AI

AI Hands-On: A group of notebooks and other files which can help you learn AI from scratch.

General

How to Become an AI Engineer in 2026: A Self-Study Roadmap
The Three Best Pieces of Writing About AI in 2026 That You Must Read Right Now: The first is Matt Shumer’s “Something Big Is Happening,” which amassed north of 80 million views on X, bringing together the entire timeline in a miracle not seen since St. Paul walked the paths of the old world proselytizing for Christ’s word (the godlike reach of Shumer’s essay can be explained by the fact that the title allows every single person to project the biggest thing in their lives right now as the thing happening to everyone else: we all have main character syndrome, especially myself). To Shumer, the big thing happening is AI, plain and simple, without caveats or nuances: AI is big and AI is happening (it's probably irrelevant that he's an AI founder himself with a tendency to hype up claims that don't hold up under scrutiny).

The second is Citrini’s “The 2028 Global Intelligence Crisis,” a financial variation of the take-off scenario where AI ends up doing everything that doomer pundits and industry leaders have been warning of but instead of killing everyone it stops at killing the $13 trillion mortgage market (because of course, that’s the most dramatic thing that could happen if you’re a financial analyst). I read it until I reached a point where they give three examples of SaaS firms that could be affected—“Monday.com, Zapier, and Asana”— because when I asked Claude 4.6 Opus about the “SaaSpocalypse” two weeks earlier, it gave those three exact examples to illustrate its point. It might be a coincidence, but stochastic parrots are usually more parrot than stochastic.

The third one, and a personal favorite, is Sam Kriss’s Harper’s “Child’s play,” a retelling of Kriss’s experience among some of the most idiosyncratic personalities of the San Francisco tech scene. This is the last one chronologically and, in literary merit and arguably historical value, the best of the three. Kriss, unlike, I presume, Shumer and Citrini, is a veteran in the sport of disguising fiction as non-fiction—worthy heir to the Borgesian style, although perhaps born at the worst time possible now that everyone seems to be shamelessly copycatting his schtick—which is apparent from the fact that, among the three texts, his is the only one that feels real. His thesis is something I imagine everyone agrees with: obsessing over being “high agency” and living your life as a means to an end is, ultimately, a relentless run-up for a date with death.

The 10+1 Commandments of Human AI Co-Existence: "The 10+1 is a standard. Not everyone will adopt it - but those who do will lead the next era. If you're a policymaker, don't wait for regulation to catch up. If you're a CEO, don't wait for PR fallout to act with integrity. If you're building AI, don't just ask if it works - ask if it's worthy. We don't need more frameworks. We need a philosophical backbone. This is it."
AI Defeats the Purpose of a Humanities Education (The Harvard Crimson)
"The Open-Source Toolkit for Building AI agents"
Is Complexity an Illusion?: "Simplicity is held by many to be the key to general intelligence. Simpler models tend to “generalise”, identifying the cause or generator of data with greater sample efficiency. The implications of the correlation between simplicity and generalisation extend far beyond computer science, addressing questions of physics and even biology. Yet simplicity is a property of form, while generalisation is of function. In interactive settings, any correlation between the two depends on interpretation. In theory there could be no correlation and yet in practice, there is. Previous theoretical work showed generalisation to be a consequence of “weak” constraints implied by function, not form. Experiments demonstrated choosing weak constraints over simple forms yielded a 110 − 500% improvement in generalisation rate. Here we show that all constraints can take equally simple forms, regardless of weakness. However if forms are spatially extended, then function is represented using a finite subset of forms. If function is represented using a finite subset of forms, then we can force a correlation between simplicity and generalisation by making weak constraints take simple forms. If function is determined by a goal directed process that favours versatility (e.g. natural selection), then efficiency demands weak constraints take simple forms. Complexity has no causal influence on generalisation, but appears to due to confounding."
Rob Conery's posts exploring using AI in a dev setting:
"You're Building AI Apps Backwards: The Model-Product Problem"
"AI Models Need a Virtual Machine"
Artificial Intelligence for a Better Future: An Ecosystem Perspective on the Ethics of AI and Emerging Digital Technologies - Bernd Carsten Stahl (PDF)
Artificial Intelligence: Foundations of Computational Agents (2017), 2nd Edition - David L. Poole, Alan K. Mackworth @ Cambridge University Press (HTML, Slides)
Artificial Intelligence: Foundations of Computational Agents (2010), 1st Edition - David L. Poole, Alan K. Mackworth @ Cambridge University Press (HTML)
Deep Learning
Introduction to Autonomous Robots - Nikolaus Correll (PDF)
On the Path to AI: Law’s prophecies and the conceptual foundations of the machine learning age - Thomas D. Grant, Damon J. Wischik (PDF)
Probabilistic Programming & Bayesian Methods for Hackers - Cam Davidson-Pilon (HTML, Jupyter Notebook)
MIT researchers propose a new model for legible, modular software: Their new approach breaks systems into “concepts,” separate pieces of a system, each designed to do one job well, and “synchronizations,” explicit rules that describe exactly how those pieces fit together. The result is software that’s more modular, transparent, and easier to understand. A small domain-specific language (DSL) makes it possible to express synchronizations simply, in a form that LLMs can reliably generate. In a real-world case study, the team showed how this method can bring together features that would otherwise be scattered across multiple services. The team, including Daniel Jackson, an MIT professor of electrical engineering and computer science (EECS) and CSAIL associate director, and Eagon Meng, an EECS PhD student, CSAIL affiliate, and designer of the new synchronization DSL, explore this approach in their paper “What You See Is What It Does: A Structural Pattern for Legible Software,” which they presented at the Splash Conference in Singapore in October. The challenge, they explain, is that in most modern systems, a single feature is never fully self-contained. Adding a “share” button to a social platform like Instagram, for example, doesn’t live in just one service. Its functionality is split across code that handles posting, notification, authenticating users, and more. All these pieces, despite being scattered across the code, must be carefully aligned, and any change risks unintended side effects elsewhere. ... A concept bundles up a single, coherent piece of functionality, like sharing, liking, or following, along with its state and the actions it can take. Synchronizations, on the other hand, describe at a higher level how those concepts interact. Rather than writing messy low-level integration code, developers can use a small domain-specific language to spell out these connections directly. In this DSL, the rules are simple and clear: one concept’s action can trigger another, so that a change in one piece of state can be kept in sync with another. “Think of concepts as modules that are completely clean and independent. Synchronizations then act like contracts — they say exactly how concepts are supposed to interact. That’s powerful because it makes the system both easier for humans to understand and easier for tools like LLMs to generate correctly,” says Jackson. “Why can’t we read code like a book? We believe that software should be legible and written in terms of our understanding: our hope is that concepts map to familiar phenomena, and synchronizations represent our intuition about what happens when they come together,” says Meng.
DORA 2025: Measuring Software Delivery After AI: "Historically, DORA split metrics into two categories: Throughput (Lead Time for Changes, Deployment Frequency), and Stability (Time to Restore, Change Failure Rate). The problem was that Change Failure Rate consistently behaved like an outlier and didn’t load cleanly with the other metrics. So in 2024, DORA made a methodological adjustment: Time to Restore moved from stability to throughput; and Rework Rate was introduced as a stability metric. Rework Rate is about the number of unplanned deployments caused by production issues compared to total deployments. Change Failure Rate compares failed deployments to total deployments. You would typically expect more unplanned deployments than outright failed deployments, which makes Rework Rate a secondary proxy for measuring instability in systems. This metric shift was small potatoes compared to what the report introduced in 2025. In 2025, the DORA report moved away from low / medium / high / elite clusters entirely. Now the report introduces seven archetypes, based on eight measures: Throughput; Stability; Team performance; Product performance; Individual effectiveness; Time spent on valuable work; Friction; and Burnout"

