Agent skill · research science · aradotso
awesome-opensource-ai
awesome-opensource-ai — an agent skill for coding agents.
Why this skill is useful
Provides a curated list of niche open-source AI tools and frameworks that the AI wouldn't reliably generate on its own.
What it needs
About 8k tokens when loaded. Last updated 2026-07-09. 70 stars on the source repository.
What this skill does
Small (1B–7B) — Edge, mobile, low-resource: Phi-4-Mini (Microsoft) — best reasoning per parameter Gemma 3 2B/7B (Google) — strong efficiency Qwen3.5-3B/7B — excellent multilingual Medium (8B–30B) — Balanced production use: Llama 4 8B — general purpose workhorse Qwen3.5-14B — coding + math Mistral Small — multilingual, tool use Large (70B+) — Max capability open: Llama 4 405B — frontier open model DeepSeek-V3.2 (MoE 671B active 37B) — math/reasoning Qwen3.5-72B — top open coding/math Coding Specialists: Qwen2.5-Coder-32B — #1 open coding DeepSeek-Coder-V2 — MoE coding powerhouse StarCoder2-15B — 600+ languages, transparent Vision-Language: Qwen2.5-VL-72B — top open VLM InternVL 2.5 — charts, OCR, video LLaVA-Next — most popular/documented python import torch import torch.nn as nn from torch.utils.data import DataLoader Define model class SimpleNet(nn.Module): def init(self, inputdim, hiddendim, outputdim): super().init() self.layers = nn.Sequential( nn.Linear(inputdim, hiddendim), nn.ReLU(), nn.Dropout(0.1), nn.Linear(hiddendim, outputdim) ) def forward(self, x): return self.layers(x) model = SimpleNet(784, 256, 10).to("cuda") optimizer = torch.optim.AdamW(model.parameters(), lr=3e-4) criterion = nn.CrossEntropyLoss() Training loop for epoch in range(10): for batchx, batchy in dataloader: batchx, batchy = batchx.to("cuda"), batchy.to("cuda") optimizer.zerograd() logits = model(batchx) loss = criterion(logits, batchy) loss.backward() optimizer.step() python from transformers import AutoTokenizer, AutoModelForCausalLM import torch modelid = "meta-llama/Llama-3.1-8B-Instruct" tokenizer = AutoTokenizer.frompretrained(modelid) model = AutoModelForCausalLM.frompretrained( modelid, torchdtype=torch.bfloat16, devicemap="auto", # auto-distributes across available GPUs ) messages = [ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "Explain gradient descent in simple terms."}, ] inputids = tokenizer.applychattemplate( messages, addgene …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aradotso/awesome-opensource-ai