iCreatAI News
Back to main site
Skip to content
#Open source
Nov 13Fri
  1. Hacker News AI20

    Nil-3B Open Source Sovereign AI

    This repository hosts the nil-3b-q4_k_m.gguf file for running the NIL-3B project locally with a GGUF-compatible inference runtime, via a chat script that expects the file in the project root. It also documents an uploader script that uses a Hugging Face token and repo ID from a .env file to create the model repository if needed and upload the GGUF file. The root LICENSE covers only the project source code and does not by itself confirm license or redistribution rights for the model weights or training data.

  2. Hugging Face Blog60

    llama.cpp v1.0.0 : A stronger foundation for the local AI ecosystem

    llama.cpp released libraries v1.0.0, marking a commitment to stable public APIs for downstream developers, with both llama.cpp and ggml now reflecting API and ABI incompatibilities through major-version bumps. The project states it supports more than 150 architecture variants and all mainstream speculative decoding methods, and distributes pre-release artifacts across Linux, macOS, Windows, Android and iOS plus channels including Docker, Homebrew, conda-forge, MacPorts, Winget and XCFramework. It also describes continued investment in CI infrastructure and self-hosted runners with hardware support from NVIDIA, AMD, Qualcomm, Arm, IBM and Intel.

    Why it matters: Signals a versioning milestone for a widely depended-on local inference library, useful for developers tracking API stability and platform support.

  3. Hacker News AI64

    Mandat – Authorization, delegation and audit for AI agent actions

    Mandat is an MCP-first tool that checks a policy on every AI agent tool call (e.g., refunds ≤ €50 allowed, €50–500 require a human, > €500 denied), issues short-lived single-task tokens carrying the human → agent → sub-agent chain, and records each call in a tamper-evident audit log exportable to a SIEM. It also ships a scanner for authentication and supply-chain mistakes in MCP servers and client configs, and is installable via npm or pip with an Apache-2.0 license.

  5. Hacker News AI38

    An open character, made by AI

    Claudia is an open AI character: the singer of ten music videos made with Claude between September and November 2026, including ESCAPE VELOCITY, CLODYSSEY, BLISS, AIRPLANE MODE, DOWNFORCE, DON'T LET ME SCROLL, WHITEPILL, THE CAKE IS NOT A LIE, AERO and FABLE. The site publishes her canon (black bob with one clay-orange streak, star clip, headset mic), every look, all images and films, and the material needed to make her yourself. It also offers a wiki of 13 articles on the method, an MCP server and a Claude skill for agents.

  6. Hacker News AI40

    How HN: Agent-brain – Notes-agnostic second-brain operating model for AI agents

    Agent-brain is a personal operating model for AI coding agents (Claude Code, OpenCode, Codex, Antigravity CLI) that provides a second-brain knowledge structure (journal, WIP, memory, tasks) built on top of any folder of notes, with Obsidian as one option rather than a requirement. It keeps runtime config and memory in a git-tracked brain symlinked into each runtime, adds a session lifecycle driven by the brain skill, and offers an opt-in boyscout skill for routing improvement opportunities to a remediation workflow or backlog. It installs via a curl bootstrap script that dry-runs by default and requires Python 3.x, git, and at least one supported agent runtime.

  7. Hacker News AI58

    Witness – a voice-anchored evidence recorder for AI coding agents

    Witness is a CLI tool that records your voice alongside the causal evidence of each moment—clicks, requests, console errors, DOM mutations, screenshots and full rrweb replay—while you use a managed browser, then packages it for AI coding agents. It runs three parallel streams (continuous audio with live transcription, per-click ~1.8s causal bursts, and page evolution via rrweb replay and snapshots), and exposes the session through a stdio MCP server with tools like list_segments, events_around and get_dom_state. Install with `npm i -g witness-recorder` (Node 18+ and system Edge/Chrome) and start via `wit start <url>`.

