iCreatAI News
Back to main site
Skip to content
#Open source
Oct 29Thu
  1. Hacker News AI22

    When AI Does the Work, What Will Humans Do?

    A software developer argues that as AI agents take over tasks, the experience people accumulate while doing that work becomes a valuable but uncompensated input, and that systems should preserve, verify and reuse that experience across agents. He points to Stack Overflow's 2024 OpenAI partnership as an early sign of the unsettled link between contributed knowledge and compensation, and warns that outsourcing too much thinking could erode the human judgment AI depends on.

  2. Hacker News AI58

    Show HN: ThreadShelf – Obsidian and AI chats: vector search, MCP, llama.cpp

    ThreadShelf is a local-first archive that parses exports from ChatGPT, Claude, Google AI Studio, OpenRouter, LM Studio and Grok into a common format, embeds them locally and stores them in LanceDB for semantic and exact search. The same index is reachable through a React UI, CLI, HTTP API and an MCP stdio server, and archived threads can optionally be continued with a loopback-only llama.cpp GGUF model or the explicitly external OpenRouter provider. It also connects Markdown/Obsidian vaults for local note search and bounded tool-calling workflows, with vault writes off by default.

  3. Hacker News AI58

    C# and NATS.io for agentic AI orchestration

    This post argues that production agentic AI systems are distributed systems, and introduces the open source Synadia Agent Protocol for NATS, a contract (not a framework or runtime) that lets agents of any kind be discovered, prompted, and monitored on a single NATS fabric. The protocol defines three responsibilities—discovery via NATS micro service ping/info on the "agents" service, conversation via typed JSON chunks streamed to a reply inbox with a mandatory first ack and a zero-byte terminator, and liveness via heartbeats on agents.hb.{agent}.{owner}.{name}—along with a subject hierarchy, request envelope, and error reporting conventions. Reference SDKs exist in TypeScript and Python, with chunked attachments, JetStream at-least-once delivery, stronger identity, and audit traces deferred to future extensions.

  4. MarkTechPost60

    MiniMax Open-Sources MCode Stack: 15 Agent Skills Its Coding Team Uses Daily

    MiniMax has open-sourced MCode Stack, a MIT-licensed collection of 17 SKILL.md skills, 5 checklists and 5 companion notes that its MiniMax Code team uses daily, installable into MiniMax Code (Node.js 22.19+) or Claude Code. The skills cover planning and splitting, context and tool budgets, long sessions and commands, review, and experiments and hotfixes, and pair with MCode Engineering Notes; no benchmarks or eval results are published.

  5. Databricks Blog36

    Voice Agents are here. Context turns them into real customer value.

    Databricks argues that voice agents are now practical because synthetic voices sound natural and can respond within roughly 200 milliseconds, but that most enterprise AI investment has focused inward on employee assistants rather than customer conversations. It describes a prototype in which LiveKit carries calls, Deepgram handles speech-to-text, ElevenLabs adds voices, and Databricks supplies the "brain" that looks up caller context, applies business rules, and records each decision, built on context, ontology, and governance. The post outlines three pillars—grounding answers in business data, fast and slow AI decision-making including the ai_decide capability, and a learning loop from recorded calls—and points to the open-source DIVA blueprint on GitHub and a suggested 90-day pilot.

  6. Hacker News AI52

    Show HN: Preview video timelines live in the browser as AI agents edit them

    Tellers released agent skills that let AI coding agents build OTIO video timelines from local files or URLs with cuts, layers, titles, effects and music, preview them on localhost and export MP4 to the project folder. The tellers-otio-player skill needs Python 3 and a browser with no Tellers account, while tellers-mcp requires an account and adds cloud project editing, footage and transcript search, generated voice, music, images and video, and live preview. Install is via npx skills add tellers-ai/skills or the Claude Code and Codex plugin marketplaces, and the player is published at https://tellers.ai/videoplayer/bundle.js under the MIT license.

  7. Hacker News AI58

    Show HN: WOML – A markup language for building workflows and AI agents

    WOML is an open-source, code-first language and runtime for building automated workflows, backend applications, and AI agents, combining HTML-inspired markup for structure with inline or imported JavaScript/TypeScript for logic and a durable runtime for execution. Each .woml file defines triggers, steps, control flow, and runtime policies, and the runtime handles retries, state, waits, recovery, and execution history. It requires Bun 1.3.14 or later and is installed via the woml-cli package, with a VS Code extension and an agent skill also available.