Automation with ...

Suggestions

10 Agent Projects: a list of 10 AI agent projects you can try this weekend. They go from basic single agents to more advanced multi-agent systems.

History

The Quest for Artificial Intelligence: A History of Ideas and Achievements - Nils J. Nilsson (PDF)

Criticism

Tools

Lovable: Create apps and websites by chatting with AI
ChatGPT-5
- https://futurism.com/gpt-5-disaster
- ChatGPT Is Blowing Up Marriages as Spouses Use AI to Attack Their Partners

Reading

Himanshu:
1. Natural Language Processing with Transformers: Start with a thorough understanding of Transformers architecture and it's ecosystem through HuggingFace with Lewis Tunstall Leandro von Werra Thomas Wolf . Personally, There cannot be a better starting point. MUST follow their blogs.
2. Build a Large Language Model (From Scratch): Build your own Decoder Transformer(Architecture for "almost" all modern LLMs) from scratch with Sebastian Raschka, PhD . MUST follow his blogs too for the latest updates. Also, lucky he keeps his GitHub repo updated.
3. Get acquainted with the GenerativeAI ecosystem with Jay Alammar Maarten Grootendorst building LLM pipelines for various tasks and learning nitty gritty details of Fine-Tuning and PEFT. Hands-On Language Models
4. Explore Generative AI on AWS with Chris Fregly Antje Barth Shelbee Eigenbrode for an enterprise level challenges.
5. Dive into the beauty of engineering a GenAI Application with AI Engineering by Chip Huyen . It will level you up to think from the whole system perspective.
6. Build Generative AI Services with FastAPI with Ali Parandeh, CEng . A very practical book to knot all you have learnt and will help you in building a GenAI system.
LangGraph101: Let's build a deep research agent
Quantifying AI-Human Strategy: "We introduce a novel Bayesian Item Response Theory framework to quantify human–AI synergy, separating individual and collaborative ability while controlling for task difficulty in interactive settings. Unlike standard static benchmarks, our approach models human–AI performance as a joint process, capturing both user-specific factors and moment-to-moment fluctuations. We validate the frame-work by applying it to human–AI benchmark data (n=667) and find significant synergy. We demonstrate that collaboration ability is distinct from individual problem-solving ability. Users better able to infer and adapt to others’ perspectives achieve superior collaborative performance with AI--but not when working alone. Moreover, moment-to-moment fluctuations in perspective taking influence AI response quality, highlighting the role of dynamic user factors in collaboration. By introducing a principled framework to analyze data from human-AI collaboration, interactive benchmarks can better complement current single-task bench-marks and crowd-assessment methods. This work informs the design and training of language models that transcend static prompt benchmarks to achieve adaptive,socially aware collaboration with diverse and dynamic human partners."
The New Operational Stack: From IaC to Platforms to AI Agents
How to Build and Deploy a Multi-Agent AI System with Python and Docker
10 LLM Engineering Concepts Explained in 10 Minutes:
1. Understanding Context Engineering
2. Implementing Tool Calling
3. Adopting the Model Context Protocol
4. Enabling Agent-to-Agent Communication
5. Leveraging Semantic Caching
6. Utilizing Contextual Compression
7. Applying Reranking
8. Implementing Hybrid Retrieval
9. Designing Agent Memory Architectures
10. Managing Inference Gateways and Intelligent Routing
LLM Inference: Inside a Fast LLM Inference Server
Sebastian Raschka: author of "How to Build a Large Language Model (from Scratch)" and "How to Build a Reasoning Model (from Scratch)"
- Website
- GitHub
- LLMs-from-scratch
- reasoning-from-scratch
- mini-coding-agent
- RAGs: Simple implementations of Retrieval Augmented Generation (RAG) Systems
- LLM-workshop-2024
- LLM-finetuning-scripts