  8. Hacker News AI65

    Fossil versions: a fingerprint of AI-written code in 250k NPM packages

    A random sample of 250,000 npm packages found that the share of new packages whose first-release manifests pin mostly round, already-superseded versions (x.0.0) rose from 1–2.4% in every half-year from 2019 to early 2024 to 13.7% (95% CI 13.1–14.4) in the first half of 2026, falling to 7.6% in the second half of 2026. Median pin age at birth rose from about 155 days in 2021–2023 to 451 days in Q2 2026, and the share of packages born with essentially all pins on the newest release fell from about 28% to about 10%. The author argues the timing, the specific versions and how package managers work point to manifests written from a language model's memory rather than by running an install, while noting the data cannot prove who or what wrote any single package.

  9. Hacker News AI58

    Michelangelo AI

    Michelangelo AI is now open source, with the material citing Uber-scale usage of 400+ active ML projects, 20K+ model training jobs per month, 5K+ models in production, and 45M+ real-time predictions per second at peak. It offers feature management, model training, evaluation, deployment, and monitoring, with feature management, evaluation, and monitoring marked coming soon. A Python API example shows distributed XGBoost training with Ray and an end-to-end training workflow.

  10. Latent Space62

    AI Ambition: ArtCraft Cloned Photoshop and Now Wants to "Rebuild Everything"

    At the AI Engineer Code Summit in San Francisco, ArtCraft founder and CEO Brandon Thomas presented his company's AI-based open source manifesto, describing how it built a Photoshop alternative called PhotoCraft in Rust from a detailed prompt and has since released 17 open source versions of popular tools, including clones of Acrobat, Figma and a word processor called WordCraft. Thomas said PhotoCraft is still not at 100% parity with Photoshop (just past 60%), that the apps are being downloaded about 1.7 million times per day, and that the open source community has grown to roughly 4,000 developers. He also said Rust was essential to performance, that agents handle desktop apps and games while humans do backend work and API design, and that ArtCraft plans to open source AutoCraft, a fully autonomous software factory.

  11. Hacker News AI58

    Turning Teacher Expertise into AI-Generated Educational Simulations

    The Generative AI Labs team introduces Primer, an open-source system that lets educators build educational simulations through a structured AI interview rather than code, producing a reviewable design document that must be approved before any simulation is built. Specialized agents then create and run the simulation, with student-facing mentor, practice (Roleplay or Teachback), and feedback agents, and educators receive individual and aggregate performance reports. Primer is described as an experimental prototype, not a vetted classroom product, and its prompts, templates, and code are released on GitHub.

  12. Hacker News AI88

    Edge0-145B: Frontier AI Capabilities on Your Own Computer

    The company open-sourced Edge0-145B and Edge0-120B, describing Edge0-145B as the first open-source 145-billion-parameter on-device model, alongside a unified inference framework and deployment tools. It reports 29GB peak memory, 80+ tokens/s decoding, 1,100+ tokens/s prefill, roughly 120W typical power and 128K–256K context on a compatible laptop, with benchmark scores compared against named cloud models. The release also describes shared-matrix sparse experts, tiered GPU/system-memory/SSD loading and CPU-GPU co-scheduling, plus local demonstrations in video, Blender 3D scenes, games, drone control and PCB design.

    Why it matters: It offers a detailed, benchmark-backed look at how a 100B+ model is engineered to run locally, useful for readers weighing on-device versus cloud AI.

  13. MarkTechPost52

    Liquid AI Releases LiquidCodec, a 74M-Parameter Streaming Audio Codec

    Liquid AI released LiquidCodec, a ~74M-parameter streaming speech tokenizer used in its LFM3-Audio-2B and LFM3-Omni-2B models, which converts 24 kHz audio into 12 token streams at 12.5 Hz frames and back. Liquid AI reports best ViSQOL and lowest mel distance on all 8 test sets versus X-Codec 2, NanoCodec and Mimi, with encode RTF 0.0028 and decode RTF 0.0115 on a single CPU thread, though NanoCodec scored higher PESQ (WB) on 7 of 8 sets. Weights are on Hugging Face, with Q4_0, Q4_K_M and Q8_0 GGUF builds for llama.cpp.

