{"schema":"catalog-search/v2","items":[{"kind":"record","record":{"id":"src_01M569C6D7K5FEKGR0DPJHZ6GN","type":"source","title":"Dramatron (hierarchical LLM script generation)","summary":null,"snippet":"Reference implementation of hierarchical prompt-chaining: logline to title, <b>characters</b>, plot beats, locations, then dialogue. Concrete template for <b>LLM</b> series/screenplay pipelines; ships 'unplugged' so you must supply an <b>LLM</b>","status":"active","categories":["T01"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569C6D7K5FEKGR0DPJHZ6GN","api_url":"https://veyrul.com/v1/records/src_01M569C6D7K5FEKGR0DPJHZ6GN","updated_at":"2026-10-18T01:17:47.801Z","score":0.3078}},{"kind":"record","record":{"id":"dsc_01M569J3MBB3RY32DCQKAV7PP8","type":"discussion","title":"How can an LLM-driven interactive story keep canon, state and plot goals consistent without a hand-authored branch graph?","summary":null,"snippet":"inside an authored state machine, keeps continuity, honors world rules and still guarantees the <b>story</b> can end?\n\nWhy this is still open: Sources read present authored state systems and <b>LLM</b>","status":"open","categories":["T18","T01"],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M569J3MBB3RY32DCQKAV7PP8","api_url":"https://veyrul.com/v1/records/dsc_01M569J3MBB3RY32DCQKAV7PP8","updated_at":"2026-10-18T01:21:01.568Z","score":0.2863}},{"kind":"record","record":{"id":"dsc_01M569MPV122YCN1V85WG182WA","type":"discussion","title":"FlawedFictions tests whether an LLM spots a plot hole in a short human-written story, using an algorithm that injects plot holes (reported: state-of-the-art LLMs struggle regardless of reasoning effort and degrade as stories get longer; LLM summaries and generated stories introduce plot holes). Con…","summary":null,"snippet":"tests whether an <b>LLM</b> spots a plot hole in a short human-written <b>story</b>, <b>using</b> an algorithm that injects plot holes (reported: state-of-the-art LLMs struggle regardless","status":"open","categories":["T01","T20"],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M569MPV122YCN1V85WG182WA","api_url":"https://veyrul.com/v1/records/dsc_01M569MPV122YCN1V85WG182WA","updated_at":"2026-10-18T01:22:26.776Z","score":0.2857}},{"kind":"record","record":{"id":"src_01M569C9GDCBC5TK6SVPWM1TZF","type":"source","title":"SEED-Story: multimodal long story generation with an LLM","summary":null,"snippet":"MLLM that writes long interleaved text-and-image <b>stories</b> with consistent <b>characters</b> and style; releases the StoryStream dataset and model on Hugging Face","status":"active","categories":["T03","T01"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569C9GDCBC5TK6SVPWM1TZF","api_url":"https://veyrul.com/v1/records/src_01M569C9GDCBC5TK6SVPWM1TZF","updated_at":"2026-10-18T01:17:50.978Z","score":0.3028}},{"kind":"record","record":{"id":"dsc_01M569MN1V87J6SVRQB070NMTN","type":"discussion","title":"Do LLM plot-hole and consistency detectors work on multi-episode series canon, not just short stories or generated text?","summary":null,"snippet":"FlawedFictions <b>uses</b> short human-written <b>stories</b> with injected plot holes; ConStory-Bench scores <b>LLM</b>-generated long <b>stories</b>; SCORE is framed around episodes but only its abstract was read","status":"open","categories":["T01"],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M569MN1V87J6SVRQB070NMTN","api_url":"https://veyrul.com/v1/records/dsc_01M569MN1V87J6SVRQB070NMTN","updated_at":"2026-10-18T01:22:24.945Z","score":0.2993}},{"kind":"record","record":{"id":"src_01M6VC6FSYRS1KMGXXP5S47B1P","type":"source","title":"MarkItDown: convert files to Markdown for LLM pipelines, README overview","summary":"The README presents MarkItDown as a converter from many document formats to Markdown for LLM pipelines.","snippet":"MarkItDown as a converter from many document formats to Markdown for <b>LLM</b> pipelines.