Definitions

Assistants

DeepTutor: AI-Powered Personalized Learning Assistant Source: Your AI Learning Companion - Transform any document into an interactive learning experience

Expert Systems / Rules Engines

Wikipedia

Fuzzy Logic

Java:

Neural Networks

You Don't Need Backpropagation To Train Neural Networks Anymore

Natural Language

Large Language Models (LLMs)

An advanced artificial intelligence (AI) system, built on deep learning and transformer architectures, that is pre-trained on massive amounts of text data to understand, process, and generate human-like language. LLMs learn to predict the next word in a sequence, enabling them to perform tasks like text generation, translation, summarization, and responding to complex queries, though they are not perfect oracles and can generate incorrect information or exhibit bias.

"On the Biology of a Large Language Model": "We investigate the internal mechanisms used by Claude 3.5 Haiku — Anthropic's lightweight production model — in a variety of contexts, using our circuit tracing methodology."

Recursive Language Models

Blog post: "We explore language models that recursively call themselves or other LLMs before providing a final answer. Our goal is to enable the processing of essentially unbounded input context length and output length and to mitigate degradation “context rot”. We propose Recursive Language Models, or RLMs, a general inference strategy where language models can decompose and recursively interact with their input context as a variable. We design a specific instantiation of this where GPT-5 or GPT-5-mini is queried in a Python REPL environment that stores the user’s prompt in a variable. We demonstrate that an RLM using GPT-5-mini outperforms GPT-5 on a split of the most difficult long-context benchmark we got our hands on (OOLONG [1]) by more than double the number of correct answers, and is cheaper per query on average! We also construct a new long-context Deep Research task from BrowseComp-Plus [2]. On it, we observe that RLMs outperform other methods like ReAct + test-time indexing and retrieval over the prompt. Surprisingly, we find that RLMs also do not degrade in performance when given 10M+ tokens at inference time."
rlm-minimal: Super basic implementation (gist-like) of RLMs with REPL environments.

Small Language Models (SLMs)

An AI model designed to handle specific tasks, using fewer parameters and less computational power than a large language model (LLM). This efficiency makes SLMs faster to train, more accessible, and suitable for deployment on devices with limited resources or for performing specialized functions, such as data extraction from documents, language translation, or specific conversational agents. In terms of size, SLM parameters range from a few million to a few billion, as opposed to LLMs with hundreds of billions or even trillions of parameters. Parameters are internal variables, such as weights and biases, that a model learns during training. These parameters influence how a machine learning model behaves and performs.

Retrieval Augmented Generation (RAG)

Coding Assistants

Create a Coding Assistant with StarCoder
"How to use GPT as a natural language to SQL query engine"
"Who owns the code?": "This shift raises an important question: who is accountable when something goes wrong – Copilot, the reviewer, or someone else?Rajesh Jethwa, CTO of software engineering consultancy Digiterre, describes this issue as a “minefield”, because there are a number of entities involved in creating the code. First, there are the providers of the models themselves, such as OpenAI or Anthropic. It is currently unclear whether these providers own the code generated by their models. Second, there are the authors of the code used to train the model. There are still questions around whether they have any claim to ownership of the resulting code, given the provenance of the training data. Third, there are employees and the organizations they work for. Typically, when an employee creates code as part of their job, the organization owns that code. However, it remains uncertain whether the organization or the individual employee should bear responsibility for the code that is produced with the help of a coding assistance."
In Which I Vibe-Code A Personal Library System