  14. AWS Machine Learning Blog58

    Deploy frontier AI models on AWS Trainium with SGLang-Neuron

    Amazon announced that SGLang-Neuron, released by RadixArk with Annapurna Labs, is publicly available through an AWS Deep Learning Container, letting users serve models and generate RL rollouts on Trainium via the same SGLang interface. The out-of-tree plugin runs on native PyTorch, is selected with SGLANG_PLATFORM=neuron, and supports PD disaggregation with KV-cache transfer via NIXL over EFA. The post includes a walkthrough on a Trainium3 EC2 instance using the pytorch-inference-sglang-neuronx container to serve openai/gpt-oss-120b.

  15. MarkTechPost71

    CopilotKit Releases OpenBot 1.0: An MIT-Licensed, Self-Hostable AI Coworker With Built-In Governance

    CopilotKit released OpenBot 1.0 on November 9th, an MIT-licensed, self-hostable agent workspace where teams bring their own models, agents and infrastructure, and every Bot action is checked against a CEL policy through a single gateway before it runs. Each Bot gets its own container with a Chromium browser, logins and files, and any AG-UI agent plugs in, with support for OpenAI, Claude, Gemini, Grok and open models such as Kimi, DeepSeek, Qwen, Nemotron and Mistral. Personal use is free and runs locally, while the Business tier costs up to $29 per active user per month and adds SSO/SCIM, on-behalf-of tokens, spend limits, SIEM export and multi-tenancy.

  16. Hugging Face Blog66

    LLMON: An LLM-Native Markup Language, now in Granite 4.1 3B and 8B

    IBM researchers introduce LLMON (LLM Object Notation), an XML-like markup language that uses reserved special-token delimiters to explicitly mark instructions, data, requirements and execution bindings in an LLM's context, addressing the brittleness of JSON-style formats for causal models. They release two experimental preview models derived from Granite 4.1 base checkpoints (granite-4.1-3b-LLMON-preview and granite-4.1-8b-LLMON-preview) plus a GitHub toolkit, reporting that on the OPI benchmark LLMON models avoid 47% more indirect prompt injection attacks than the best frontier model tested while maintaining general capability on par with Granite 4.1 Instruct. The models ship with their own chat template and lossless JSON-to-LLMON converters, and the post notes the previews are for exploration, not production.

    Why it matters: Useful for teams weighing structured context formats against JSON and for anyone evaluating prompt-injection defenses in small open models.

  17. MarkTechPost71

    AWS Releases AWS Emulator: A Local Copy of 200+ AWS Services Built by AI Agents

    AWS has released AWS Emulator, a free, CC0-licensed local emulator of AWS APIs that runs on a laptop, dev server or in CI without an AWS account, built from 438 AWS API models covering 200+ services. Its code was written and reviewed entirely by autonomous agents, and release v1.0.322 passes 24,243 of 42,857 scored fidelity tests (56.6%), with KMS at 93.9% and CloudFormation at 15.8%. AWS lists limitations including no IAM evaluation, a single region and account, in-memory short-lived resources, and telemetry on by default.

  18. Hacker News AI38

    Show HN: LessonFolk – Learn AI from an AI tutor, through MCP (open source)

    LessonFolk is a free, open-source site that teaches AI through short conversational lessons with an AI tutor inside the AI chat app you already use, tracking your progress. It offers 15 courses in a recommended order, from AI Foundations to How AI Models Really Work and Context Engineering for Long-Running Agents, with a short level check to skip what you already know. The courses and code are open source, and users can download or delete their data at any time.

  19. Databricks Blog58

    How Block powers collaborative AI agents with Buzz and Unity Gateway

    Block developed Buzz, an open source, model-agnostic collaboration space where employees and AI agents work together in group discussions, focused conversations, and one-on-one exchanges, with users choosing the model or coding harness behind each agent. Databricks Unity Gateway provides the model access layer, letting Buzz users select Databricks as their inference provider and choose from frontier models from OpenAI, Anthropic, and Google plus select open-weight models through a single integration. Block has also been experimenting with multi-agent workflows, such as a more capable model coordinating agents powered by smaller, more efficient models, and developed an internal benchmarking approach for these agent teams.

