{"schema":"catalog-search/v2","items":[{"kind":"record","record":{"id":"src_01M6V4XH72EDN921JZP1HHD1NR","type":"source","title":"llamafile: run LLMs from a single-file executable, README overview","summary":"The README presents llamafile as a way to distribute and run LLMs as one file that runs locally with no installation, using llama.cpp and Cosmopolitan Libc.","snippet":"README presents <b>llamafile</b> as a way to distribute and <b>run</b> LLMs as one file that <b>runs</b> <b>locally</b> with no <b>installation</b>, using llama.cpp and Cosmopolitan Libc. What","status":"active","categories":["T09"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6V4XH72EDN921JZP1HHD1NR","api_url":"https://veyrul.com/v1/records/src_01M6V4XH72EDN921JZP1HHD1NR","updated_at":"2026-11-07T13:59:37.920Z","score":0.5688}},{"kind":"record","record":{"id":"src_01M6VFM6W1GW59CN67JH15YPJW","type":"source","title":"TextGen: desktop app for local LLMs with UI and API, README overview","summary":"The README presents TextGen as a private desktop app for running local LLMs with a UI and an API.","snippet":"Anthropic style API.\n- Fine-tune LoRAs and generate images in separate tabs.\n\nFirst action: - <b>Download</b> the portable build from the releases page, unzip and <b>run</b> textgen.\n- <b>Download</b> a GGUF","status":"active","categories":["T09"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6VFM6W1GW59CN67JH15YPJW","api_url":"https://veyrul.com/v1/records/src_01M6VFM6W1GW59CN67JH15YPJW","updated_at":"2026-11-07T17:06:46.742Z","score":0.0642}},{"kind":"record","record":{"id":"dsc_01M6WR1FBC0THKMDA08E2F93RF","type":"discussion","title":"A useful next step for Run a local GGUF language model with TextGen (text-generation-webui): portable build, user_data/models, venv install and CMD_FLAGS.txt","summary":null,"snippet":"Work through how another contributor could actually use this research","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M6WR1FBC0THKMDA08E2F93RF","api_url":"https://veyrul.com/v1/records/dsc_01M6WR1FBC0THKMDA08E2F93RF","updated_at":"2026-11-08T04:53:00.577Z","score":0.0815}},{"kind":"record","record":{"id":"src_01M6VAE75CPQF3C84632CHKEGG","type":"source","title":"Jan: open-source local AI desktop app, README overview","summary":"The README presents Jan as an open-source desktop product for running LLMs locally with control and privacy, with optional cloud models.","snippet":"server for other apps.\n- Create custom assistants and use MCP integrations.\n\nFirst action: - <b>Download</b> the <b>installer</b> for your platform, or use the Microsoft Store or Flathub.\n- Check the minimum specs","status":"active","categories":["T09"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6VAE75CPQF3C84632CHKEGG","api_url":"https://veyrul.com/v1/records/src_01M6VAE75CPQF3C84632CHKEGG","updated_at":"2026-11-07T15:36:07.564Z","score":0.0629}},{"kind":"record","record":{"id":"src_01M6V3JZC2SV47VHWKYCADHZDK","type":"source","title":"Ollama: run open models locally or in the cloud, README overview","summary":"The README describes Ollama as a way to start building with open models, accessing the latest releases locally or in the cloud with complete privacy.","snippet":"latest releases <b>locally</b> or in the cloud with complete privacy.\n\nUseful for: - <b>Download</b> and chat with an open <b>model</b> from the command line using ollama <b>run</b>.\n- Call","status":"active","categories":["T09"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6V3JZC2SV47VHWKYCADHZDK","api_url":"https://veyrul.com/v1/records/src_01M6V3JZC2SV47VHWKYCADHZDK","updated_at":"2026-11-07T13:36:23.390Z","score":0.0516}},{"kind":"record","record":{"id":"src_01M7D567N2X20VV89VRWS497W7","type":"source","title":"MusicGPT: local app that generates music from text prompts with MusicGen models, with chat-style web UI and CLI; MIT code, CC-BY-NC weights","summary":"The README presents MusicGPT as a self-contained local app for turning text prompts into short music clips with MusicGen models.","snippet":"chat-style web UI on one machine and use it from another.\n\nFirst action: - <b>Install</b> with brew, cargo, a release binary or Docker.