Generative AI

https://www.kdnuggets.com/generative-ai-a-self-study-roadmap
"Godot isn't making it": "What if what we're seeing today isn't a glimpse of the future, but the new terms of the present? What if artificial intelligence isn't actually capable of doing much more than what we're seeing today, and what if there's no clear timeline when it'll be able to do more? What if this entire hype cycle has been built, goosed by a compliant media ready and willing to take career-embellishers at their word? (March 2024) The reason I'm repeating myself is that it's important to note how obvious the problems with generative AI have been, and for how long."
Generative AI exists because of the transformer
"Stable Diffusion in Java (SD4J) Enables Generating Images with Deep Learning"
Stable Diffusion in C# (mentioned in the SD4J article)

Science

Making large language models reliable data science programming copilots for biomedical research: "Large language models (LLMs) can generate impressive data visualizations from simple requests, yet their accuracy remains underexplored. Here we present a benchmark of 293 coding tasks derived from 39 studies across 7 biomedical research areas, including biomarkers, integrative analysis, genomic profiling, molecular characterization, therapeutic response, translational research and pan-cancer analysis. Benchmarking eight proprietary and eight open-source LLMs under various prompting strategies reveals an overall accuracy below 40%. This low accuracy raises serious concerns about the risk of propagating incorrect scientific findings when blindly relying on AI-generated analyses. Therefore, we develop an AI agent that begins with and iteratively refines an analysis plan before generating code, achieving 74% accuracy. We embody this insight in a platform that enables users to codevelop analysis plans with LLMs and execute them within an integrated environment. In a user study with five medical researchers, the platform enabled users to complete over 80% of the analysis code for three studies."

Machine Learning

Semantics derived automatically from language corpora contain human-like biases: Artificial intelligence and machine learning are in a period of astounding growth. However, there are concerns that these technologies may be used, either with or without intention, to perpetuate the prejudice and unfairness that unfortunately characterizes many human institutions. Here we show for the first time that human-like semantic biases result from the application of standard machine learning to ordinary language---the same sort of language humans are exposed to every day. We replicate a spectrum of standard human biases as exposed by the Implicit Association Test and other well-known psychological studies. We replicate these using a widely used, purely statistical machine-learning model---namely, the GloVe word embedding---trained on a corpus of text from the Web. Our results indicate that language itself contains recoverable and accurate imprints of our historic biases, whether these are morally neutral as towards insects or flowers, problematic as towards race or gender, or even simply veridical, reflecting the {\em status quo} for the distribution of gender with respect to careers or first names. These regularities are captured by machine learning along with the rest of semantics. In addition to our empirical findings concerning language, we also contribute new methods for evaluating bias in text, the Word Embedding Association Test (WEAT) and the Word Embedding Factual Association Test (WEFAT). Our results have implications not only for AI and machine learning, but also for the fields of psychology, sociology, and human ethics, since they raise the possibility that mere exposure to everyday language can account for the biases we replicate here.
10 Github Repositories to Master Reinforcement Learning
Machine Learning for Software Engineering: A curated list of papers, theses, datasets, and tools related to the application of Machine Learning for Software Engineering.
Adversarial Machine Learning: A Taxonomy and Terminology of Attacks and Mitigations
A Brief Introduction to Machine Learning for Engineers - Osvaldo Simeone (PDF)
A Brief Introduction to Neural Networks
A Comprehensive Guide to Machine Learning - Soroush Nasiriany, Garrett Thomas, William Wang, Alex Yang (PDF)
A Course in Machine Learning (PDF)
A First Encounter with Machine Learning - Max Welling (PDF) (:card_file_box: archived)
A Selective Overview of Deep Learning - Fan, Ma, and Zhong (PDF)
Algorithms for Reinforcement Learning - Csaba Szepesvári (PDF)
An Introduction to Statistical Learning - Gareth James, Daniela Witten, Trevor Hastie and Robert Tibshirani (PDF)
Approaching Almost Any Machine Learning Problem - Abhishek Thakur (PDF)
Bayesian Reasoning and Machine Learning
Deep Learning - Ian Goodfellow, Yoshua Bengio and Aaron Courville
Deep Learning for Coders with Fastai and PyTorch - Jeremy Howard, Sylvain Gugger (Jupyter Notebooks)
Deep Learning with PyTorch - Eli Stevens, Luca Antiga, Thomas Viehmann (PDF)
Dive into Deep Learning
Explorations in Parallel Distributed Processing: A Handbook of Models, Programs, and Exercises - James L. McClelland
Foundations of Machine Learning, Second Edition - Mehryar Mohri, Afshin Rostamizadeh, Ameet Talwalkar
Free and Open Machine Learning - Maikel Mardjan (HTML)
Gaussian Processes for Machine Learning
IBM Machine Learning for Dummies - Judith Hurwitz, Daniel Kirsch
Information Theory, Inference, and Learning Algorithms
Interpretable Machine Learning - Christoph Molnar
Introduction to CNTK Succinctly - James McCaffrey
Introduction to Machine Learning - Amnon Shashua
Keras Succinctly - James McCaffrey
Learn Tensorflow - Jupyter Notebooks
Learning Deep Architectures for AI (PDF)
Machine Learning
Machine Learning for Data Streams - Albert Bifet, Ricard Gavaldà, Geoff Holmes, Bernhard Pfahringer
Machine Learning from Scratch - Danny Friedman (HTML, PDF, Jupyter Book)
Machine Learning, Neural and Statistical Classification
Machine Learning with Python - Tutorials Point (HTML, PDF)
Mathematics for Machine Learning - Garrett Thomas (PDF)
Mathematics for Machine Learning - Marc Peter Deisenroth, A Aldo Faisal, and Cheng Soon Ong
Neural Networks and Deep Learning
Practitioners guide to MLOps - Khalid Samala, Jarek Kazmierczak, Donna Schut (PDF)
Probabilistic Models in the Study of Language (Draft, with R code)
Python Machine Learning Projects - Lisa Tagliaferri, Brian Boucheron, Michelle Morales, Ellie Birkbeck, Alvin Wan (PDF, EPUB, Kindle)
Reinforcement Learning: An Introduction - Richard S. Sutton, Andrew G. Barto (PDF)
Speech and Language Processing (3rd Edition Draft) - Daniel Jurafsky, James H. Martin (PDF)
The Elements of Statistical Learning - Trevor Hastie, Robert Tibshirani, and Jerome Friedman
The LION Way: Machine Learning plus Intelligent Optimization - Roberto Battiti, Mauro Brunato (PDF)
The Mechanics of Machine Learning - Terence Parr and Jeremy Howard
The Python Game Book - Horst Jens (:card_file_box: archived)
Top 10 Machine Learning Algorithms Every Engineer Should Know - Binny Mathews and Omair Aasim
Understanding Machine Learning: From Theory to Algorithms - Shai Shalev-Shwartz, Shai Ben-David
You Don't Need Backpropagation To Train Neural Networks Anymore

