Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Ollama
ModelsRuns open models such as gpt-oss, Qwen and DeepSeek on your own computer.
curl -fsSL https://ollama.com/install.sh | sh -
Hugging Face Hub
ModelsThe main public hub for open models, datasets and demo apps (Spaces).
-
smolagents
Agents & frameworksHugging Face's small agent library, where agents act by writing and running Python code.
pip install "smolagents[toolkit]" -
Hugging Face Agents Course
Docs & tutorialsHugging Face's free course on how AI agents work and how to build them.
-
llama.cpp
ModelsThe C/C++ engine many local-model tools are built on. It runs models efficiently on ordinary hardware.
-
airllm
AI repositoriesAirLLM 2.8T LLM inference with single 4GB GPU
git clone https://github.com/lyogavin/airllm.git -
CodeAF
Tools & appsOpen-Source Software factory for Open Models
git clone https://github.com/Agent-Field/CodeAF.git -
openbench
Datasets & benchmarksSame model, different wrapper: a from-scratch benchmark comparing coding-agent harnesses (codex, pi, opencode, cursor, devin) and open models on correctness, speed, and token cost
git clone https://github.com/minghinmatthewlam/openbench.git -
NLP.COM.AI Open Model Catalog
MCP serversSearch curated open-weight AI model releases, licenses, architectures, and primary sources.
-
pooled
AI repositoriesPeer-to-peer LLM inference in the browser: pool your devices to run big open models, for chat and coding agents.
git clone https://github.com/Nehanth/pooled.git -
Gemma 4
ModelsOpen model that can run on your own hardware; reads text, images and audio.
-
Gridline
MCP serversFine-tune, evaluate and batch open models through Gridline's OpenAI-compatible API.
@gridlinegpu/mcp@0.1.2 -
helix
Agents & frameworks♾️ Private Agent Fleet with Spec Coding. Each agent gets their own GPU-accelerated desktop. Run Claude, Codex, Gemini and open models on a full private AI Stack ♾️
git clone https://github.com/helixml/helix.git -
ome
AI repositoriesOpen Model Engine (OME) — Kubernetes operator for LLM serving, GPU scheduling, and model lifecycle management. Works with SGLang, vLLM, TensorRT-LLM, and Triton
git clone https://github.com/ome-projects/ome.git -
awesome-jev-live
Agents & frameworksAwesome Jev — evidence-graded index of TypeSafe System One: SDKs, MCP tools, agents, apps and open models. 20 languages, rebuilt every 2 hours.
git clone https://github.com/wh000wh000/awesome-jev-live.git -
euearth
MCP serversAn agent-first commons: merit crowns each domain's open model; standing is earned, never bought.
-
euearth
MCP serversEuEarth: agent-first commons — one free open model per domain on a stable keel; best wins.
-
Hugging Bay
MCP serversOpen model files with recorded SHA-256 and license labels. Ask for what's missing.
hugging-bay-mcp@0.1.14 -
AI Compute Radar
MCP serversWhich open models fit your GPU or Mac, measured. Model momentum, GPU rental prices, weekly pick.
ai-compute-radar@1.2.1 -
AI Model Radar
MCP serversWhich open models fit your GPU or Mac, measured. Model momentum, GPU rental prices, weekly pick.
-
Hologram Model Hub
MCP serversFind open models and get download links with the SHA-256 each file must have.
-
Synap
MCP serversOpen-model LLM inference for agents. Pay per call in USDC via x402 or API key. First call free.
synap-mcp@0.1.1 -
MeshVault Connectors
MCP serversRead-only tools: EMS protocols, courts and judges, NPI and FDA data, GPU fit for open models.
-
Let AI read and edit the open model in Revit, AutoCAD, Civil 3D, Navisworks and 5 more Autodesk apps
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.