  8. Hacker News AI36

    Show HN: Vu – a new programming language designed for AI. Rust speeds, Py syntax

    The author introduces Vu, a programming language developed over roughly six years that aims to combine Python-like, easy-to-read syntax with Rust-style ownership and memory safety, compiling to C for approximately C-level runtime speed. The compiler's own source (about 21,500 lines of Vu) passes `vuc check` in roughly 0.4 seconds, covering parsing, type and borrow checking, and the author says LLMs can read and write Vu out of the box due to its similarity to Python. Vu has no macros and a lighter-weight borrow checker than Rust's, and the author has added security and LLM-efficiency as principles, publishing a battery of tests intended to attack the language.

  9. Allen Institute for AI Blog38

    How researchers are adapting olmOCR 2 for historical and archaeological archives

    Ai2 describes how researchers adapted its open olmOCR 2 model: historian Maurice Casey built ArtificeOCR to run olmOCR 2 locally and make his Tropy photo library of archival sources searchable, while TU Wien and Austrian Academy of Sciences researchers fine-tuned olmOCR 2 with LoRA on 57 annotated Carnuntum pottery records, lowering transcription error on 450 test records from 15.58% to 1.11% through their CENTURIA benchmark.

  11. Hacker News AI42

    Show HN: Muscle Memory – Can you still write code without AI?

    A developer with six years of experience built Muscle Memory, a LeetCode-style practice site with more realistic challenges across 12 languages, where code runs in a network-denied sandbox in the browser with no account required. With user consent, it records practice as raw events including keystrokes, runs and submissions, aiming to build an open dataset on how people write code in the AI era, with individual results kept private unless shared and a "Stealth" mode excluding data from published findings. The code is MIT-licensed on GitHub, and the data is planned to be published as a report/notebook on the site and released raw under MIT license (parquet) once a critical mass is reached.

Oct 28Wed
  1. The Decoder69

    Nvidia's open Nemotron 3.5 Transcribe combines transcription, translation, and speaker recognition

    Nvidia released Nemotron 3.5 Transcribe, an open speech model that follows text instructions to transcribe 40 languages, translate 31 to or from English, identify speakers in 13, and answer questions about recordings up to an hour long with up to eight speakers. The 30-billion-parameter model activates about 4 billion parameters per step, runs on a single Nvidia GPU, and ranks first among open-weight models on Hugging Face's English Open ASR Leaderboard with a 5.33 percent average word error rate. Nvidia also released the Granary v2 dataset of about 844,000 hours of speech in 48 languages plus dataset-building tools, and reported that targeted fine-tuning on recordings of Indian doctors and medical students cut error rates from 30.8 to 11.8 percent in about 14 GPU hours on one GB300.

  2. Hugging Face Blog78

    NVIDIA Nemotron 3.5 Transcribe and Granary v2: Intelligent Multilingual Transcription You Can Prompt and Adapt

    NVIDIA released Nemotron 3.5 Transcribe, an open-weight, promptable model that handles transcription in 40 languages, translation of 31 to or from English, speaker attribution in 13 languages, and audio question answering in one checkpoint, running on a single NVIDIA GPU. It ranks first among open-weight models on the Hugging Face Open ASR Leaderboard for English at 5.33% average WER and posts the lowest diarization error rate on David AI's 21-language leaderboard. The release also includes Granary v2, an open data curation pipeline covering 463,062 hours across 48 languages, and NeMo Speech fine-tuning recipes that cut held-out WER by 45.8% relative to the best prompt in a medical case study.

    Why it matters: It documents concrete benchmark standings, an open data pipeline, and a reproducible fine-tuning recipe for teams evaluating or adapting open speech models.

  4. Hacker News AI60

    Show HN: Open-source AI workspace with shared procedural memory

    CleanSlate is an MIT-licensed open-source AI workspace built on VS Code that combines agents, project chats, a browser, terminals, files, and change review, with an optional MuscleMemory service that learns reusable skills from verified work and shares them across connected agents. The current release is CleanSlate 1.2.0 for macOS (Apple Silicon), with Intel macOS, Windows, and Linux not yet published; the same agent runtime also powers a CLI and SDK. Memory is local by default and opt-in, and skills can be exported as SKILL.md files for Claude Code or Codex.

  5. Hacker News AI28

    How to Build a Slow Product in the Fast AI Era

    The developer of Mole, a Mac and Windows cleanup tool, describes spending two months on unscalable work: installing and uninstalling 850 Mac apps one by one to build cleanup rules, testing more than 30 AI tools in real use, and redrawing dozens of icons over three rounds. Mole went from 1.13 to 1.18, added AI tool and System Data cleanup, shipped a Windows version on October 14, and passed 72.9K GitHub stars. The author argues that as AI makes code cheaper, the details learned only by doing the work yourself increasingly set products apart.