Semantic Entity Resolution (Knowledge Graphs) (?)

The Rise of Semantic Entity Resolution

AI Agent Knowledge Base

Anatomy of an AI Agent Knowledge Base
Graphiti (Source): a Python framework for building temporally-aware knowledge graphs designed for AI agents. It enables real-time incremental updates to knowledge graphs without batch recomputation, making it suitable for dynamic environments where relationships and information evolve over time.
6 agentic knowledge patterns emerging in the wild

Detail Pages:

"Vibeing" Thoughts, links, and notes about "vibe" coding/engineering/whatevering.
A2UI An open-source project, complete with a format optimized for representing updateable agent-generated UIs and an initial set of renderers, that allows agents to generate or populate rich user interfaces.
Adala Autonomous Data (Labeling) Agent framework
AdenHQ Outcome driven agent development framework that evolves.
agent.cpp Building blocks for agents in C++.
Agent4Rec Recommender system simulator with 1,000 agents
Agent Client Protocol (ACP) Standardizes communication between code editors/IDEs and coding agents and is suitable for both local and remote scenarios.
Agent Definition Language (ADL) A vendor-neutral, open standard for defining AI agents.
Agent Definition Language (ADL) OpenAPI for agents: a single, declarative spec that says what an agent is, what tools it can call, what data it can touch, and how it is configured.
Agent Development Kit (ADK) An open-source, code-first toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
AgentForge LLM-agnostic platform for agent building & testing
AgentGPT Browser-based no-code version of AutoGPT
Agentic AI A collection of topics and notes on the subject.
Agentic Teams Links and notes on agent "teams" that collaborate to accomplish tasks.
AgentPilot Build, manage, and chat with agents in desktop app.
Agents Library/framework for building language agents.
AGENTS.md A simple, open format for guiding coding agents.
Agents (AI) Collection of notes and links on AI "agents".
Agent Skills A simple, open format for giving agents new capabilities and expertise.
Agent Skills Thoughts and notes on the topic.
Agent-to-Agent (A2A) protocol An open standard designed to enable seamless communication and collaboration between AI agents.
AgentVerse Platform for task-solving & simulation agents.
AIAC (Artificial Intelligence Infrastructure-as-Code generator) A library and command line tool to generate IaC (Infrastructure as Code) templates, configurations, utilities, queries and more via LLM providers such as OpenAI, Amazon Bedrock and Ollama.
AI Agent AGENTS.md file examples A collection of AGENTS.md exemplars
AI Agent ARCHITECTURE.md file examples A collection of ARCHITECTURE.md exemplars
AI Agent CONTRIBUTING.md file examples A collection of CONTRIBUTING.md exemplars
AI Agent DECISIONS.md file examples A collection of DECISIONS.md exemplars
AI Agent PROMPTS.md file examples A collection of PROMPTS.md exemplars
AI Agent README.md file examples A collection of README.md exemplars
AI Agent style file examples A collection of exemplars
AI Agent TASKS.md file examples A collection of TASKS.md exemplars
AI Coding Agent Specification files Notes, links, and thoughts on the various AI coding agent MD files.
Aider Use command line to edit code in your local repo.
AI Legion Multi-agent TS platform, similar to AutoGPT.
AIlice Create agents-calling tree to execute your tasks.
AI Models An overview of AI models.
AIScript A language designed specifically for web development in the AI era, with AI capabilities as first-class language features, and an intuitive route DSL and directive design.
Alibaba Qwen AI model.
AllenAI / AI2 A Seattle based non-profit AI research institute founded in 2014 by the late Paul Allen.
Amazon Q Amazon's coding agent.
Amp The frontier coding agent that lets you wield the full power of leading models.
Android and AI/LLMs
Antigravity (IDE) Next-generation IDE.
AnythingLLM Everything great about AI in one desktop application. Chat with docs, use AI Agents, and more - full locally and offline.
Arcee Own your own small language models.
Auggie Augment Code CLI tool.
AutoGen Multi-agent framework with diversity of agents.
AutoGPT Experimental attempt to make GPT4 fully autonomous.
Automata Generate code based on your project context.
Autonomous HR Chatbot Agent that answers HR-related queries using tools.
AutoPR AI-generated pull requests agent that fixes issues.
Barfi A Flow-Based Programming framework that offers a graphical programming interface.
BentoML The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more! (Unified Model Serving Framework)
BoundaryML (BAML) A domain-specific language to generate structured outputs from LLMs — with the best developer experience.
Chappie A CLI that turns a repository into an automated build machine.
Claude Code The AI agent.
Claude Code CLAUDE.md file examples Example CLAUDE.md scripts and links
Cline Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.