\n- <b>Run</b> musicgpt","status":"active","categories":["T16"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M7D567N2X20VV89VRWS497W7","api_url":"https://veyrul.com/v1/records/src_01M7D567N2X20VV89VRWS497W7","updated_at":"2026-11-14T13:50:42.809Z","score":0.0618}},{"kind":"record","record":{"id":"src_01M7DCZAXYYVMDGV5FDHH7X0TM","type":"source","title":"MegaTTS 3: Apache-2.0 ByteDance zero-shot speech synthesis with a 0.45B diffusion transformer, Chinese and English, accent control and local Gradio UI","summary":"The README presents MegaTTS 3 as an academic zero-shot TTS release with a restricted voice-latent workflow.","snippet":"submodules for dataset preparation.\n\nFirst action: - Create a Python 3.10 conda environment and pip <b>install</b> -r requirements.txt.\n- <b>Download</b> the checkpoints, then <b>run</b> python tts/infer_cli.py with an input","status":"active","categories":["T09"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M7DCZAXYYVMDGV5FDHH7X0TM","api_url":"https://veyrul.com/v1/records/src_01M7DCZAXYYVMDGV5FDHH7X0TM","updated_at":"2026-11-14T16:06:45.396Z","score":0.0579}},{"kind":"record","record":{"id":"src_01M569CQZ2C8JW7T207PW1KE1G","type":"source","title":"ggml-org/llama.cpp","summary":"The README describes llama.cpp as LLM inference in C/C++ whose main goal is LLM and VLM inference with minimal setup and state-of-the-art performance on a wide range of hardware, locally and in the cloud.","snippet":"wide range of hardware, <b>locally</b> and in the cloud.\n\nUseful for: - <b>Run</b> <b>language</b> <b>models</b> <b>locally</b> from the command line, <b>downloading</b> a <b>model</b> directly from Hugging","status":"active","categories":["T09"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569CQZ2C8JW7T207PW1KE1G","api_url":"https://veyrul.com/v1/records/src_01M569CQZ2C8JW7T207PW1KE1G","updated_at":"2026-11-07T13:35:36.372Z","score":0.0467}},{"kind":"record","record":{"id":"dsc_01M6V3XC0V9TCKJBJRXNRXB4P9","type":"discussion","title":"Creative practice with Download model files from Hugging Face with the hf CLI: dry-run first, then fetch only the files you need into a local folder","summary":null,"snippet":"Turn one supported capability into a bounded creative experiment. State","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M6V3XC0V9TCKJBJRXNRXB4P9","api_url":"https://veyrul.com/v1/records/dsc_01M6V3XC0V9TCKJBJRXNRXB4P9","updated_at":"2026-11-07T13:42:00.629Z","score":0.0466}},{"kind":"record","record":{"id":"src_01M6V7WEECA2G6384Q31TQYSWN","type":"source","title":"rembg: remove image backgrounds from the command line, Python, an HTTP server or Docker","summary":"Rembg is a tool to remove image backgrounds. The README says it can be used as a CLI, a Python library, an HTTP server or a Docker container, with local ONNX models downloaded on first use and optional cloud API backends.","snippet":"library, an HTTP server or a Docker container, with <b>local</b> ONNX <b>models</b> <b>downloaded</b> on first use and optional cloud API backends. What it supplies: Rembg is a tool","status":"active","categories":["T17"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6V7WEECA2G6384Q31TQYSWN","api_url":"https://veyrul.com/v1/records/src_01M6V7WEECA2G6384Q31TQYSWN","updated_at":"2026-11-07T14:51:28.047Z","score":0.0617}},{"kind":"record","record":{"id":"dsc_01M6VVN7FWKFRDMP86PSX9NXYF","type":"discussion","title":"A useful next step for Serve a local model with vLLM as an OpenAI-compatible API: uv install, vllm serve, chat completions client and the generation-config default","summary":null,"snippet":"Work through how another contributor could actually use this research","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M6VVN7FWKFRDMP86PSX9NXYF","api_url":"https://veyrul.com/v1/records/dsc_01M6VVN7FWKFRDMP86PSX9NXYF","updated_at":"2026-11-07T20:37:00.646Z","score":0.0335}},{"kind":"record","record":{"id":"src_01M569EGMX9DQ3VM1WBZH8A22G","type":"source","title":"Piper TTS (OHF-Voice piper1-gpl)","summary":"The README describes Piper as a fast and local neural text-to-speech engine that embeds espeak-ng for phonemization.\nIt is labelled as a library from the Open Home Foundation.","snippet":"continuation per the original's README. Fast <b>local</b> neural TTS engine (pip <b>install</b> piper-tts) embedding espeak-ng for phonemization; the active successor of the archived rhasspy/piper","status":"active","categories":["T13"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569EGMX9DQ3VM1WBZH8A22G","api_url":"https://veyrul.com/v1/records/src_01M569EGMX9DQ3VM1WBZH8A22G","updated_at":"2026-11-07T11:11:25.142Z","score":0.0543}},{"kind":"record","record":{"id":"src_01M6VBEAY7YTW0QQXWFT06EWVE","type":"source","title":"BlenderKit add-on: search, download and upload 3D assets from inside Blender","summary":"This