Learn AI and LLMs from scratch using free resources

[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.

A selective learning and memory substrate for agentic systems — typed, revisable, decayable memory with competence learning and trust-aware retrieval.

A practical framework for AI-Assisted Research in Mathematics and Machine Learning

The definitive OpenAI, Claude, MCP, Harness, Evals, and Production Agent Systems learning roadmap.

A collection of servers which are deliberately vulnerable to learn Pentesting MCP Servers.

A universal, industry-neutral taxonomy of cognitive core skills (perception, memory, reasoning, planning, action, verification, learning, governance) for LLMs, SLMs, AI agents, and world models — with schemas, 159 skill cards, benchmarks, and CI.

A collection of notes on Data Science

memX: self-learning, self-maintaining memory plugin for AI agents; native support for claude code, codex, and openclaw

Solid Tumor Associative Modeling in Pathology

Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning

Experiment task scheduling made easy.

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→DBLP-fact-checked academic homepage generator and hand-authored long-form blogs 🌱

In-depth tutorials on LLMs, RAGs and real-world AI agent applications.

Turn dense long-form ideas into immersive Reading Editions.

OpenSquilla — Token-Efficient AI Agent with same budget, higher intelligence density

Install, run and deploy your own decentralized AI agent service

README-first research reproduction skills with bounded execution, auditable evidence, and byte-preserving README annotations.

SRA-Bench and SR-Agents: a benchmark and toolkit for skill-retrieval-augmented LLM agents.

Curated list of AutoResearch use cases with optimization traces and open source implementations

The Enterprise-Grade Multi-Agent Orchestration Framework. Website: https://swarms.ai

MCP server for spatial transcriptomics analysis through natural language interfaces.

Umbrella package for SciTeX — reproducible science from raw data to manuscript

🔬 A Researcher&Agent-Friendly Framework for Time Series Analysis. Train Any Model on Any Dataset!