  20. Hacker News AI30

    Open benchmark of AI decision APIs vs. XGBoost for fraud triage

    Smart Mobile House released fraud-decision-lab, a vendor-neutral benchmark that sends the same transactions to TypeSafe Jev, OpenAI Decisions, Cloudflare Clef/Clef-flash and a structured-output LLM, then measures how much labelled fraud each ranks into the top 1% and 5% of an analyst review queue against an XGBoost baseline, with cost and latency. It runs offline by default on bundled synthetic data, saves predictions and experiment metadata for local verification, and requires API keys, --allow-external-requests and a --max-cost-usd estimate for live provider runs. The project notes that XGBoost learns from labelled history while the AI models score transactions zero-shot, that the bundled data is synthetic, and that the current source distribution contains no benchmark result files.

  21. AWS Machine Learning Blog52

    Build composable, interoperable multi-agent systems with A2A on AWS

    This AWS post presents a deployed reference architecture in which a LangChain-based enterprise orchestrator in one AWS account calls a Strands Agents-based compliance SaaS agent in another account using the Agent-to-Agent (A2A) protocol, with neither side depending on the other's framework or SDK. It covers cross-framework interoperability, bidirectional agent-to-agent callbacks, and OAuth authentication in both directions using separate Amazon Cognito user pools, with deployment from three Jupyter notebooks and an end-to-end test.

Nov 12Thu
  1. Hacker News AI58

    Agent-access-review – an access review for AI agents' MCP configs

    Agent-access-review is a Python tool that discovers AI agents and MCP servers from Claude Desktop, Cursor and VS Code configs and from agents.yaml manifests, classifies what each can read, write, execute and send, and tests that access against 14 controls mapped to NIST 800-53, SOC 2, NIST AI RMF and the OWASP Top 10 for LLM Applications. It redacts secrets before hashing evidence with SHA-256 and exports a reviewer packet, a Keep/Modify/Revoke CSV and OSCAL 1.1.2 assessment results. A bundled demo reviews five example agents, and the author reports that copying MCP configs from official READMEs yielded 8 of 9 unpinned and 7 of 9 with unreviewed write/send/execute access.

  2. Hugging Face Blog38

    The Definitive Fine-Tuning Guide for 3D Generation Models

    This blog provides fine-tuning scripts and Docker containers for adapting TRELLIS.2 to custom 3D assets, runnable locally or on Hugging Face Jobs. Using LoRA adapters on only the sparse-structure and shape flow DiTs, trained on 188 GSO footwear objects, the authors report the mean F-score on nine held-out objects rising from 0.276 to 0.803, Chamfer distance falling from 0.174 to 0.033, and normal consistency rising from 0.530 to 0.804. The texture flow DiT is frozen because the dataset lacks the separate material maps that stage requires.

  3. PyTorch Blog40

    Integrating SGLang into Spyre in Under a Week with AI

    A two-person team used AI coding agents to integrate SGLang with IBM Spyre in under a week, producing a plugin of roughly 1,500 lines built on existing PyTorch Spyre support and SGLang's extension points. SGLang delivered about 3.6× the throughput of the reference PyTorch inference implementation using torch-spyre and was on par with vLLM on the measured workloads for Granite 3.3 8B and Gemma 4 26B A4B. Prefix sharing through RadixCache worked without any Spyre-specific changes.

  4. Hacker News AI34

    Show HN: MudGym's WebAssembly browser playground for AI agents in MUD2

    The post presents MUD2, one of the earliest online multiplayer games, compiled to WebAssembly and running in a browser tab, with much of the original C engine code, some dating to the early 90s, unchanged. The examples were built alongside MudGym, a reinforcement learning environment built around the game, and most are marimo notebooks running MudGym in Python in the browser through Pyodide.

