Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
json_repair
AI repositoriesRepair malformed JSON from LLMs, APIs, logs, and user input in Python.
git clone https://github.com/mangiucugna/json_repair.git -
outlines
PromptsStructured Outputs
git clone https://github.com/dottxt-ai/outlines.git -
XHS-Downloader
MCP servers小红书(XiaoHongShu、RedNote)链接提取/作品采集工具
git clone https://github.com/JoeanAmier/XHS-Downloader.git -
datamodel-code-generator
SkillsGenerate Pydantic v2 models, dataclasses, TypedDict, and msgspec.Struct from OpenAPI, JSON Schema, GraphQL, Avro, Protobuf, and raw JSON/YAML/CSV, plus FastAPI servers and Python clients from OpenAPI.
git clone https://github.com/datamodel-code-generator/datamodel-code-generator.git -
hh-rlhf
Datasets & benchmarksHugging Face dataset by Anthropic
Anthropic/hh-rlhf -
opendataloader-pdf
AI repositoriesPDF Parser for AI-ready data. Automate PDF accessibility. Open-source.
git clone https://github.com/opendataloader-project/opendataloader-pdf.git -
webgradients
Agents & frameworks180 free CSS3, Figma, Sketch & PSD gradients — plus a JSON dataset for design tools, generators, and AI agents.
git clone https://github.com/itmeo/webgradients.git -
unstract
MCP serversLLM-Driven Extraction of Unstructured Data — Built for API Deployments & ETL Pipeline Workflows
git clone https://github.com/Zipstack/unstract.git -
xerj
MCP serversAI search engine and MCP server for bots and agents. One Rust binary indexes code, docs, logs, JSONL/CSV and PDFs for BM25 full-text, vector and hybrid search, code search without grep, agent memory and RAG. Elasticsearch-compatible API; Corpus Hub serves hundreds of reference memory corpora.
git clone https://github.com/xerj-org/xerj.git -
toon
AI repositories🎒 Token-Oriented Object Notation (TOON) – compact, human-readable serialization of JSON data for LLM prompts. TypeScript SDK, CLI, benchmarks.
git clone https://github.com/toon-format/toon.git -
claude-opus-4.6-4.7-reasoning-8.7k
Datasets & benchmarksHugging Face dataset by angrygiraffe
angrygiraffe/claude-opus-4.6-4.7-reasoning-8.7k -
Llama-Nemotron-Post-Training-Dataset
Datasets & benchmarksHugging Face dataset by nvidia
nvidia/Llama-Nemotron-Post-Training-Dataset -
databricks-dolly-15k
Datasets & benchmarksHugging Face dataset by databricks
databricks/databricks-dolly-15k -
Qwen-2.5-1B-RLCD
Modelstext generation model by harshatheg · mlx
harshatheg/Qwen-2.5-1B-RLCD -
Opus-4.6-Reasoning-3000x-filtered
Datasets & benchmarksHugging Face dataset by nohurry
nohurry/Opus-4.6-Reasoning-3000x-filtered -
OpenHermes-2.5
Datasets & benchmarksHugging Face dataset by teknium
teknium/OpenHermes-2.5 -
openassistant-guanaco
Datasets & benchmarksHugging Face dataset by timdettmers
timdettmers/openassistant-guanaco -
alpaca-cleaned
Datasets & benchmarksHugging Face dataset by yahma
yahma/alpaca-cleaned -
docutranslate
AI repositories文档(小说、论文、字幕)翻译工具(支持 pdf/word/excel/json/epub/srt...)Document (Novel, Thesis, Subtitle) Translation Tool (Supports pdf/word/excel/json/epub/srt...)
git clone https://github.com/xunbu/docutranslate.git -
OIG
Datasets & benchmarksHugging Face dataset by laion
laion/OIG -
AI-Visual-Prompt-Cookbook
PromptsPlug-and-play JSON style prompts for Nano Banana Pro, GPT Image & Midjourney. Copy one style.json, get a consistent look. New styles every week.
git clone https://github.com/VigoZhao/AI-Visual-Prompt-Cookbook.git -
capcut-cli
SkillsIndependent, unofficial CLI to edit CapCut and JianYing (剪映) projects — subtitles, timing, speed, volume, templates, cut long-form to shorts. No API needed, reads draft_content.json and draft_info.json (剪映草稿) directly. Not affiliated with ByteDance.
git clone https://github.com/renezander030/capcut-cli.git -
natural_reasoning
Datasets & benchmarksHugging Face dataset by facebook
facebook/natural_reasoning -
MetaMathQA
Datasets & benchmarksHugging Face dataset by meta-math
meta-math/MetaMathQA
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.