Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
K2-Horizon-MoVA-36B-A4B
Modelstext generation model by IFM · transformers
IFM/K2-Horizon-MoVA-36B-A4B -
fine-tuning
Tools & appsThe Best TypeScript framework for fine-tuning
git clone https://github.com/arkorlab/fine-tuning.git -
Open weights briefly beat every proprietary model in early 2025 (deepseek-r1); today the best.
-
EdgeRock
Modelstext generation model by rockmatrix-ai
rockmatrix-ai/EdgeRock -
Of 51 named model launches since 6 Jul 2026, 22 stated their weights: 18 closed, 4 open. All.
-
openmake_llm
MCP serversOpen-source, self-hosted AI workspace for local and open-weight LLMs with vLLM, LiteLLM, autonomous agents, MCP tools, deep research, artifacts, and BYOK.
git clone https://github.com/openmake/openmake_llm.git -
AgileRL
Agents & frameworksThe complete post-training stack for LLMs, plus RL for any problem. SFT, DPO and multi-turn agentic RL, with evolutionary hyperparameter optimization built in.
git clone https://github.com/AgileRL/AgileRL.git -
blender-open-mcp
MCP serversMCP for Blender Using Open Weights Models
git clone https://github.com/dhakalnirajan/blender-open-mcp.git -
awesome-decision-models
AI repositoriesA curated list of decision models (System One / typed decision models): hosted APIs, open-weight models, runtimes, SDKs, applications, benchmarks, and papers.
git clone https://github.com/AnotiaWang/awesome-decision-models.git -
atomic-agent
AI repositoriesAtomic Agent is a local-first AI agent. Runs open-weight models on your own machine via llama.cpp.
git clone https://github.com/AtomicBot-ai/atomic-agent.git -
QuelLLM
Public APIsOpen-weight language model catalogue with memory requirements and installation metadata
-
BambooAI
Agents & frameworksAI-powered data analysis workbench built for transparency, reproducibility and user control. Inspect the code and evidence behind results, verify calculations through replay, and choose from a wide range of models, including local open-weight models.
git clone https://github.com/pgalko/BambooAI.git -
Qwen: Qwen3.8 2.4T A95B
ModelsQwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...
qwen/qwen3.8-2.4t-a95b -
fagan
MCP serversAutonomous coding pipeline: frontier models plan and review, open-weight models write the code.
-
c0mpute
MCP serversChat with open-weight models on the c0mpute open compute network (c0mpute.com)
-
Atomic-Chat
AI repositoriesLocal AI app and inference engine for agents. Run open-weight LLMs locally — private, 100% offline on your computer. Join our Discord: https://discord.com/invite/8wGSsvmg4V
git clone https://github.com/AtomicBot-ai/Atomic-Chat.git -
Model Tested
MCP serversIndependent test scores for open-weight LLMs: best model for your GPU or Mac, comparisons.
-
UncensoredLLM
MCP serversAbliterated and derestricted open-weight models on one prepaid key, prices readable without a key
-
quelllm-mcp
MCP serversMCP server for quelllm.fr: 190+ open-weights LLM catalog - list, compare, VRAM and cost estimates
-
Local AI Picks
MCP serversFind open-weight AI models that fit your hardware, with weight sizes, memory and sources.
-
NLP.COM.AI Open Model Catalog
MCP serversSearch curated open-weight AI model releases, licenses, architectures, and primary sources.
-
The Neural Net
MCP serversSourced register of open-weight AI model releases and AI news. Every field cites its source.
-
Open Uncensored
MCP serversOpen-weight and abliterated LLMs on one API: compare models and rankings, chat, check credits.
-
ai-model-license-lint
MCP serversReads the open-weight model IDs in your code and names the licence clause that binds you - 22 rules
@readystack/ai-model-license-lint@1.0.2
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.