Codebase Navigator An AI-powered tool for exploring and understanding GitHub repositories.
CodeBuddy Code where you build.
Codex OpenAI coding agent (ChatGPT).
Codex-Container Codex in a local Docker container with cron, file watchers, webhooks, search/indexing, speech, and hundreds of tools on tap.
ComfyUI A node-based Gradio GUI designed for generative AI models to generate AI images, video, and audio locally on your own hardware.
Context7 Get the latest documentation and code into Cursor, Claude, or other LLMs.
Continue.dev Open-source (?) CLI and IDE agent for coding models.
Copilot An AI agent from GitHub/Microsoft.
Courses in AI A collection of links to academic courses and/or tutorials on AI.
Critiques of "AI" A collection of links and notes talking about or criticizing/critiquing "AI" (mostly LLM-based).
Deepseek AI model and company.
Dify https://dify.ai/
Docker MCP Hub Access the largest library of containerized MCP servers.
dotLLM High-performance LLM inference engine written natively in C#/.NET. Not a wrapper — a ground-up implementation.
DSPydantic Automatically optimizes your Pydantic model prompts and field descriptions using DSPy.
Faiss A library for efficient similarity search and clustering of dense vectors. It contains algorithms that search in sets of vectors of any size, up to ones that possibly do not fit in RAM. It also contains supporting code for evaluation and parameter tuning.
Firecrawl The API to search, scrape, and interact with the web at scale.
First Principles Framework A rigorous, transdisciplinary architecture for thinking, written in human- and machine-readable pseudo-code (the informal "language of technical standards" with multiple "May", "Should", "Must"). It provides a generative pattern language to model complex systems, manage knowledge evolution, and ensure auditable assurance across engineering, research, and management domains.
FLUX AI model.
Fuzzy logic Readings and links on fuzzy logic.
gelab-zero GUI Exploration Lab. One of the best GUI agent solutions in the galaxy, built by the StepFun-GELab team and powered by Step’s research capabilities.
Gemini Google's AI agent.
Gentleman Guardian Angel Provider-agnostic code review using AI. Use Claude, Gemini, Codex, Ollama to enforce your coding standards.
Get-Shit-Done A light-weight and powerful meta-prompting, context engineering and spec-driven development system for any coding agent.
GitBook Agent An AI teammate that works alongside you, helping you keep your documentation accurate, complete, and current.
GitHub Copilot GitHub's coding agent.
GitNexus A client-side knowledge graph creator that runs entirely in your browser -- drop in a GitHub repo or ZIP file, and get an interactive knowledge graph wit a built in Graph RAG Agent.
Goblin.tools A collection of small, simple, single-task tools, mostly designed to help neurodivergent people with tasks they find overwhelming or difficult.
Google AI Studio Google's Gemini-powered answer engine website.
Google Gemma 3 AI model.
Google Jules
Goose Your local AI agent, automating engineering tasks seamlessly.
GPT4All Run Local LLMs on Any Device.
gptlang A new programming language implemented by GPT-4.
HTML Tools HTML applications built which combine HTML, JavaScript, and CSS in a single file and use them to provide useful functionality.
HuggingFace The platform where the machine learning community collaborates on models, datasets, and applications.
HuggingFace Smol AI model.
Husky Research language aimed at next generation AI and software.
HyperbookLM A powerful research assistant built with Next.js 15, React 19, and Hyperbrowser that allows users to aggregate diverse sources (Web URLs, PDFs) and gain deep insights through interactive AI tools.
Inclusion AI Ling AI model.
IronClaw OpenClaw inspired implementation in Rust focused on privacy and security.
Jlama A modern Java inference engine for LLMs.
Joplin An open source note-taking app to capture your thoughts and securely access them from any device.
json-render Let end users generate dashboards, widgets, apps, and data visualizations from prompts — safely constrained to components you define.
Kiro Bringing structure to AI coding with spec-driven development.
KittenTTS Small AI Text-to-Speech LLM Runs on CPUs Without a GPU
koboldcpp Run GGUF models easily with a KoboldAI UI.
Kokoro (model) Local processing model.
LangChain, LangGraph The open, composable framework that provides a standard interface for every model, tool, and database – so you can build LLM apps that adapt as fast as the ecosystem evolves.. (More description needed!)
LangStream Combines data streaming with generative AI.
Language Model Training (How-Tos) Training and fine-tuning language models.
Large Language Model (LLM) Collection of links, notes, and models.
lfm-thinking LFM2.5 is a new family of hybrid models designed for on-device deployment.
LiteRT High-performance ML & GenAI deployment on edge platforms.
litgpt 20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