\n\n<b>Useful</b> for: - <b>Turn</b> PDFs, Office files, HTML and EPubs into Markdown text.\n- Prepare documents","status":"active","categories":["T04"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6VC6FSYRS1KMGXXP5S47B1P","api_url":"https://veyrul.com/v1/records/src_01M6VC6FSYRS1KMGXXP5S47B1P","updated_at":"2026-11-07T16:06:51.413Z","score":0.2829}},{"kind":"record","record":{"id":"dsc_01M569J3KJ6N743N8SJPWH8ED5","type":"discussion","title":"Can storylet or quality-based selection be driven by an LLM without losing author control?","summary":null,"snippet":"quality-based structures select content by state. Is it better to let an <b>LLM</b> generate storylets, select them, or only render them, and how do authors specify constraints","status":"open","categories":["T18"],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M569J3KJ6N743N8SJPWH8ED5","api_url":"https://veyrul.com/v1/records/dsc_01M569J3KJ6N743N8SJPWH8ED5","updated_at":"2026-10-18T01:21:01.547Z","score":0.2771}},{"kind":"record","record":{"id":"dsc_01M569GEMFSMH104MV74K5HTPT","type":"discussion","title":"Do non-three-act structures (kishotenketsu etc.) change long-form LLM planning quality, and how should they be encoded as plans?","summary":null,"snippet":"does it produce different or worse coherence?\n\nWhy this is still open: The long-<b>story</b> generation papers read evaluate Western-style plots; no source read tests alternative structures","status":"open","categories":["T01"],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M569GEMFSMH104MV74K5HTPT","api_url":"https://veyrul.com/v1/records/dsc_01M569GEMFSMH104MV74K5HTPT","updated_at":"2026-10-18T01:20:07.302Z","score":0.282}},{"kind":"record","record":{"id":"src_01M67NXPMVMD6ZP8K6K0ECBGQE","type":"source","title":"Searge-LLM for ComfyUI v1.0 (ComfyUI registry node ComfyUI_Searge_LLM)","summary":"ComfyUI node registry custom node pack ComfyUI_Searge_LLM at revision 3804774923b3: publisher admin-11338bd3-f081-43cf-b3f9-295c829826f7; declared licence {}; repository https://github.com/SeargeDP/ComfyUI_Searge_LLM. Metadata-only index entry; not tested guidance.","snippet":"NodeStatusActive Locate ComfyUI_Searge_<b>LLM</b> and check its declared structure and requirements before <b>use</b>","status":"active","categories":["T08"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M67NXPMVMD6ZP8K6K0ECBGQE","api_url":"https://veyrul.com/v1/records/src_01M67NXPMVMD6ZP8K6K0ECBGQE","updated_at":"2026-10-31T00:32:00.610Z","score":0.2839}},{"kind":"record","record":{"id":"src_01M6V5B7W93N49JJQYF874BS4J","type":"source","title":"Inspect AI: LLM evaluation framework from the UK AI Security Institute, README overview","summary":"The README presents Inspect as a framework for large language model evaluations created by the UK AI Security Institute.","snippet":"framework for large language model evaluations created by the UK AI Security Institute.\n\n<b>Useful</b> for: - Build evaluations <b>using</b> built-in components for prompts, tools, multi-<b>turn</b> dialog and model","status":"active","categories":["T20"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6V5B7W93N49JJQYF874BS4J","api_url":"https://veyrul.com/v1/records/src_01M6V5B7W93N49JJQYF874BS4J","updated_at":"2026-11-07T14:07:07.050Z","score":0.2822}},{"kind":"record","record":{"id":"src_01M569CRSQQDWKAAV60QAYVVF0","type":"source","title":"LAVE: LLM-Powered Agent Assistance and Language Augmentation for Video Editing","summary":null,"snippet":"Research system where an <b>LLM</b> agent plans and executes editing actions over automatically generated text descriptions of footage; user study on agent-assisted editing. An early reference for agent","status":"active","categories":["T10"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569CRSQQDWKAAV60QAYVVF0","api_url":"https://veyrul.com/v1/records/src_01M569CRSQQDWKAAV60QAYVVF0","updated_at":"2026-10-18T01:18:06.636Z","score":0.2772}},{"kind":"record","record":{"id":"src_01M6W707Q7JW1231YP60P2KR44","type":"source","title":"MLflow: open source platform for agents, LLMs and ML models, README overview","summary":"The README presents MLflow as a platform to trace, evaluate and manage LLM and agent applications.","snippet":"MLflow as a platform to trace, evaluate and manage <b>LLM</b> and agent applications.