Trackio is very minimalist and hackable i think you will like it
OPEN SOURCE
-
AI creativity is architecture, not imagination
By
–
people think ai creativity is magic. it paints, writes, composes – so we assume it’s “thinking” like us. but that’s not what’s happening under the hood. researchers recently showed that creativity in models comes from architecture, not imagination. the wiring matters more than
-
AI’s creativity stems from pattern recognition
By
–
ai doesn’t create because it “wants to.” it creates because we wired it to notice patterns. architectural choices like locality and equivariance force the model to capture structure in the data. that’s why it can remix old knowledge into something that looks new. creativity in
-
100+ Free Open Source AI Agents and RAG Tutorials
By
–
Stay tuned for more such interesting posts → @Saboo_Shubham_ I have created 100+ AI Agents and RAG tutorials, 100% free and opensource. P.S: Don't forget to star the repo to show your support
-
oLLM: Lightweight Library for Local LLM Inference
By
–
oLLM is a lightweight Python library for local large-context LLM inference. Run gpt-oss-20B, Qwen3-next-80B, Llama-3.1-8B on ~$200 consumer GPU with just 8GB VRAM. And this is without any quantization – only fp16/bf16 precision. 100% Opensource.
-
RAGLight: Lightweight Open Source RAG Library for Production Systems
By
–
RAGLight: Open Source RAG Library A lightweight Python library for building production-ready RAG systems, featuring LangGraph-powered agent pipelines and multi-provider LLM support with built-in GitHub integration and CLI tools. Check out RAGLight now!
-
Anuar Sharafudinov’s ollm Repository: Open Source LLM Project
By
–
Awesome work by Anuar Sharafudinov! Here's the repo:
↳ https://
github.com/Mega4alik/ollm -
oLLM: Lightweight Python Library for LLM Inference
By
–
Ace. oLLM is a lightweight Python library for LLM inference built on top of transformers Run qwen3-next-80B, GPT-OSS, Llama3, on consumer hardware. ↳ Handle 100k tokens on an 8GB GPU
↳ Works with contracts, logs, reports
↳ No quantization, just fp16/bf16 Repo in ↓ -
Language Models Learn to Think and Chat Better with RL
By
–
7. Language Models that Think, Chat Better A simple recipe, RL with Model-rewarded Thinking, makes small open models “plan first, answer second” on regular chat prompts and trains them with online RL against a preference reward.
-
Meta FAIR Releases CWM: 32B Open-Weights Code Execution Model
By
–
3. Code World Model Meta FAIR releases CWM, a 32B open-weights coder trained to model code execution and to act inside containers.