  6. Hacker News AI66

    Cisco open-sources Project Quarry, a detection language for AI agent behavior

    Cisco has open-sourced Project Quarry, a neurosymbolic rule language and evaluation engine for detecting harmful or disallowed AI agent behavior across multi-step traces, covering LLM conversations, tool use, MCP interactions and multimodal inputs. Rules combine machine learning classifiers and LLM judges with exact symbolic checks, and return evidence for each match; Quarry is already in production in Cisco AI Defense, with planned integration into DefenseClaw and Policy Studio.

  7. Hacker News AI58

    Harvey raised 500M for legal AI, I built the same and open sourced it

    CaseCite is a source-available, self-hosted legal research platform that lets firms upload and index their own documents and run chat-based research with inline citations, contract review, drafting, and CourtListener-backed case-law tools on infrastructure they control. It is licensed under the Elastic License 2.0, free to self-host and modify internally but not to offer as a hosted service, and AI features send document text to user-configured providers (BYOK) unless self-hosted OpenAI-compatible endpoints are set.

  8. Hacker News AI58

    Show HN: Keep your credentials out of the AI agents you use and build

    Weir is a tool that detects when AI agents leak API keys by planting unique fake keys where real ones live, running the agent's own flows against a local fake model, and searching spans, logs, console output, model prompts and other services for those exact values. It also offers a Claude Code status line and optional redaction hook that count and strip inventoried real keys before the model reads tool results. The author reports it found CVE-2026-116691 (GHSA-j7qq-vr8c-xvw3) in MLflow, fixed in 3.17.0.

  9. Hacker News AI58

    Show HN: ReplySlip – An open-source async task inbox for AI agents

    ReplySlip is an open-source async task inbox that lets AI agents hand tasks to each other with a JSON Schema for the expected answer, waking the receiving agent via webhook or a local watcher even when it isn't in a live session. Replies are validated with Ajv and mismatches are returned with errors, so the sender is only woken once a valid result arrives; it works with any agent supporting MCP tools such as Claude Code, Codex, Cursor and Grok Bot. The server is AGPL-3.0, the CLI and watcher are Apache-2.0, and a free hosted plan offers 10 agents and 1,000 tasks a month.

  10. Hacker News AI58

    Show HN: Nuvrail – make an AI agent ask before it sends, moves or deletes email

    Nuvrail is an approval layer that sits between an AI agent and a real mail server, presenting a normal IMAP/SMTP interface while staging every write (moves, deletes, flag changes, outbound sends) for a human to approve or reject with one tap; reads pass through instantly. EXPUNGE and CLOSE are never forwarded, and a local Docker Compose setup runs the approval UI, REST API, and IMAP/SMTP proxies on localhost for evaluation.

  11. MarkTechPost58

    Polymathic AI and Princeton Researchers Release FlashMap, a Flow Map Drafter for 6.14x Faster LLM Decoding

    Researchers from Polymathic AI, Princeton University, USC ISI, NYU and the Flatiron Institute released FlashMap, a speculative decoding drafter that uses a continuous flow map to draft a full 16-token block in one forward pass, keeping tokens in the block consistent with each other. On Qwen3-8B the team reports up to 6.14x lossless speedup on GSM8K, and says 1-step FlashMap is the fastest drafter tested on every Qwen3-8B task at both temperatures 0 and 1. Drafter weights for Qwen3-8B and Qwen3-4B are on Hugging Face with vLLM and SGLang plugins.

  12. Hacker News AI55

    Show HN: Hackerscad – Code-first CAD with MCP server for AI agents

    Hackerscad is a free, open-source parametric CAD tool where the model is code: typing updates the 3D view, and mouse actions like filleting an edge write readable code into the file. It uses OpenCascade B-rep for exact solids and real threads, exports 3MF, STL, STEP or drawings, and supports unittest blocks plus a command line for checking, rendering and exporting in scripts or CI. It ships with an MCP server and an agent skill so AI coding assistants can model parts, check dimensions and render them in the user's window.

  13. Hacker News AI71

    Rocky Linux Creator Built a New "Not Linux" Kernel in 11 Days Using AI

    Gregory Kurtzer, creator of CentOS and Rocky Linux, has released Ginux, an independent Rust-first x86-64 kernel written from scratch that implements the Linux ABI so existing Linux binaries run unmodified. Built over 11 days by a persistent OpenAI Codex task running GPT-5.6 Sol under what Kurtzer calls Human-Directed Agentic Engineering, it boots Rocky Linux 10 to systemd's multi-user.target in QEMU and is released as an Apache 2.0 research prototype with no physical hardware, GPU or NVMe support and no independent security audit.

