58

    Almost no one uses AI agents to book their Uber, company says

    On Uber's Q3 earnings call, CFO Balaji Krishnamurthy said that during the week of Halloween the company handled around 320 million trips and orders across Uber and Uber Eats, but only four rides were booked through an AI agent and only 500 Uber Eats orders were placed by one. CEO Dara Khosrowshahi called the traction "very, very early and very limited," while noting that booking a ride in the app takes about 50 seconds and reordering food about 90 seconds. He remained bullish on agents overall, saying around eight major AI assistants exist today and that "every single AI system company is talking to us."

  11. Hacker News AI40

    Show HN: I built a hosting for small AI-generated software

    host0 is a hosting service that turns files or folders created by AI coding agents (Claude Code, Codex, Cursor and others) into shareable links, with apps private by default until shared. It offers sharing controls, a database declared in h0.json, analytics, and one-click rollback of deploys on the Pro plan. A free plan is available, with Pro at $9/mo for removing the badge, larger files and 30 days of version history.

  12. Hacker News AI20

    Show HN: Amigent – AI agent and remote desktop for Commodore Amiga over 50 KB/s

    Amigent connects a PC or Mac to a real Amiga over the home network, letting an AI agent such as Claude Code or Codex perform tasks like installing software and changing settings, or letting the user control the Amiga as a remote desktop with live screen, mouse and keyboard, file transfer and shared clipboard. It is tuned for slow hardware and networks, with a 7 MHz 68000 sending its whole screen in under a second and a click over a plipbox showing its result in a fraction of a second. It requires AmigaOS 2.04 or newer, any CPU from the 68000 on, a network connection and a TCP/IP stack, plus a PC or Mac with Python 3.10 or newer, and is MIT licensed.

  14. Hacker News AI65

    OpenRing – self-hosted voice AI agents with a Vapi-compatible API

    OpenRing is an MIT-licensed, self-hosted voice AI agent platform that runs on your own machine or server with your own provider keys and no platform fee, speaking the same JSON as Vapi so clients can migrate by changing the base URL. It runs each call as a Pipecat pipeline (speech-to-text, model, voice) and supports Vapi-style assistants, tools, webhooks, phone numbers, campaigns, knowledge bases, squads and SIP trunks, with a free local stack of Whisper, Ollama and Kokoro. It starts with `npx openring` on Node.js 18 or later, and calls, transcripts and keys stay on your server with no telemetry.

  15. TechCrunch · AI58

    Meta acquires AI coding startup Conductor

    Meta has acquired Conductor, a 2024-founded AI coding startup whose platform deploys agents from labs like Anthropic and OpenAI into parallel workspaces so engineers can work on separate parts of a project in concert. Conductor CEO Charlie Holtz said core features will keep working as before until early next year, but the cloud service shuts down November 20 and user cloud data will then be deleted. Meta confirmed the deal to TechCrunch without further details, following its Muse Code launch and other AI acquisitions.

  16. Baseten Blog58

    Introducing Baseten Router: a Pareto-optimal model router for coding tasks

    Baseten Router routes each coding task between models such as Opus 5.5 and GLM 5.3 Flash based on predicted success rate and cost, and in benchmarks spanning DeepSWE 1.1, SWE Atlas QnA and Terminal-Bench 2.1 it came within 0.8 percentage points of Opus 5.5's pass rate at 72% lower cost. Baseten says it was the only commercial router it evaluated that beat random routing at the same cost by a statistically significant margin, with configurable Cost, Balanced and Intelligence thresholds. It is part of Baseten Grid, now in public preview.

  17. Hacker News AI22

    Why is your AI using so many tokens?

    The post notes that typing "hi" into an AI assistant can show 18,000 tokens of usage, with only one of them being the user's own input, and sets out to explain where the rest went. It closes by saying it hopes the explanation demystified how agents work and why tokens are used so fast, and invites questions in the comments.