LittleHorse A high-performance microservice orchestration engine that allows developers to build scalable, maintainable, and observable applications.
llama.cpp Widely used inference engine for running local models.
Llama-3 Practical Llama 3 inference in Java.
llama3pure Three inference engines for Llama 3: pure C for desktop systems, pure JavaScript for Node.js, and pure JavaScript for Web environments.
LlamaIndex or LlamaParse The enterprise agentic OCR and document agent platform.
LLM Prompts Collection of interesting/useful prompts for LLMs.
llms.txt (Website convention) A proposal to standardise on using an /llms.txt file to provide information to help LLMs use a website at inference time.
LMQL A programming language for LLMs; Robust and modular LLM prompting using types, templates, constraints and an optimizing runtime.
LMStudio Local AI, on Your Computer.
LM Studio Locally-installed host for LLMs.
LobeHub The ultimate space for work and life: to find, build, and collaborate with agent teammates that grow with you.
LocalAGI a powerful, self-hostable AI Agent platform designed for maximum privacy and flexibility as a complete drop-in replacement for OpenAI's Responses APIs with advanced agentic capabilities.
Local AI Locally-installed host for LLMs.
LocalRecall 100% Local Memory layer and Knowledge base for agents with WebUI.
local-seo Local AI agent that audits URLs for SEO issues using Browser Use + Claude API + Playwright
Loglan A language which was originally devised to test the Sapir-Whorf hypothesis that the structure of language determines the boundaries of human thought.
Lukan (Agent, IDE, and workstation) An AI layer on top of your OS; sandboxed, permission-aware, fully local, and tmux-based so you don't lose sessions.
Machine Learning Links and notes on the topic.
Manifest An Open Source, portable backend that fits into 1 YAML file. Easy for both humans and LLMs to generate and validate.
mdflow Multi-backend CLI for executable markdown prompts.
MemPalace The best-benchmarked open-source AI memory system.
Meta Llama AI model.
Microsoft Phi AI model.
MinerU A document parsing tool that converts PDF, image, and DOCX inputs into machine-readable formats such as Markdown and JSON for downstream retrieval, extraction, and processing.
MiniCPM-V Offers advanced optical character recognition and multimodal understanding capabilities.
MiniMax AI model.
Mini-SGLang A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.
Mistral Ministral AI model.
Mistral Pixtral AI model.
mistral-vibe Minimal CLI coding agent.
MNN Chat An open-source Android app that lets you run large language models fully offline on your phone with a focus on speed efficiency and real on-device inference.
Model Control Protocol (MCP) An open standard that enables developers to build secure, two-way connections between their data sources and AI-powered tools.
Molmo AI model.
MoonshotAI Kimi Proprietary AI model.
Msty The "all-in-one" AI studio.
n8n Fair-code workflow automation platform with native AI capabilities.
NanoBot An ultra-lightweight personal AI assistant inspired by OpenClaw.
NanoClaw The secure personal AI agent that runs securely in containers, built to be understood and customized for your own needs.
Natural Language A collection of links around natural language parsing/processing/programming.
Nitrogen A vision-action foundation model for generalist gaming agents that is trained on 40,000 hours of gameplay videos across more than 1,000 games.
Nomic GPT4All Your private and local AI chatbot.
NotebookLM A collection of notebooks for LLMs.
OCRFlux A multimodal large language model fine-tuned from Qwen2.5-VL-3B-Instruct for converting PDFs and images into clean, readable Markdown text.
OfficeCLI The first and best command-line tool purpose-built for AI agents to read, edit, and automate Word, Excel, and PowerPoint files.
Ollama Locally-installed host for LLMs.
olmOCR A vision-language model optimized for optical character recognition on documents.
Onyx Open Source AI Platform - AI Chat with advanced features that works with every LLM.
Oobabooga The original local LLM interface. Text, vision, tool-calling, training, and more. 100% offline.
OpenAI gpt-oss AI model.
OpenClaw / MoltBot / ClawdBot Clears your inbox, sends emails, manages your calendar, checks you in for flights.
Opencode An open source agent that helps you write code in your terminal, IDE, or desktop.
opendataloader-pdf Extract Markdown, JSON (with bounding boxes), and HTML from any PDF.
OpenLLM Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.
OpenNotebook An open-source collection of notebooks for LLMs.
OpenWebUI An extensible, feature-rich, user-friendly, self-hosted AI platform designed to operate entirely offline, supporting various LLM runners like Ollama and OpenAI-compatible APIs, with built-in inference engine for RAG.
OpenWork An open-source alternative to Claude Cowork built for teams, powered by opencode
Opus Anthropic's premium model.
Outerbase An AI-powered database platform.
PaddleOCR VL An ultra-compact vision-language model specifically designed for efficient multilingual document parsing.
