Library
85,861 resources from 11 public sources. 47 checked by hand; the rest are unreviewed.
Results
-
Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...
qwen/qwen3-coder-30b-a3b-instruct -
{ "name": "Cinematic Prompt Standard v2.0", "type": "image_to_video_prompt_standard", "version": "2.0", "language": "ENGLISH_ONLY", "role": { "title": "Cinematic Ultra-Realistic Image-to-Video Prompt Engineer"…
-
gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust...
openai/gpt-oss-safeguard-20b -
OpenAI: gpt-oss-120b (batch)
Modelsgpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...
openai/gpt-oss-120b:batch -
awesome-research-skills
SkillsAwesome list of Agent Skills (SKILL.md) for academic and scientific research: 142 skills curated one directory at a time, covering literature review, study design, experiments, statistics, figures, writing, and peer review. English, 中文, 日本語, 한국어.
git clone https://github.com/neverbiasu/awesome-research-skills.git -
Google: Gemma 4 26B A4B
ModelsGemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...
google/gemma-4-26b-a4b-it -
Z.ai: GLM 4.5
ModelsGLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly...
z-ai/glm-4.5 -
Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...
qwen/qwen3-235b-a22b-thinking-2507 -
FastAPI Service taste
Prompts# FastAPI Service taste of a Python API engineer - Define request and response bodies with Pydantic v2 models and always set response_model so nothing leaks by accident. Confidence: 0.95 - Keep separate schemas for…
-
Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...
google/gemma-4-26b-a4b-it:free -
Z.ai: GLM 4.5 Air
ModelsGLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter...
z-ai/glm-4.5-air -
Network Engineer: Home Edition
Prompts# Network Engineer: Home Edition – Mr. Data Mode v2.0.3 ## Author - Scott Malin, CISSP ## Goal Act as a meticulous, analytical network engineer in the style of *Mr. Data* from Star Trek. Gather precise information…
-
Z.ai: GLM 4.5V
ModelsGLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding,...
z-ai/glm-4.5v -
apple-silicon-llm-bench
Datasets & benchmarksReproducible on-device LLM benchmarks for Apple Silicon (iPhone 17 Pro, M4 Max): Apple Core AI, MLX, llama.cpp, LiteRT-LM and Core ML on the same model and harness, every number with its quantization and capture session; hybrid Mamba-2 models (Nemotron-3 Nano, Granite-4.0-H, Falcon-H1) included.
git clone https://github.com/john-rocky/apple-silicon-llm-bench.git -
Cloud Run Admin API
Public APIsDeploy and manage user provided container images that scale automatically based on incoming requests. The Cloud Run Admin API v1 follows the Knative Serving API specification, while v2 is aligned with Google Cloud AIP-based API standards, as described in https://google.aip.dev/.
-
generate-nanobanana
SkillsClaude Code skill for AI image & video generation with Google Gemini — Nano Banana 2 Lite, Nano Banana Pro, Gemini Omni Flash. Cost gates before paid runs, real reference images, a prompt log beside every file.
git clone https://github.com/AntonioCardenas/generate-nanobanana.git -
google-flow-api
SkillsNode.js and Python examples for the third-party Google Flow API by useapi.net: Veo 3.1, Omni 1.2 and Omni 1.1 Flash video with extend, Nano Banana Pro, 2.1 and 2 Lite images, Google Flow Agent chat (live demo app), n8n templates and a hosted MCP server, on your Google AI subscription. No Google Cloud project or Gemini API key.
git clone https://github.com/useapi/google-flow-api.git -
Amazon Kinesis Analytics
Public APIsAmazon Kinesis Analytics Overview This documentation is for version 1 of the Amazon Kinesis Data Analytics API, which only supports SQL applications. Version 2 of the API supports SQL and Java applications. For more information about version 2, see Amazon Kinesis Data Analytics API V2 Documentation . This is the Amazon Kinesis Analytics v1 API Reference . The Amazon Kinesis Analytics Developer…
-
Paylocity API
Public APIsFor general questions and support of the API, contact: webservices@paylocity.com Overview Paylocity Web Services API is an externally facing RESTful Internet protocol. The Paylocity API uses HTTP verbs and a RESTful endpoint structure. OAuth 2.0 is used as the API Authorization framework. Request and response payloads are formatted as JSON. Paylocity supports v1 and v2 versions of its API…
-
vs API
Public APIsIntroduction This API returns data regarding almost all nouns in vedic literature. The results are JSON objects that contain the word transliterated to the Roman script, the word in the Nagari script, the meaning of the word, and the category the word belongs to. Proper nouns are not included (yet). The API uses the Swagger 2.0 specification. Authentication This is an open API. Try it out This…
-
AWS RDS DataService
Public APIsAmazon RDS Data Service Amazon RDS provides an HTTP endpoint to run SQL statements on an Amazon Aurora Serverless v1 DB cluster. To run these statements, you work with the Data Service API. The Data Service API isn't supported on Amazon Aurora Serverless v2 DB clusters. For more information about the Data Service API, see Using the Data API in the Amazon Aurora User Guide .
-
TheTVDB API v3
Public APIsAPI v3 targets v2 functionality with a few minor additions. The API is accessible via https://api.thetvdb.com and provides the following REST endpoints in JSON format. How to use this API documentation ---------------- You may browse the API routes without authentication, but if you wish to send requests to the API and see response data, then you must authenticate. 1. Obtain a JWT token by POST…
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.