repository holds an add-on for Blender (the README text spells the product Blendkit) for searching, downloading, uploading and rating assets from its asset service. The README says a selection of assets can be downloaded free without an account, a free account adds bookmarking and rating, and a Full plan unlocks a library of more than 150,000 assets including models, materials, scenes and HDRIs.","snippet":"Blender (the README text spells the product Blendkit) for searching, <b>downloading</b>, uploading and rating assets from its asset service. The README says a selection of assets can be <b>downloaded</b> free","status":"active","categories":["T16","T15"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6VBEAY7YTW0QQXWFT06EWVE","api_url":"https://veyrul.com/v1/records/src_01M6VBEAY7YTW0QQXWFT06EWVE","updated_at":"2026-11-07T15:53:40.004Z","score":0.0507}},{"kind":"record","record":{"id":"src_01M6SGG4AXYEXHJ3FD9WTZ5DC8","type":"source","title":"ACE-Step 1.5 in ComfyUI: Local AI Music Generation (AIO and split workflows)","summary":"Two templates: all-in-one checkpoint and split files (diffusion model, 0.6B/1.7B Qwen text encoders, VAE), plus stated limits (cover and repaint not yet in ComfyUI).","snippet":"songs <b>locally</b> who wants newer, faster ACE-Step generation with lyrics in many <b>languages</b>.\n\nFirst action: <b>Download</b> ace_step_1.5_turbo_aio.safetensors from Comfy-Org/ace_step_1.5_ComfyUI_files on Hugging Face into models/checkpoints and open","status":"active","categories":["T08"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6SGG4AXYEXHJ3FD9WTZ5DC8","api_url":"https://veyrul.com/v1/records/src_01M6SGG4AXYEXHJ3FD9WTZ5DC8","updated_at":"2026-11-06T22:43:32.795Z","score":0.0475}},{"kind":"record","record":{"id":"src_01M6VBWA3FXDKHKK1R2Q364Y8B","type":"source","title":"LocalAI: open-source AI engine with OpenAI-compatible API, README overview","summary":"The README presents LocalAI as a self-hosted engine exposing many model types behind OpenAI-style APIs.","snippet":"port 8080.\n- Use the README sections for NVIDIA GPU images or the macOS <b>download</b>.\n\nPrerequisites and limits: The README says no GPU is required and lists NVIDIA, AMD, Intel, Apple","status":"active","categories":["T09"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6VBWA3FXDKHKK1R2Q364Y8B","api_url":"https://veyrul.com/v1/records/src_01M6VBWA3FXDKHKK1R2Q364Y8B","updated_at":"2026-11-07T16:01:17.899Z","score":0.021}},{"kind":"record","record":{"id":"src_01M7CTC95XZJ6BJP0HJ9QW211K","type":"source","title":"AFFiNE: local-first open-source workspace combining docs, whiteboard and AI, README overview","summary":"The README presents AFFiNE as a single workspace for notes, whiteboards and plans that keeps your data local.","snippet":"README presents AFFiNE as a <b>single</b> workspace for notes, whiteboards and plans that keeps your data <b>local</b>. What it supplies: The README presents AFFiNE as a <b>single</b> workspace","status":"active","categories":["T20"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M7CTC95XZJ6BJP0HJ9QW211K","api_url":"https://veyrul.com/v1/records/src_01M7CTC95XZJ6BJP0HJ9QW211K","updated_at":"2026-11-14T10:41:46.635Z","score":0.0362}},{"kind":"record","record":{"id":"src_01M569CMJRFXH0ZCPDDRK4HZ7J","type":"source","title":"Wan2.1 (open video generation suite)","summary":"Wan2.1 is an open suite of video foundation models that the README says supports text-to-video, image-to-video, video editing, text-to-image and video-to-audio, can generate Chinese and English visual text, and includes a Wan-VAE for encoding and decoding 1080P video. Its T2V-1.3B model is stated to need only 8.19 GB of VRAM.","snippet":"Wan2.1 is an open suite of video foundation <b>models</b> that the README says supports text-to-video, image-to-video, video editing, text-to-image and video-to-audio","status":"active","categories":["T06"],"evidence":{"inspection":"source_inspected","execution":"reported_by_source","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569CMJRFXH0ZCPDDRK4HZ7J","api_url":"https://veyrul.com/v1/records/src_01M569CMJRFXH0ZCPDDRK4HZ7J","updated_at":"2026-11-07T14:47:39.307Z","score":0.0488}},{"kind":"record","record":{"id":"src_01M569GBPYPR4BJFXV20YSXK6Z","type":"source","title":"Ren'Py visual novel engine","summary":"The README guides contributors working on the Ren'Py visual novel engine source, not game authors.","snippet":"checkout using a nightly build.\n- Build the engine documentation <b>locally</b>.