Paperless-ngx A community-supported open-source document management system that transforms your physical documents into a searchable online archive so you can keep, well, less paper.
Paradigms of Artificial Intelligence Programming Norvig's classic, on the Web.
PeonPing Game character voice lines the instant your AI agent finishes or needs permission.
PicoClaw Tiny, Fast, and Deployable anywhere — automate the mundane, unleash your creativity
PocketFlow A 100-line minimalist LLM framework.
Priml A new programming language aimed at facilitating systems and AI infrastructure development.
Prompt Orchestration Markup Language (POML) An open-source framework designed to bring order, modularity, and extensibility to prompt engineering for LLMs.
Psyche A local‑first, file‑based, git‑versioned cognitive scaffold for the natural flow of curiosity‑driven, multi‑threaded thinking. Built so nothing valuable gets lost, and ideas become real artifacts with minimal toil.
Quint Code Structured reasoning framework for Claude Code, Gemini, Cursor, and Codex — hypothesis-driven decision making with auditable evidence trails
Qwen-Code An open-source AI agent that lives in your terminal.
Ray.io An AI compute engine that consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
Raycast A collection of powerful productivity tools all within an extendable launcher.
RepoAssist A generic, all-purpose automated repository assistant for software maintainers.
Retrival Augmented Generation (RAG) Concepts, notes, links, reading
Rockbot A "principle of least privilege" team of agents.
RockBot Autonomous personal agent designed to be cloud-native.
SearXng A free internet metasearch engine which aggregates results from up to 247 search services.
Sever A Programming Language by AI, for AI.
SGLang A fast serving framework for large language models and multi-modality models.
SHAI A Shell AI assistant, to help you interact with your machine through a command line interface.
SimStudio Build, deploy, and orchestrate AI agents. Sim is the central intelligence layer for your AI workforce.
Small Language Models (SLM) Collection of links and notes.
SmartMock An AI-powered API mock server built with Spring Boot, Ollama, and LangChain4j that, instead of serving hardcoded responses, uses an LLM to generate realistic, context-aware mock data directly from your OpenAPI specifications.
Spec Kit An effort to allow organizations to focus on product scenarios rather than writing undifferentiated code with the help of Spec-Driven Development.
Spec-Kit An open source toolkit that allows you to focus on product scenarios and predictable outcomes instead of vibe coding every piece from scratch.
SpecLang An attempt at lifting the developer experience to a higher level of abstraction, closer to how we conceptually think about our programs: where programming is much more similar to how you'd instruct a human being.
Spec-Oriented Programming Using natural language and language models to build software.
Stable Diffusion AI model capable of generating photorealistic images from both text and image prompts.
Strands Agents A simple-to-use, code-first framework for building agents.
Structured and Unstructured Query Language (SUQL) Conversational Search over Structured and Unstructured Data with LLMs
Suno Generate music from prompts.
Superagent Your AI-powered business research assistant.
SurfSense Connect any LLM to your internal knowledge sources and chat with it in real time alongside your team.
TabbyML Opensource, self-hosted AI coding assistant.
Tencent Hunyuan
Tensors Concepts about tensors, which build LLM neural networks.
The Edge of Sentience Notes on (and links to) the book.
tldw (Too Long; Didn't Watch) An open-source, API-first platform for ingesting media, transcribing, analyzing, and retrieving knowledge from video, audio, documents, websites, and more.
Toad A unified interface for AI in your terminal.
TrustClaw A 24/7 AI assistant with 1000+ tools via OAuth and sandboxed execution.
Unsloth Train your own model with Unsloth, an open-source framework for LLM fine-tuning and reinforcement learning.
VectorSearchJS A library to perform semantic vector search, over millions of vectors in milliseconds, and can even visualize the tokens or embeddings too; runs entirely client side in the web browser (custom Vector DB layer written on top of IndexDB) and currently supports Google's EmbeddingGemma (highest quality but 300Mb), or all-Mini-L6-v2 (fastest and only 30mb) embedding models via Web AI libraries with WebGPU acceleration for speed.
vLLM Easy, fast, and cheap LLM serving for everyone
WebMCP A Web-based version of the MCP protocol.
Xiaomi MiMo AI model and company.
Z.ai GLM AI model.
Zep A context engineering platform that systematically assembles personalized context—user preferences, traits, and business data—for reliable agent applications.
Z-Image AI model.
Zvec A lightweight, lightning-fast, in-process vector database.

Last modified 15 April 2026