Library
86,235 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
Looks like a goal we have a starting path for: I want to research potential clients
-
text generation model by Infatoshi · exllamav3
Infatoshi/GLM-5.3-UNCENSORED-EXL3-3.0bpw -
TapeAgents
Agents & frameworksTapeAgents is a framework that facilitates all stages of the LLM Agent development lifecycle
git clone https://github.com/ServiceNow/TapeAgents.git -
doc2harness
Datasets & benchmarksOfficial Code for the paper "Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents "
git clone https://github.com/YuyaoGe/doc2harness.git -
Step-3.7-Flash
Modelsimage text to text model by stepfun-ai · transformers
stepfun-ai/Step-3.7-Flash -
awesome-langchain-zh
Agents & frameworkslangchain 工具,流程设计组件,服务,代理以及相关学习文档的合集(agent,service,tutorials,flow-design)
git clone https://github.com/microxxx/awesome-langchain-zh.git -
image text to text model by baidu · transformers
baidu/ERNIE-4.5-VL-28B-A3B-Thinking -
paper2slides
Agents & frameworksTransform any arXiv papers into slides using LLMs
git clone https://github.com/takashiishida/paper2slides.git -
LFM2.5-350M
Modelstext generation model by LiquidAI · transformers
LiquidAI/LFM2.5-350M -
llm-api-starterkit
Docs & tutorialsBeginner-friendly repository for launching your first LLM API with Python, LangChain and FastAPI, using local models or the OpenAI API.
git clone https://github.com/tleers/llm-api-starterkit.git -
text generation model by NousResearch · transformers
NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO -
minimind-notes
Docs & tutorials🚀 [从零构建 LLM] 极简大模型训练原理与实践指南。包含 Transformer, Pretraining, SFT 核心代码与对照实验。 | A minimal, principle-first guide to understanding and building LLMs from scratch.
git clone https://github.com/joyehuang/minimind-notes.git -
wesight
SkillsOpen-source desktop AI agent workspace with one-click Claude Code, Codex, OpenClaw, Hermes Agent setup and custom LLM model routing.
git clone https://github.com/freestylefly/wesight.git -
KG_RAG
PromptsEmpower Large Language Models (LLM) using Knowledge Graph based Retrieval-Augmented Generation (KG-RAG) for knowledge intensive tasks
git clone https://github.com/BaranziniLab/KG_RAG.git -
Glyd
Datasets & benchmarksLossless AI compression: 33% less GPU memory, bit for bit.
git clone https://github.com/surya-koritala/Glyd.git -
LFM2-2.6B-Exp
Modelstext generation model by LiquidAI · transformers
LiquidAI/LFM2-2.6B-Exp -
Apriel-1.6-15b-Thinker
Modelsimage text to text model by ServiceNow-AI · transformers
ServiceNow-AI/Apriel-1.6-15b-Thinker -
llmman
AI repositoriesRun any agent on any model, models stored as OCI images
git clone https://github.com/llmmanorg/llmman.git -
crit
AI repositoriesReview AI coding agents' plans, diffs and running apps in the browser. Local-first, works with any agent.
git clone https://github.com/tomasz-tomczyk/crit.git -
Mage-VL
Modelsimage text to text model by microsoft · transformers
microsoft/Mage-VL -
inferssd
AI repositoriesRun models larger than your RAM or VRAM by streaming MoE experts from SSD. Built on llama.cpp.
git clone https://github.com/wici-ai/inferssd.git -
blades
Agents & frameworksBlades is a Go-based multimodal AI Agent framework.
git clone https://github.com/go-kratos/blades.git -
ElatoAI
AI repositoriesRealtime Voice AI with 100+ Models on Arduino ESP32 with Secure Websockets and Edge Functions for AI Companions, and Devices
git clone https://github.com/akdeb/ElatoAI.git -
memoria
AI repositoriesSecure memory management for AI Agents • Ensures data integrity • Reduces hallucinations • Maintains consistent long-term context
git clone https://github.com/matrixorigin/memoria.git -
arkon
MCP serversArkon: Enterprise AI Knowledge Hub & MCP Server. Self-hosted knowledge base for teams to manage RAG contexts, access policies, and AI skills. Connect Claude and other LLMs via Model Context Protocol (MCP) for automated, secure organizational knowledge integration.
git clone https://github.com/nduckmink/arkon.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.