Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
R-KV
AI repositories[Neurips 2025] R-KV: Redundancy-aware KV Cache Compression for Reasoning Models
git clone https://github.com/Zefan-Cai/R-KV.git -
deep-searcher
AI repositoriesOpen Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.
git clone https://github.com/zilliztech/deep-searcher.git -
xVerify
Datasets & benchmarksxVerify: Efficient Answer Verifier for Reasoning Model Evaluations
git clone https://github.com/IAAR-Shanghai/xVerify.git -
reasoning-from-scratch
AI repositoriesImplement a reasoning LLM in PyTorch from scratch, step by step
git clone https://github.com/rasbt/reasoning-from-scratch.git -
Search-o1
AI repositories🔍 Search-o1: Agentic Search-Enhanced Large Reasoning Models [EMNLP 2025]
git clone https://github.com/RUC-NLPIR/Search-o1.git -
eShopLite
AI repositorieseShopLite is a set of reference .NET applications implementing an eCommerce site with features like Semantic Search, MCP, Reasoning models and more.
git clone https://github.com/Azure-Samples/eShopLite.git -
Elorian: Glimpse
ModelsGlimpse is a multimodal visual reasoning model from Elorian, built for visual understanding and complex visual reasoning in the physical world. It reasons directly over images and video rather than...
elorian/glimpse -
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 -
MiniMax: MiniMax M1
ModelsMiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom "lightning attention" mechanism, allowing it...
minimax/minimax-m1 -
LiquidAI: LFM2.5-2.6B
ModelsLFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...
liquid/lfm-2.5-2.6b -
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 -
LiquidAI: LFM2.5-2.6B (free)
ModelsLFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...
liquid/lfm-2.5-2.6b:free -
Sakana: Sakana Namazu
ModelsSakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with additional training for Japanese language and business contexts. It is suited for Japanese instruction following,...
sakana/sakana-namazu -
DeepSeek: DeepSeek V3.1
ModelsDeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...
deepseek/deepseek-chat-v3.1 -
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 -
Qwen: Qwen3.8 Flash
ModelsQwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis.
qwen/qwen3.8-flash -
MoonshotAI: Kimi K3
ModelsKimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...
moonshotai/kimi-k3 -
KT: Mi:dm K 3.0 Pro
ModelsMi:dm K 3.0 Pro is a Mixture-of-Experts reasoning model from KT, with 120B total and 12B active parameters. It uses a hybrid architecture that mixes Mamba, MoE and attention layers.
kt/midm-k-3.0-pro -
Inkling 2 Small is an open-weight multimodal mixture-of-experts reasoning model from Thinking Machines Lab, with 17B active parameters out of 594B total. It is the first model in the second...
thinkingmachines/inkling-2-small -
Ling 3.2 Flash is a hybrid reasoning model from inclusionAI that accepts text and image input, with a 1M-token context window and up to 200 images per request. Thinking can...
inclusionai/ling-3.2-flash:free -
Meta: Muse Wonder
ModelsMuse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with...
meta/muse-wonder -
Qwen: Qwen3.7 Flash
ModelsQwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world...
qwen/qwen3.7-flash -
MoonshotAI: Kimi K3 (batch)
ModelsKimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...
moonshotai/kimi-k3:batch
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.