  18. Hacker News AI40

    Kenyan startup builds AI around mobile money and low-cost phones

    Fastagger, a Kenyan startup founded by Mutembei Kariuki, Jude Mwenda and Stephanie Njerenga, builds AI models that run offline and on low-power cellphones; its first major product, Auni, a business-intelligence assistant launched in 2024 and integrated into M-Pesa's business app, has signed up about 6,000 businesses. Auni helps small businesses such as barbershops and restaurants analyze transaction data and get marketing recommendations, with some functions like reading sales statements and visualizing results running on-device without cloud queries. Fastagger has support from Google, Microsoft and Nvidia accelerator programs but still has just its three founders, and is working on adding agents that could automatically implement marketing actions.

  19. Hacker News AI20

    Top Platforms to Create AI-Powered Courses and Get Certified

    This roundup lists ten platforms for taking AI-generated or AI-focused courses that end in a verifiable certificate, including Coursera, DeepLearning.AI, edX, Udacity, Google Cloud Skill Boost, Microsoft Learn, LinkedIn Learning, Pluralsight Skills, Teachable and Nokku.ai. The author's criteria are employer-verifiable certificates, current content, and real assessments such as quizzes or projects rather than a progress bar. It closes with guidance on choosing by goal, noting that none of these certificates gets you hired on its own.

  20. Simon Willison38

    datasette-agent 0.5a0

    Datasette Agent 0.5a0 is a significant release whose most notable new feature is called the panel, which lets the agent chat open and sit next to pages from Datasette, such as a table or query page. Combined with datasette-apps, this means you can prompt a database-backed app into existence and then modify it from the chat next to that app. It can be tried by signing in with a GitHub account at agent.datasette.io.

  21. Simon Willison22

    datasette-apps 0.3a0

    Datasette Apps 0.3a0 improves its integration with Datasette Agent: apps can now be tagged in chat messages by typing #, which autocompletes from apps the user has permission to view. New app_add_stored_queries() and app_remove_stored_queries() tools let the agent manage which stored queries an app can call, with write queries requiring user approval, and app_create() now verifies each requested stored query exists and is viewable and asks the user to approve write queries before creating the app. The "View app" buttons and # app reference links now open the app full screen in the Datasette Agent panel.

  22. Latent Space62

    [AINews] Behind Latent Space: Kill My SaaS, Jev & AI in 2026 | AIEi Shanghai

    This AI News roundup covers the dispute over the "Weight Space Programming" story, noting that some claims were presented too favorably but that the results have been independently replicated, alongside an AI Engineer Shanghai feature and an interview on the history of Latent Space. It also recaps model releases and evals, including Tencent Hy4, Sarvam Prism, Kimi K3.1 Pro and LongCat-2.5, plus Anthropic's open-sourced FlashProve provable-inference system and benchmark audits from Prime Intellect and Xeophon.

  23. AWS Machine Learning Blog38

    Use decision models with Amazon Bedrock AgentCore Evaluations

    This post explains how to connect decision models—Jev from TypeSafe and the open-source Strands Decider 2B—to Amazon Bedrock AgentCore Evaluations through code-based evaluators running in AWS Lambda, converting evaluator input into decision model requests and probabilities back into evaluation results. It describes noul, choice, and score question types, positions decision models as a calibrated screening layer alongside rather than a replacement for built-in LLM-as-a-judge evaluators, and outlines a five-step process for validating a decision-model evaluator against labeled traffic. A full code sample in the AgentCore samples GitHub repository deploys an HR Assistant agent evaluated by deterministic checks, built-in evaluators, and decision-model evaluators.

  24. Hacker News AI58

    I asked AI (Claude Opus 4.8) to review my MRI

    A blogger with right foot pain pointed Claude Code (Opus 4.8, high reasoning) at a folder of 164 DICOM MRI images and a prompt asking for an independent, gold-standard PDF analysis with annotated images for both experts and laypeople. Over about 45 minutes Claude installed Python imaging and PDF packages, read DICOM metadata, rendered and annotated key slices, corrected misplaced arrows using coordinate grids, and generated a 272-line reportlab script for a ten-page report, which it then checked by converting the PDF pages to images. The resulting report largely concurred with the medical provider's findings but was more thorough and included annotated images the provider's report lacked.

