Library
86,219 resources from 11 public sources. 46 checked by hand; the rest are unreviewed.
Results
-
agents-from-scratch
PromptsBuild AI agents from first principles using a local LLM - no frameworks, no cloud APIs, no hidden reasoning.
git clone https://github.com/pguso/agents-from-scratch.git -
MoonshotAI: Kimi K2 Thinking
ModelsKimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...
moonshotai/kimi-k2-thinking -
Nous: Hermes 4 405B
ModelsHermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...
nousresearch/hermes-4-405b -
Made with Nano Banana 2.1 Prompt: Vertical 9:16 candid fashion portrait of a beautiful East Asian girl wearing a fitted long-sleeve orange turtleneck and a black mini skirt, with long, messy, loose black hair. She…
-
IBM: Granite 4.2 8B
ModelsGranite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows that need multi-step reasoning. It supports full, low-effort,...
ibm-granite/granite-4.2-8b -
OpenAI: o3 Mini (batch)
ModelsOpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the `reasoning_effort` parameter, which can be set to...
openai/o3-mini:batch -
A Mentat's eye on Sui DeepBook v3: read-only market data plus desk template tools. No keys.
-
LiquidAI: LFM2.5-24B-A2B
ModelsLFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools. Liquid...
liquid/lfm-2.5-24b-a2b -
OpenAI: GPT-5
ModelsGPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...
openai/gpt-5 -
OpenAI: o4 Mini (batch)
ModelsOpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning...
openai/o4-mini:batch -
Fireworks: Ember-1
ModelsEmber-1 is a specialized reasoning model from Fireworks Research, built on [Kimi K3](https://openrouter.ai/moonshotai/kimi-k3). It is designed to make every token go further: it produces shorter reasoning traces, using roughly 40%...
fireworks/ember-1 -
OpenAI: GPT-5 Pro
ModelsGPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and...
openai/gpt-5-pro -
OpenAI: GPT-5 (batch)
ModelsGPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...
openai/gpt-5:batch -
Begin by enclosing all thoughts within <thinking> tags, exploring multiple angles and approaches. Break down the solution into clear steps within <step> tags. Start with a 20-step budget, requesting more for complex…
-
inclusionAI: Ling 3.1 Flash
ModelsLing 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.
inclusionai/ling-3.1-flash -
OpenAI: GPT-5 Pro (batch)
ModelsGPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and...
openai/gpt-5-pro:batch -
OpenAI: GPT-5.1
ModelsGPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning...
openai/gpt-5.1 -
OpenAI: GPT-5.1 (batch)
ModelsGPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning...
openai/gpt-5.1:batch -
{[ { "SYSTEM_AUDIT_REPORT": { "PROMPT_NAME": "PALADIN_OCTEM_PLUS_v3.1", "STATUS": "HYPER_OPTIMIZED", "AUDIT_FINDINGS": [ "Eliminated redundant descriptor blocks (Objective/Optimization) by mapping them to ⟦P_VEC⟧…
-
modelplan
SkillsWhich AI coding model, at which effort, on which plan? Recommended efforts, a leaderboard at those efforts and plan advice from modelplan.ai, in Claude Code, Codex and the terminal (plugins, Skill, CLI).
git clone https://github.com/modelplan/modelplan.git -
The current api version is v3.4 The api methods listed below can be called directly from this page to test the output. You might set the api key to pre-authenticate all requests on this page (this will work if your secret is blank). API endpoint URL: http://{apiName}.text2data.com/v3/ {method} The api can be consumed directly or using our SDK. Our Excel Add-In and Google Sheets Add-on are also…
-
cross-review
Agents & frameworksCross-model review skills for Claude Code and Codex CLI: one agent orchestrates, another model reviews plans, code and reasoning.
git clone https://github.com/lploc94/cross-review.git -
Google: Gemini 2.5 Pro
ModelsGemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...
google/gemini-2.5-pro -
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
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.