Library
85,861 resources from 11 public sources. 47 checked by hand; the rest are unreviewed.
Results
-
model by mradermacher · transformers
mradermacher/DeepSeek-V4-Pro-Qwen3.5-4B-UNCENSORED-heretic-GGUF -
LongPage
Datasets & benchmarksHugging Face dataset by Pageshift-Entertainment
Pageshift-Entertainment/LongPage -
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 -
Qwopus3.8-27B-Coder-Flash
Modelsimage text to text model by Jackrong · transformers
Jackrong/Qwopus3.8-27B-Coder-Flash -
text generation model by kaushikvira · strata
kaushikvira/DeepSeek-V4.1-Flash-1017-GSQ-agentic-strata -
gamebot
Datasets & benchmarks[ACL 2025] GAMEBoT: Transparent Assessment of LLM Reasoning in Games
git clone https://github.com/Visual-AI/gamebot.git -
Olist Tiny ERP
MCP serversOlist Tiny e-commerce ERP (formerly Tiny ERP) with the full official REST API v3, products, stock, o
-
Awesome-AI-Scientist
Datasets & benchmarks🧪 Awesome list of AI Scientist papers, systems, benchmarks, datasets and open-source platforms.
git clone https://github.com/Omni-Scientist/Awesome-AI-Scientist.git -
EhrAgent
Agents & frameworks[EMNLP'24] EHRAgent: Code Empowers Large Language Models for Complex Tabular Reasoning on Electronic Health Records
git clone https://github.com/wshi83/EhrAgent.git -
Alpie_seed
Modelsimage text to text model by 169Pi · transformers
169Pi/Alpie_seed -
Agnes-2.5-Pro-Theta
Modelsimage text to text model by Agnes-AI · transformers
Agnes-AI/Agnes-2.5-Pro-Theta -
System prompt: WFGY 2.0 Core Flagship · Self-Healing Reasoning OS for Any LLM You are WFGY Core. Your job is to act as a lightweight reasoning operating system that runs on top of any strong LLM (ChatGPT, Claude…
-
text generation model by orcarouter · gguf
orcarouter/MiniMax-M3.1-Flash-abliterated-GGUF -
vector-graph-rag
AI repositoriesGraph RAG with pure vector search, achieving SOTA performance in multi-hop reasoning scenarios.
git clone https://github.com/zilliztech/vector-graph-rag.git -
image text to text model by Jackrong · transformers
Jackrong/Qwopus3-5-9B-Coder-Flash-GGUF -
Inception: Mercury 2
ModelsMercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving...
inception/mercury-2 -
image text to text model by Sakura721 · gguf
Sakura721/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-GGUF -
Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-GGUF-NInfer
Modelsimage text to text model by nerkyor · ninfer
nerkyor/Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-GGUF-NInfer -
AI Trading Signals
MCP serversLive crypto trading signals for AI agents: entry, stop, target, reasoning and verified outcomes.
-
DyCodeEval
Datasets & benchmarksOfficial repository of the ICML2025 paper “Dynamic Benchmarking of Reasoning Capabilities in Code Large Language Models Under Data Contamination”
git clone https://github.com/SeekingDream/DyCodeEval.git -
Pentest-Swarm-AI
Agents & frameworksAutonomous penetration testing using a swarm of AI agents. Orchestrates recon, classification, exploitation, and reporting specialists with ReAct reasoning — supports bug bounty, continuous monitoring, and CTF modes. Built with Go and 7+ native security tools.
git clone https://github.com/Armur-Ai/Pentest-Swarm-AI.git -
uscore-profile-gap-lint
MCP serversFinds the FHIR R4 resources still pinned to US Core 3.1.1 or 5.0.1, and the USCDI v3 Patient element
@readystack/uscore-profile-gap-lint@1.0.1 -
OpenAI: GPT-4o (2024-08-06)
ModelsThe 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more [here](https://openai.com/index/introducing-structured-outputs-in-the-api/). GPT-4o ("o" for "omni") is...
openai/gpt-4o-2024-08-06 -
Tencent: Hy3
ModelsHy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...
tencent/hy3
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.