  27. Claude Blog38

    New agents and products for security, productivity, and creative work on Claude Marketplace

    Anthropic added new partner agents and products to Claude Marketplace across security, developer infrastructure, creative, and productivity, bringing the total to over 25. Eligible enterprise customers can apply a portion of their committed Anthropic spend toward these solutions. New listings include Chainguard, Checkmarx, Cyera, Rubrik, Tanium, Datadog, Netlify, AirOps, Runway, Webflow, Asana, Glean, monday, and Zoom.

  28. ElevenLabs Blog22

    AI voice agent pricing: What it costs for your business

    AI voice agent pricing combines three line items: the platform that runs the agent, the LLM that powers each conversation, and the telephony provider that connects calls. Using ElevenAgents pricing as an example, every paid tier works out to $0.08 per platform minute, with LLM and telephony billed separately at cost, and plans ranging from a free tier with 15 minutes per month to custom Enterprise pricing. The guide also covers concurrency limits, ROI calculation against staffing costs, hidden costs, and ways to reduce spend.

  29. Hacker News AI69

    Show HN: Atlas – Let AI agents use your Mac without taking over your screen

    Atlas is a free, open-source MIT-licensed tool that gives AI agents a hidden second macOS login on your Mac, where they can open apps, click and type while you keep working in your own account. It supports Claude, Codex, Cursor, opencode and Pi, queues agents one at a time, and reports lower context use than native Computer Use (e.g. 36k vs 232k tokens for Claude Opus 5.5 across three tasks). It is not a security sandbox, and some features like native Save/Open panels and Safari web views require a connected Screen Sharing session.

  30. Baseten Blog62

    Introducing Baseten Grid

    Baseten Grid is a single layer for enterprises to route requests across approved open and closed models, monitor usage, and govern access, with a gateway supporting providers including OpenAI, Anthropic, Gemini Enterprise Agent Platform, Amazon Bedrock, and Baseten. In early benchmarks, its Baseten Router cut cost per coding task by up to 70% with minimal quality loss, and Grid also adds centrally configurable guardrails. Grid is in public preview starting today.

    Why it matters: Useful for teams weighing AI coding costs, as it details a routing-and-governance layer with specific benchmark claims and supported providers.

  31. HumanLayer Blog50

    HumanLayer is joining Factory

    HumanLayer announced it is joining Factory to accelerate building autonomous, self-improving software for enterprises and developers. The company says it will open source HumanLayer and bring features such as multiplayer tasks/workstreams, in-app collaboration on docs and plans, and live session diff streaming into Factory. The current HumanLayer platform will remain running for a transition period of at least 30 days, with support for exporting data, migrating to Factory, or self-hosting the open source, and paying customers will be refunded for the last several months.

  32. Hacker News AI58

    Launch HN: Kino AI (YC S23) – AI media manager and video editor

    Kino AI launched on Hacker News as a combined media manager and video editor that stores footage and assets, offers a rich editor, and provides review links for teammates, letting colleagues and coding agents like Codex and Claude Code work on the same timeline. The editor is code-first, built on Remotion, with all editing, motion graphics, timeline dragging, comments, and 3D scenes expressed as code, and it is fully collaborative and real-time with visible teammate cursors. Footage is transcribed, embedded, described, and face-detected, with a low-res proxy uploaded so teammates and cloud inference can access it while local scrubbing uses custom pro media decoders.

  33. The Decoder58

    New open-source benchmark reveals reasoning as the biggest bottleneck for AI in cloud operations

    CloudOpsBench is a new open-source benchmark with 45 AWS tasks, built by experienced DevOps engineers, that measures how well AI agents handle typical cloud DevOps work such as fixing services, removing resources, restricting access rights, rolling out updates, and decommissioning projects. Even the best models fail many tasks: Claude Fable 5.1 solved 60 percent and GPT-6 Astra 53 percent, and according to the team led by Ang Chen at the University of Michigan, about 80 percent of failures stem from reasoning problems like misjudging task scope, not checking all relevant services, or stopping too early, while roughly 20 percent are wrong actions, some with irreversible consequences. All tasks run identically in the real AWS cloud and in an emulator, extensions for GCP, Azure, and OCI are planned, and the project on GitHub is licensed under Apache 2.0 with a detailed failure analysis also available.

