Young Python growth, turned up in the mcp-server patch. A seedling, new this season.
In the maintainer's words ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.
3 of your topics (llm, machine-learning, mcp)
~2298 stars a month (new, 9 months ago, top 11% in machine-learning)
A young C specimen, spotted in the deep-learning patch. Fresh from the seed bed.
In the maintainer's words A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.
~3380 stars a month (new, 4 months ago, top 3% in machine-learning)
A young find from in the cli patch, rooted in Python. Fresh from the seed bed.
In the maintainer's words Don't memorize ML. Understand it from first principles including Inference, Cuda, Deep Learning, Data Science and Reinforcement Learning
~286 stars a month (new, 3 months ago, top 18% in deep-learning)
A young find from in the machine-learning patch, rooted in Python. A seedling, new this season.
In the maintainer's words A small, fast decision model, or system one model, for agentic workflows. Pick between options or rate on a scale faster than an LLM, with a calibrated confidence on every decision.
~715 stars a month (new, 52d ago, top 11% in machine-learning)
A young find from in the deep-learning patch, rooted in Python. Barely out of the soil.
In the maintainer's words A machine learning primer built from first principles. For engineers who want to reason about ML systems the way they reason about software systems.
~158 stars a month (new, 8 months ago, top 21% in deep-learning)
Found in the healthcare patch: a young HTML specimen. Barely out of the soil.
In the maintainer's words Auditing algorithmic bias in criminal justice, hiring, lending, healthcare, welfare, and tenant screening: 7 open-source audits, measurable fairness gaps, and concrete fixes.
~12 stars a month (new, 6 months ago, top 27% in healthcare)
Found in the cli patch: a young Swift specimen. Fresh from the seed bed.
In the maintainer's words Shared Single-file memory layer for all your agents, sub mili-second RAG over text, photo and video on Apple Silicon.. No Server. No API. One File. Pure Swift
~81 stars a month (new, 10 months ago, top 45% in data-science)
Spotted in the machine-learning patch, a young specimen rooted in JavaScript. Barely out of the soil.
In the maintainer's words Interactive, source-linked ML workflow diagrams written by your coding assistant (Copilot, Codex or Claude Code) and opened in VS Code.
~192 stars a month (new, 2 months ago, top 24% in vscode-extension)
Found in the deep-learning patch: a young Python specimen. Fresh from the seed bed.
In the maintainer's words Bilingual (中文+EN) ML / LLM / diffusion / agent interview cheat sheets for AI 秋招 — generated by ARIS /interview-cheatsheet, rendered by /render-html into single-file HTML, reads anywhere — plus a CV→D…
~107 stars a month (new, 6 months ago, top 40% in deep-learning)
Young Python growth, turned up in the rag patch. Fresh from the seed bed.
In the maintainer's words Free Course : Data, Machine Learning, Deep Learning and AI Engineering, the long way round: the math, the code, the systems and the security. 173 lessons, 166 runnable labs, no shortcuts. Free under …
~97 stars a month (new, 55d ago, top 29% in data-engineering)
A young find from in the ai-agents patch, of no fixed habitat. A seedling, new this season.
In the maintainer's words Free interactive tools for data scientists to learn MLOps, ML system design and agentic analytics: a production ML system map, ML project structure, data drift simulator, agentic analytics system map…
~497 stars a month (new, 18d ago, top 18% in data-science)
Spotted in the machine-learning patch, a young specimen rooted in Swift. Barely out of the soil.
In the maintainer's words On-device AI SDKs for iOS, macOS, Android, and the web. Small, focused models that run fully offline in Swift, Kotlin, and JavaScript with Core ML, LiteRT, and WebAssembly.
~103 stars a month (new, 4 months ago, top 48% in machine-learning)
Found in the machine-learning patch: a young TypeScript specimen. Fresh from the seed bed.
In the maintainer's words Become a cracked AI/ML researcher/engineer with this unconventional textbook covering maths, computing, and ML with intuition.
~799 stars a month (new, 10 months ago, top 9% in computer-vision)
Young Python growth, turned up in the machine-learning patch. Barely out of the soil.
In the maintainer's words An open workbench for leakage-aware, calibrated, explainable risk modeling on longitudinal EHR-style data — built for students, labs, and health-informatics research.
~3 stars a month (new, 8 months ago, top 41% in ehr)
A young find from in the computer-vision patch, rooted in C++. Barely out of the soil.
In the maintainer's words Fast, offline OCR for Node.js & C++. PP-OCRv6 with Core ML / WebGPU hardware acceleration — recognize text in images with confidence scores & coordinates. npm: @arcships/light-ocr
~153 stars a month (new, 4 months ago, top 29% in computer-vision)
Found in the claude-code patch: a young Python specimen. A seedling, new this season.
In the maintainer's words 🔥 An autonomous AI agent that runs your deep learning experiments 24/7 while you sleep. Zero-cost monitoring, Leader-Worker architecture, constant-size memory.
~152 stars a month (new, 8 months ago, top 23% in deep-learning)
A young Python specimen, spotted in the deep-learning patch. A seedling, new this season.
In the maintainer's words Cevahir Zihin: a mind that learns by living, not a Transformer. It keeps knowledge as evidence on ties, attends with a Seven-Place Focus and learns from every conversation. Also: a Turkish BPE tokeni…
pushed today
~36 stars a month (new, 9 months ago, top 71% in deep-learning)
Young growth, turned up in the machine-learning patch. Fresh from the seed bed.
In the maintainer's words A complete, structured hub for learning Artificial Intelligence — covering AI, Machine Learning, Deep Learning, and Data Science with books, roadmaps, and curated resources from beginner to advanced.
~111 stars a month (new, 11 months ago, top 35% in deep-learning)
Found in the data-science patch: a young Dart specimen. Barely out of the soil.
In the maintainer's words PocketStrike is a privacy-first mobile AI workstation. It combines zero-cloud native on-device GGUF inference (ARM NEON accelerated) │ with frontier cloud LLMs, multi-step ReAct agent tools, Model Co…
~61 stars a month (new, 3 months ago, top 49% in data-science)
Young Python growth, turned up in the agentic-ai patch. Barely out of the soil.
In the maintainer's words 🤖 AI Agent-driven Kaggle competition workflow. Battle-tested patterns for score stabilization, submission troubleshooting, kernel workflows, and spec-driven development.
~29 stars a month (new, 7 months ago, top 72% in data-science)
Young Python growth, turned up in the machine-learning patch. A seedling, new this season.
In the maintainer's words Z80-μLM is a 2-bit quantized language model small enough to run on an 8-bit Z80 processor. Train conversational models in Python, export them as CP/M .COM binaries, and chat with your vintage compute…
~102 stars a month (new, 11 months ago, top 41% in nlp)
Found in the machine-learning patch: a young Jupyter Notebook specimen. Barely out of the soil.
In the maintainer's words Companion code for Machine Learning From Scratch — 10 core ML algorithms built from scratch with NumPy, compared with Scikit-learn and PyTorch.
~49 stars a month (new, 7 months ago, top 60% in data-science)