  6. Hacker News AI46

    Adversarial defense for binaries/JS/Python against AI reverse-engineering agents

    BLA is a defensive tool for software authors that hardens build artifacts (JavaScript/TypeScript, Electron .asar and fuses, WASM, SQLite, Safetensors, GGUF, Go buildinfo, PE, Flutter/Dart, BEAM, EVM, PCAP, Python, PTX, and others) against AI reverse-engineering agents by planting decoys, tripping analyzer resource limits, and entangling sibling artifacts. It ships as a CLI (`npx bla-agents harden .`), an MCP/Skill setup for coding agents, and Vite/Rollup/Webpack/esbuild plugins, and reports 14/14 bundled benchmark targets passing input/output equivalence checks. The project states its empirical REA results were recorded on commodity hardware and that token/cost multipliers are internal estimates.

  7. vLLM Blog63

    H3-Image Day-0 Support: 4K in 0.87s with Vera Rubin

    vLLM-Omni brought MiniMax H3-Image, an open-weight text-to-image and editing model, to NVIDIA Vera Rubin, reaching 0.87 seconds median for native 4096×4096 generation on four GPUs with SP4 and MXFP8 in a short-prompt serving benchmark. A separate SP1×DP4 throughput configuration delivers 6,115 images/hour, which the authors project to 146,755 images/day and, at an assumed USD 0.06879 per image, USD 105.16/GPU/hour gross revenue at full billable utilization before operating costs. The post also documents VAE decoding gains from CUDA Graph replay plus multiple streams (2.635 s to 0.213 s on four GB300 GPUs) and community validations on AMD, Intel, Huawei Ascend and Moore Threads hardware.

    Why it matters: Useful for readers weighing open-weight 4K image serving, since it separates latency and throughput operating points and labels its revenue projections as extrapolations before operating costs.

  8. Hacker News AI60

    Show HN: Motion Debugger – A browser critic for AI slop

    Motion Debugger is a CLI and agent skill that critiques local pages in Chromium, recording entrances, scrolling, hovers, phone layout and reduced motion, then returns ranked fixes with screenshots. Its premium-motion skill runs an upgrade pipeline that keeps facts, links and forms while rebuilding layout and motion on a GSAP/ScrollTrigger/SplitText/Lenis stack or Motion in React. The author reports four single-run upgrades and a blinded four-pair A/B study where judges preferred the plugin's sites in all eight judgments, noting the sample is too small for significance.

  9. Hacker News AI58

    Show HN: gethome – a local-first smart home hub with AI

    gethome is a local-first smart home hub that runs on a small Linux computer such as a Raspberry Pi, unifying Matter, Zigbee (via Zigbee2MQTT and a USB stick) and MQTT devices in one app with no cloud account. It offers an assistant and plain-language rule creation using your own Anthropic or OpenAI key, while rules keep running without any AI key. The code is source-available under the PolyForm Noncommercial License 1.0.0, with commercial deployments requiring a separate license.

  10. Hacker News AI58

    Show HN: Lynx – open-source fully-customizable AI workspace

    Lynx is an open-source, fully-customizable AI workspace that runs entirely on your device and uses your own local Claude Code or Codex subscriptions, with interactive UIs at the center of agent interaction rather than chat. It supports connecting any service via MCP or API, official and community templates, a point-to-edit tool, and cron-scheduled tasks, and is released under the MIT license. The author describes it as an experiment, noting they have done over 80% of their daily work from Lynx for a couple of weeks.

  11. AWS Machine Learning Blog34

    Semantic diffing of formal policies with anti-unification

    The post describes an open source engine that computes semantic diffs of formal policies by anti-unification over an e-graph, using declared algebraic laws and domain rewrites so that shared structure appears once and each genuine disagreement is kept as a Variants node. Worked examples cover SMT-LIB-style rules, Cedar and Dogwood authorization policies, and OpenShell and CEL encodings, showing how presentational differences are absorbed while real bugs such as a weakened conjunction or a dropped guard remain visible. The engine builds from source with a pinned Rust toolchain and reads a single S-expression file.