  14. Hacker News AI34

    AetherGrid, an open-source distributed AI workload orchestrator

    AetherGrid is an open-source distributed AI workload orchestrator that matches workloads to compute nodes by resource requirements and constraints, manages the full job lifecycle, and enforces exclusive execution ownership through time-bound leases rather than assignment flags. Its domain logic is pure Python with no infrastructure dependencies, and every route requires API key authentication. The project documents each non-obvious engineering decision in architecture decision records covering reconciliation, lease fencing, scheduling policy, and API key scoping.

  15. Browser Use Blog58

    Odysseys2: a long-horizon web agent benchmark

    Carnegie Mellon University and Browser Use released Odysseys2, a benchmark of 100 long-horizon tasks on the live web, each graded on 8 to 12 pass/fail checks. The best agent, GPT-6 Astra, fully completes 47 of 100 tasks with a mean rubric score of 84.6, while no other agent reaches 20 and five complete none. The authors note the LLM judge has not been validated against a human reference, reward-hacking flags are model judgments, and the live web changes.

  16. Hacker News AI38

    Show HN: SelfClaw – Self-hosted multi-model AI chat with OpenAI-compatible API

    SelfClaw is a self-hosted AI chat system that aggregates multiple model providers (DeepSeek, NVIDIA, SiliconFlow, ZenMux, Zhipu, Kimi, MiMo, Mistral) with automatic failover polling, a CCR closed-loop agent with tool calling and memory, file operations, Bing/Baidu web search, and voice interaction. It runs a FastAPI gateway plus a Streamlit UI on port 8502, and also ships Self-IDE, a local Python service with an OpenAI-compatible proxy, goal engine, subagent orchestration and cost meter (default port 19898) with a thin VS Code extension.

  17. Hacker News AI58

    Show HN: OpenMontage Drama Studio – self-hosted AI studio for short dramas

    OpenMontage Drama Studio is a self-hostable web studio that turns a one-line idea into a short drama, viral short or product clip through a seven-stage pipeline: script, characters, scenes, props, storyboard and shots, voice, and edit. It requires users to supply their own text, image and video model keys (e.g. Volcengine Ark for Seedream and Seedance, or a ComfyUI server for images), with edge-tts as the default TTS, and ships a Docker Compose setup bundling PostgreSQL, Redis and a media worker while requiring an external S3-compatible endpoint. It is an independent AGPL-3.0 product by @charliewwdev derived from the calesthio/OpenMontage codebase.

  18. Hacker News AI60

    I ran each AI coding-agent sandbox's own tests against the others

    An open lab that turns sandbox claims (no key reads, no network, no git hooks) into runnable contracts and publishes results across sandboxes on the same tests. Corpus v1.1 (2026-10-26) holds 196 contracts harvested from the public test suites of sandbox-runtime, nono, Codex, Deno, bubblewrap and OpenHands, each re-expressed in a neutral format and credited. First results measure sandbox-runtime 0.0.79, nono 0.80.0, Codex CLI 0.162.1 and landrun on Linux kernel 6.8, with later runs adding TartarOS and masked-credential contracts.

  20. Hacker News AI58

    AI Phone

    AI Phone is an AGPL-3.0 open-source agent that runs on a computer and handles phone calls over SIP, currently requiring macOS on Apple Silicon with 16 GB RAM recommended for the default 4B model. Setup via a git clone and install script configures call direction, model, line and voice, and the daemon supports outgoing calls with an AI disclosure plus incoming calls using a set greeting. Speech recognition and synthesis stay local, while the language model can be local MLX, a Claude Code or Codex subscription, or an OpenAI-compatible endpoint.

  21. MarkTechPost65

    Meet LEANN: An Open-Source Vector Index that Shrinks a 60M-Chunk RAG Index from 201 GB to 6 GB

    UC Berkeley's Sky Computing Lab built LEANN, an MIT-licensed vector index on FAISS that stores a pruned graph and recomputes embeddings at query time instead of saving them, shrinking a 60M-chunk Wikipedia index from 201 GB to 6 GB in the repo benchmark. The paper, which won Best Research Paper at MLSys 2026, reports matching HNSW downstream accuracy (25.5% on NQ) at 90% recall using 4 GB instead of 188 GB, at the cost of slower retrieval (2.48 s vs 0.05 s on NQ). It ships apps for documents, Apple Mail, Chrome history, WeChat, iMessage and chat exports, plus an MCP server for Claude Code.