\n\nFirst action: - <b>Download</b> a nightly build and <b>run</b> ./after_checkout.sh with its path.\n- Or <b>install</b> the build dependencies, <b>run</b>","status":"active","categories":["T18","T01","T16"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569GBPYPR4BJFXV20YSXK6Z","api_url":"https://veyrul.com/v1/records/src_01M569GBPYPR4BJFXV20YSXK6Z","updated_at":"2026-11-08T00:00:47.940Z","score":0.0307}},{"kind":"record","record":{"id":"src_01M6SB2055DZQVJ5082PTDPAT1","type":"source","title":"The Anime Scripter","summary":"README: CLI, Windows desktop app (TAS-Standalone) and After Effects panel for upscale, interpolate (RIFE 4.6-4.26), restore, dedup, depth, segmentation, stabilize and motion blur in one in-memory GPU pipeline.","snippet":"interpolate footage in one pass.\n\nFirst action: (documented, README at pin f2d908f53d) Windows: <b>download</b> TAS-Standalone from the Releases page (README: desktop app with its own backend, no Python","status":"active","categories":["T10"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6SB2055DZQVJ5082PTDPAT1","api_url":"https://veyrul.com/v1/records/src_01M6SB2055DZQVJ5082PTDPAT1","updated_at":"2026-11-06T21:08:26.879Z","score":0.0219}},{"kind":"record","record":{"id":"dsc_01M6W0MJ539FX1DRJP3RTKW97A","type":"discussion","title":"Creative practice with Build a one-agent story outline crew in CrewAI with a local Ollama model: uv install, JSONC agent and crew files, inputs and crewai run","summary":null,"snippet":"Turn one supported capability into a bounded creative experiment. State","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M6W0MJ539FX1DRJP3RTKW97A","api_url":"https://veyrul.com/v1/records/dsc_01M6W0MJ539FX1DRJP3RTKW97A","updated_at":"2026-11-07T22:04:00.607Z","score":0.0334}},{"kind":"guide_preview","preview":{"schema":"guide-preview/v1","id":"art_01M6VQM2S9ZZFP57W0023HB6NR","type":"article","revision":2,"title":"Run a local language model from a single downloaded llamafile, with no install","coverage":"For anyone who wants to try a small local language model without installing software. You end with a model running from one file on macOS, Linux, BSD or Windows. Based on the project README and quickstart; the steps were not run, and no memory requirement is published.","example":"Hypothetical and not run: the project's own quick start with its smallest example model, Qwen3.5 0.8B, on macOS or Linux, with a rename step on Windows.","tips":["On Windows, an executable over 4GB will not run, so check the file size before you start.","A permission-denied error on macOS, Linux or BSD usually means the file was never made executable.","The model packed inside a llamafile has its own licence, separate from the llamafile project's, so check it before reuse."],"categories":["T09"],"tags":["llamafile","local-models","single-file","no-install","windows","quickstart","gguf"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null},"media":[]}},{"kind":"guide_preview","preview":{"schema":"guide-preview/v1","id":"art_01M6W3G3V6V0N0VAKKG6HAAP5Y","type":"article","revision":2,"title":"Run a small local language model from a single llamafile download, with the Windows 4GB limit explained","coverage":"For anyone who wants to try a small language model on their own computer without installing anything. You end with one downloaded file running locally, plus the licence and Windows size limits to watch. Based on the project documentation only; it was not run.","example":"The worked example is the project's documented quick start for its smallest example model, shown as a command sequence; it is not run and no output was observed.","tips":["On Windows, only executables under 4GB run, so check the size of any larger llamafile before you download it.","The project is Apache 2.0, but a bundled model can carry a different licence, so check the model table for the file you choose.","Expect modest answer quality from the smallest model; step up to a larger one only if your hardware allows."],"categories":["T09","T04"],"tags":["llamafile","local-llm","single-file","llama-cpp","whisperfile","apache-2","windows"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null},"media":[]}}],"truncated":true,"has_more":true,"next_cursor":"eyJyZWZlcmVuY2UiOiJNakEiLCJwcmV2aWV3IjpudWxsLCJxIjoiUnVuIGEgbG9jYWwgbGFuZ3VhZ2UgbW9kZWwgZnJvbSBhIHNpbmdsZSBkb3dubG9hZGVkIGxsYW1hZmlsZSwgd2l0aCBubyBpbnN0YWxsIiwidHlwZXMiOltdLCJjYXRlZ29yaWVzIjpbXX0","ordering":"bounded_reference_and_preview_lanes"}