\n\n<b>Useful</b> for: - Trace <b>LLM</b> calls and inspect them in a local UI.\n- Manage prompts","status":"active","categories":["T20"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6W707Q7JW1231YP60P2KR44","api_url":"https://veyrul.com/v1/records/src_01M6W707Q7JW1231YP60P2KR44","updated_at":"2026-11-07T23:55:18.088Z","score":0.2795}},{"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":"performance on a wide range of hardware, locally and in the cloud.\n\n<b>Useful</b> for: - Run language models locally from the command line, downloading a model directly from Hugging Face.\n- Launch","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":0.2794}},{"kind":"record","record":{"id":"src_01M6A765R84XB1GQSE7QRBW47R","type":"source","title":"ComfyUI-NewBie-LLM-Formatter (ComfyUI registry node NewBie-LLM-Formatter)","summary":"ComfyUI node registry custom node pack NewBie-LLM-Formatter at revision 37f59104390c: latest version 1.4.2; publisher sakizuki; declared licence {\"file\": \"LICENSE\"}; repository https://github.com/SuzumiyaAkizuki/ComfyUI-NewBie-LLM-Formatter. Metadata-only index entry; not tested guidance.","snippet":"This extension automates the creation of structured XML prompts for the NewBie model by <b>using</b> <b>LLM</b> APIs to transform natural language or images into formatted descriptions. It provides specialized","status":"active","categories":["T08"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6A765R84XB1GQSE7QRBW47R","api_url":"https://veyrul.com/v1/records/src_01M6A765R84XB1GQSE7QRBW47R","updated_at":"2026-11-01T00:12:12.883Z","score":0.2771}},{"kind":"record","record":{"id":"src_01M6SRZBJV5G8B3GWD1CXSS6H6","type":"source","title":"Ableton MCP","summary":"MCP server plus Ableton Live Remote Script that lets an LLM client create tracks, clips and arrangements and manipulate a Live session.","snippet":"<b>LLM</b> client create tracks, clips and arrangements and manipulate a Live session.\n\n<b>Useful</b> for: music: AI-assisted track creation and session editing inside Ableton Live\n\nFirst action: DOCUMENTED: install","status":"active","categories":["T14"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6SRZBJV5G8B3GWD1CXSS6H6","api_url":"https://veyrul.com/v1/records/src_01M6SRZBJV5G8B3GWD1CXSS6H6","updated_at":"2026-11-07T01:11:40.340Z","score":0.2812}},{"kind":"record","record":{"id":"dsc_01M569J385TB8CRHTCHRETZV7K","type":"discussion","title":"Does LLM multi-agent pre-production planning produce shot plans professionals would accept?","summary":null,"snippet":"FilmAgent and MovieAgent simulate director, screenwriter and cinematographer roles, but","status":"open","categories":["T03","T20"],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M569J385TB8CRHTCHRETZV7K","api_url":"https://veyrul.com/v1/records/dsc_01M569J385TB8CRHTCHRETZV7K","updated_at":"2026-10-18T01:21:01.178Z","score":0.2771}},{"kind":"record","record":{"id":"src_01M62F7RVGNMFJGBTK1A5DJ5AR","type":"source","title":"Seedance 2.0 + LLM Prompt Helper (ComfyUI template template_seedance_2_0_plus_llm_prompt_helper)","summary":"official ComfyUI workflow template template_seedance_2_0_plus_llm_prompt_helper at revision 0cc0fba562ef: 9 nodes. Metadata-only index entry; not tested guidance.","snippet":"plus_<b>llm</b>_prompt_helper and check its declared structure and requirements before <b>use</b>","status":"active","categories":["T08"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M62F7RVGNMFJGBTK1A5DJ5AR","api_url":"https://veyrul.com/v1/records/src_01M62F7RVGNMFJGBTK1A5DJ5AR","updated_at":"2026-10-28T23:58:58.354Z","score":0.2772}},{"kind":"record","record":{"id":"src_01M6AEFPNVSP4SFC0P8HP3XZAN","type":"source","title":"Storyboard-LLM (ComfyUI registry node Storyboard-LLM)","summary":"ComfyUI node registry custom node pack Storyboard-LLM at revision 8ebe07e183d8: latest version 1.0.3; publisher lbunc; declared licence {\"file\": \"License\"}; repository https://github.com/Lbunc/ComfyUI-Storyboard-LLM. Metadata-only index entry; not tested guidance.","snippet":"status: NodeStatusActive Locate Storyboard-<b>LLM</b> and check its declared structure and requirements before <b>use</b>","status":"active","categories":["T08"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6AEFPNVSP4SFC0P8HP3XZAN","api_url":"https://veyrul.com/v1/records/src_01M6AEFPNVSP4SFC0P8HP3XZAN","updated_at":"2026-11-01T02:19:45.176Z","score":0.2771}},{"kind":"record","record":{"id":"src_01M66Q65FSRRX10DVH3NMV25MT","type":"source","title":"ComfyUI-Korean-Prompt-Engineer-with-LLM (ComfyUI registry node ComfyUI-Korean-Prompt-Engineer-with-LLM)","summary":"ComfyUI node registry custom node pack ComfyUI-Korean-Prompt-Engineer-with-LLM at revision 2bdb9b32cf35: latest version 0.1.1; publisher garura; declared licence {\"file\": \"LICENSE\"}; repository https://github.com/TheGarura/ComfyUI-Korean-Prompt-Engineer-with-LLM. Metadata-only index entry; not tested guidance.","snippet":"Korean-Prompt-Engineer-with-<b>LLM</b> and check its declared structure and requirements before <b>use</b>","status":"active","categories":["T08"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M66Q65FSRRX10DVH3NMV25MT","api_url":"https://veyrul.com/v1/records/src_01M66Q65FSRRX10DVH3NMV25MT","updated_at":"2026-10-30T15:34:52.107Z","score":0.2771}},{"kind":"record","record":{"id":"src_01M6AEFVR8NQB39BDC5KRYGKXX","type":"source","title":"Tenos_LLM_Image_Describe (ComfyUI registry node Tenos_LLM_Image_Describe)","summary":"ComfyUI node registry custom node pack Tenos_LLM_Image_Describe at revision 08c89fada043: latest version 1.0.0; publisher tenosai; declared licence {\"file\": \"LICENSE\"}; repository https://github.com/Tenos-ai/Tenos-LLM-Image-Describe. Metadata-only index entry; not tested guidance.","snippet":"Locate Tenos_<b>LLM</b>_Image_Describe and check its declared structure and requirements before <b>use</b>","status":"active","categories":["T08"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6AEFVR8NQB39BDC5KRYGKXX","api_url":"https://veyrul.com/v1/records/src_01M6AEFVR8NQB39BDC5KRYGKXX","updated_at":"2026-11-01T02:19:50.363Z","score":0.2771}},{"kind":"guide_preview","preview":{"schema":"guide-preview/v1","id":"art_01M6HH6B5789VX4QD9WPRTAEA1","type":"article","revision":1,"title":"Story Ribbons: using an LLM to turn a novel or script into a character-path chart","coverage":"A source note on a 2025 paper that parses novels and scripts into chapters, scenes, characters and locations, then draws each character as a ribbon across the story. Useful to writers and story analysts weighing LLM story-structure tools. Based on two arXiv pages; nothing was run and all results are the authors' own.","example":null,"tips":["The paper reports that LLMs sometimes invent or alter quotes, so checking every quoted line against the source text is part of using this kind of output.","Scene splitting was inconsistent until scenes were defined by a change of story location; a clear definition of 'scene' matters.","Ratings such as importance and sentiment are subjective; treat them as one reading to check, not a measurement."],"categories":["T05","T10"],"tags":["story-ribbons","storyline-visualization","llm-pipeline","story-analysis","arxiv","documented-not-tested"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null},"media":[]}}],"truncated":true,"has_more":true,"next_cursor":"eyJyZWZlcmVuY2UiOiJNakEiLCJwcmV2aWV3IjpudWxsLCJxIjoiU3RvcnkgUmliYm9uczogdXNpbmcgYW4gTExNIHRvIHR1cm4gYSBub3ZlbCBvciBzY3JpcHQgaW50byBhIGNoYXJhY3Rlci1wYXRoIGNoYXJ0IiwidHlwZXMiOltdLCJjYXRlZ29yaWVzIjpbXX0","ordering":"bounded_reference_and_preview_lanes"}