  23. Hacker News AI28

    Show HN: Spend Extra AI Usage Transcribing Murray's New English Dictionary

    A GitHub repository invites people to point an AI coding agent at it to transcribe scans of Murray's New English Dictionary (1888–1928) into public-domain text, with all materials released under CC0 1.0. As of a 2026-10-27 snapshot, 117 page files exist under text/, all in volume 01-AB (scans 25–141): 112 draft, 3 partial, and 2 ok. Contributors need a GitHub account, git, uv, qpdf, curl, gh, and an AI agent that can run shell commands and read PDF pages, following AGENTS.md and claiming scan ranges via draft pull requests.

  24. Hacker News AI58

    Running Local AI on Nvidia DGX Spark Without CUDA

    CUDA++ is a research-stage toolchain and runtime that encodes GB10 (sm_121) machine code directly, replacing nvcc, PTX and libcuda with its own encoder and a client for NVIDIA's open kernel module ioctls, while NVIDIA's kernel module and signed GSP firmware remain. It currently supports only the DGX Spark's GB10, does not compile CUDA C++ or PTX, and reports partial coverage of CUDA's libraries; a head-to-head speed comparison against llama.cpp and vLLM has not been published.

  25. Hacker News AI58

    Show HN: I built flightdeck – Observability and control plane for AI agents

    flightdeck is a self-hosted, Apache 2.0 observability and control plane that streams every LLM call, MCP event, and tool call from AI agents to a dashboard with a per-agent timeline and live fleet-wide feed. It offers token budgets with warn/swap/block thresholds, a kill switch and remote directives, per-flavor MCP allow/block rules, and sub-agent trees, and agents attach via a Claude Code plugin or the flightdeck-sensor Python package using init() + patch(). It is not a proxy: the sensor wraps SDK clients inside the agent's process and calls go straight to the provider, with prompt capture off by default in the sensor.

  26. Hacker News AI58

    Survival LLM: AI assistant and emergency library that runs on your own computer

    Survival LLM is a free, open-source offline AI assistant and emergency reference library that runs entirely on the user's computer, answering questions from sources like FEMA, CDC, MedlinePlus, WikEM, military survival manuals, wikiHow, iFixit and about 930,000 Wikipedia articles while showing the exact passages used. It selects an AI model based on available memory (from IBM Granite 4.2 8B at 16–31 GB up to NVIDIA Nemotron 3.5 Super at 128 GB or more), requires Apple Silicon macOS 14+ or 64-bit Windows 10/11, and needs internet only during setup. The library is a 9 GB download (19 GB installed), or 1.3 GB (3 GB installed) without Wikipedia and iFixit, and users can also add their own PDFs, Word documents, ebooks and notes for the AI to search locally.

  27. Hacker News AI22

    Vibe coded a point-and-click game to learn about the Drupal AI Ecosystem

    A developer vibe coded "AI Mac Packwala and the Curse of the Stale Cache," a browser-based point-and-click adventure in which players escape an island by learning the Drupal AI ecosystem, including providers, automators, agents, Tool API tools and MCP. The game has about 60 puzzles over three acts, is built in vanilla TypeScript with Vite and drawn entirely in code on a 320 × 200 canvas, and is also available as an Electron desktop app for Windows, macOS and Linux. The source code and a walkthrough are available.

  28. Ars Technica · AI58

    Vibe genes? Natural(ish) language comes to protein, genome design software

    Researchers in China developed Pinal, a protein design tool that takes natural-language prompts and uses a text-to-structure module (T2struct) plus SAProt-T to generate amino acid sequences, though only one of 29 tested GFP-like designs fluoresced. Separately, Hugging Face, the Zhongguancun Academy, and the University of Naples "Federico II" introduced Carbon X, an open-weight model retrained from Qwen3-14B on DNA that can translate between DNA and English and run locally. The article notes that testing designs still requires specialized lab work and that Carbon X can struggle with specific positions and hallucinate on vague prompts.

  29. Hacker News AI47

    Show HN: Search2o Simplifies AI Agents

    Search2o is an agent server that handles the infrastructure behind building, discovering and running AI agents, letting developers focus on business logic. Agents are described in English, discovered via search requests, and can build on each other within a conversation, with managed state, encrypted conversations and memories, multi-user roles, and stateless horizontally scalable servers. It offers integration via Python expressions, a REST API, and hooks, and its agent server and UI are source available.