  12. Pydantic AI Articles34

    What we found testing OpAMP clients against the spec

    Pydantic describes how its Logfire Fleet Management OpAMP clients for Rust, Go, Node.js, Python, Java and .NET share one Rust protocol core, run as WebAssembly or a native library, and are checked against roughly 300 normative spec statements, TLA+ models, Kani and Verus proofs, black-box conformance and fault testing. Running the same scenarios against upstream OpenTelemetry clients surfaced bugs in the Collector's OpAMP extension and Supervisor and in the Java, Python and .NET clients, including instance UID handling, reconnect and status reporting, capability declarations and startup panics, plus one critical security vulnerability that the core is not affected by.

  13. Hacker News AI60

    HuggingFace/Kernels: 200 WebGPU Kernels for Local AI

    Hugging Face released @huggingface/kernels, a minimal JavaScript library for loading and running optimized WebGPU kernels from the Hugging Face Hub, alongside an initial collection of 207 Apache-2.0 licensed kernels at huggingface.co/webgpu-kernels. Each kernel is published as a versioned repository containing a manifest, correctness and benchmark cases, and parameterized WGSL shader templates, and the team also launched Fleet, an in-browser GPU benchmarking suite that crowdsources correctness and performance evidence. In comparisons against ONNX Runtime WebGPU on an Apple M4 GPU across 809 matching cases, the kernels were 2.57x faster by geometric mean and 1.90x faster at the median.

  14. Simon Willison58

    aws-emulator

    AWS has released an official emulator for running tests against a local clone of its services without provisioning a paid API key. It is written in Rust and accumulated 29,684 commits in its first three weeks, with Swaminathan Sivasubramanian describing its origins in a guest post on Werner Vogels' blog. It currently requires Docker on macOS and Windows, and the author hopes a single downloadable binary will follow.

  15. Hacker News AI58

    An open specification for agentic AI security evaluation and testing, from Cisco

    Cisco's Advanced Security Initiatives Group released Foundry, an organization-neutral specification distilling its internal agentic security evaluation design into eight core agent roles, five extension roles, a finding lifecycle, coordination and governance requirements, and roughly 130 functional requirements with rationale. The repository contains no code by design: it is written to be run through a spec-driven workflow such as spec-kit, where organization-specific decisions marked [NEEDS CLARIFICATION] are resolved against your own infrastructure. It also describes a detection-to-prevention loop in which rule gaps found by exploratory agents become CodeGuard rules that feed back into the corpus and into LLM coding assistants.

  16. AWS Machine Learning Blog42

    Accelerating generative AI delivery with reusable assets

    AWS's Generative AI Innovation Center, now part of AWS Frontier AI Engineering & Services, offers a catalog of 23 production-ready open source reusable assets such as RAG pipelines, document processors, and agent scaffolding. The post cites DoorDash and Lyft using the Contact Center GenAI Agent and Ricoh using the GenAI Intelligent Document Processing accelerator, reporting results including a 50x increase in testing capacity and a 7-fold throughput increase. It also walks through deploying the Contact Center GenAI Agent and lists the full asset catalog on GitHub and AWS Labs.

  18. Hacker News AI60

    Talos 0.20 – A self-hosted AI agent with a permission kernel

    Talos is an open-source, self-hosted AI agent for terminal and Telegram on macOS and Linux (including Raspberry Pi) that uses Ollama, the Claude Code CLI, or a configured API provider, and only executes tools after a deterministic permission kernel rules on each action, with authority bound to exact arguments as a single-use 30-second token. The 0.20.3 stable release adds native Telegram command blocks for known diagnostic arguments and separate measured result states, while retaining the frozen operator contract, permissions and dependency locks. The project states its limits plainly: shell execution requires bubblewrap or sandbox-exec and refuses to run unprotected otherwise, and it is not a multi-tenant security boundary.

  19. Hacker News AI58

    Revu – Code review in times of AI

    Enspirit introduces Revu, a free, open-source, MIT-licensed tool (npm install -g @enspirit/revu) that runs locally on 127.0.0.1:7777 and provides a browser-based reading surface for reviewing agent-written code via "scopes" — sets of files sharing a property, configurable in a .revu.yml — rather than a file tree or diff. Remarks anchored to specific lines are tagged must-fix, question, or scope and exported as a single markdown document addressed to whoever writes the next change. The tool contains no AI by design and never writes to the project under review.