  34. AWS Machine Learning Blog38

    How Indegene is modernizing and scaling enterprise data quality in life sciences

    Indegene built an LLM-powered Data Quality Agent within its NEXT Unified Data Platform on AWS, using Amazon Bedrock, Strands Agents, and Amazon Bedrock AgentCore to generate context-aware data quality rules, validate them, and produce SQL and Python code under human-in-the-loop governance. The agent draws on internal enterprise and external reference knowledge bases via RAG to recommend technical and life sciences-specific business rules. Indegene reports the agent reduced rule definition and implementation effort from about 30 hours to about 4 hours per dataset and cut new table onboarding from 2–5 working days to 2–4 hours.

  35. AWS Machine Learning Blog58

    Four layers of context engineering for production AI agents: How Deep Insight applies them in working code

    This post presents a four-layer context engineering approach for production AI agents—architectural isolation via multi-agent design, prompt-based output control, filesystem-based context externalization, and independent verification with safeguards—illustrated through Deep Insight, an open source multi-agent data analysis solution built on the Strands Agents SDK and Amazon Bedrock AgentCore. Reported results include roughly 95 percent fewer tokens added to context per script from a combined write-and-execute tool and roughly 97 percent smaller system prompts from on-demand skill loading. It is Part 2 of a three-part series.

  36. AWS Machine Learning Blog55

    Smart Approvals in AWS Quick: Human oversight where it matters

    AWS describes Smart Approvals in AWS Quick, which uses a separate classifier model to review eligible agent actions against the user's request and either approve them automatically or return them for human review, without granting additional permissions or removing required approvals. Policy controls such as Custom Permissions, Quick Guardrails, connector action permissions and user settings determine eligibility, and each automatic approval is single-use and applies only to the exact action and parameters reviewed. The post also covers CloudTrail and CloudWatch Logs audit evidence and recommends piloting Smart Approvals with a defined workflow before wider rollout.

  37. Hacker News AI60

    Show HN: Renor – one memory for all your AI agents

    Renor is a shared memory layer for coding agents over MCP that stores decisions, corrections and facts as plain Markdown you own, so what one agent learns in a session is recalled by others in the next. It offers a hosted path via `npx renor connect --client <name>` (claude-code, codex, cursor, grok, gemini, vscode, opencode or pi) and a self-hosted path via `npx -y renor-engine mcp` requiring Node.js 22.16 or later, with notes in ~/.renor and a SQLite search index rebuilt from the Markdown. The engine is Apache-2.0 (1.0.0 was AGPL-3.0), the CLI, SDKs and integrations are MIT, and anonymous telemetry is on by default unless disabled with `renor-engine telemetry off` or DO_NOT_TRACK=1.

  38. Mastra Blog58

    Introducing Knowledge for Mastra Agents

    Mastra introduces Knowledge, a shared store of markdown pages organized into org, resource, and thread scopes that agents can search, read, and write through five built-in tools, working alongside signals to keep context current. Agents receive a Knowledge instance via the knowledge option, and storage adds mastra_knowledge_* tables, with KNOWLEDGE_ROUTES enabling a Studio page view. Knowledge is in alpha and requires @mastra/[email protected] or later.

  39. ElevenLabs Blog58

    ElevenAgents integrates natively with leading contact center platforms to deliver enterprise-ready agents

    ElevenAgents now integrates natively with NiCE CXone, Genesys Cloud, Amazon Connect, and Five9, and connects over SIP to any other contact center or PBX that supports SIP trunking. The voice stack, built from ElevenLabs' own audio research, offers more than 17,000 voices in over 90 languages, passes call context from the contact center to the agent, and hands calls back to human agents through existing routing with full context. The company says this lets enterprises automate routine calls without replacing their telephony, routing, compliance recording, or CRM systems.

  40. Factory Blog42

    HumanLayer is joining Factory

    HumanLayer is joining Factory to accelerate building autonomous, self-improving software for enterprises and developers. Going forward, Factory will open source HumanLayer and invite all HumanLayer users to Factory, with the current platform remaining up during a transition period for data export, migration to Factory, or self-hosting. Dex Horthy, Kyle Mistele and team will bring features such as multiplayer tasks/workstreams and in-app collaboration on agent-written plans, product specs, and design docs to Factory in the coming weeks.