Artificial Intelligence
76 items from owainlewis/awesome-artificial-intelligence ★16,654
-
OpenAI Agents SDK openai.github.io
A small SDK for tools, handoffs, guardrails, tracing, and agent orchestration.
-
Codex Orchestration with Symphony openai.com
A reference architecture that turns project work into isolated, observable coding-agent runs.
-
Harness Engineering openai.com
OpenAI's field report on building software with coding agents, repository constraints, automated checks, and human steering.
-
Model Context Protocol modelcontextprotocol.io
The open specification for connecting AI applications to external tools, data sources, prompts, and interactive apps.
-
Made With ML madewithml.com
An open course on designing, developing, deploying, and iterating on production ML systems.
-
Hands-On Large Language Models llm-book.com
A visual and practical guide by Jay Alammar and Maarten Grootendorst.
-
Microsoft Agent Framework learn.microsoft.com
Microsoft's successor to AutoGen and Semantic Kernel for agents and graph-based workflows.
-
DeepLearning.AI Short Courses learn.deeplearning.ai
Focused courses on current generative AI engineering techniques.
-
Langfuse langfuse.com
Tracing, evaluation, prompt management, and metrics for LLM applications.
-
MIT 6.S191: Introduction to Deep Learning introtodeeplearning.com
Deep learning foundations and applications.
-
Hugging Face LLM Course huggingface.co
Transformers, fine-tuning, datasets, and modern NLP tooling.
-
Google Agent Development Kit google.github.io
Google's framework for developing and evaluating agents.
-
Blueprint github.com
An open-source set of focused agent skills for designing, implementing, testing, reviewing, and shipping software changes.
-
OWASP Top 10 for LLM Applications genai.owasp.org
Risks and mitigations for developing and deploying generative AI applications.
-
Full Stack Deep Learning fullstackdeeplearning.com
The full lifecycle of building and shipping AI products.
-
vLLM docs.vllm.ai
An inference and serving engine for language models.
-
Ragas docs.ragas.io
Evaluation and experimentation for retrieval and generative AI applications.
-
LlamaIndex docs.llamaindex.ai
Data ingestion, indexing, retrieval, and agent workflows.
-
LiteLLM docs.litellm.ai
A model gateway and unified interface for multiple model providers.
-
LangGraph docs.langchain.com
Low-level orchestration for long-running, stateful agents.
-
Haystack docs.haystack.deepset.ai
Modular pipelines for retrieval and generative AI applications.
-
GitHub Copilot coding agent docs.github.com
An asynchronous agent that works from GitHub issues and opens pull requests.
-
Anthropic Prompt Engineering docs.anthropic.com
Techniques for defining success criteria, testing prompts, and improving model behaviour.
-
OpenHands docs.all-hands.dev
An open-source platform for running software development agents locally or in the cloud.
-
Cursor CLI cursor.com
A terminal agent connected to Cursor's editor and cloud workflows.
-
Stanford CS336: Language Modeling from Scratch cs336.stanford.edu
Build language models from data preparation through evaluation and deployment.
-
OpenAI Cookbook cookbook.openai.com
Code examples for structured outputs, tool use, retrieval, evals, and other LLM application patterns.
-
Google Generative AI Learning Path cloudskillsboost.google
An introductory path through generative AI concepts and Google Cloud tooling.
-
A Practical Guide to Building Agents cdn.openai.com
OpenAI's guide to models, tools, instructions, orchestration, and guardrails.
-
Direct Preference Optimization arxiv.org
Reframed preference alignment as a simple classification objective without explicit reward modelling.
-
Constitutional AI arxiv.org
A method for training helpful and harmless AI assistants using written principles.
-
ReAct arxiv.org
Combined reasoning traces with actions for tool-using language-model agents.
-
Training Compute-Optimal Large Language Models arxiv.org
Showed how model size and training data should scale together under a compute budget.
-
Training Language Models to Follow Instructions with Human Feedback arxiv.org
Established the instruction tuning and RLHF recipe used by InstructGPT.
-
LoRA arxiv.org
Introduced low-rank adaptation for parameter-efficient model fine-tuning.
-
Language Models are Few-Shot Learners arxiv.org
Demonstrated in-context learning at scale.
-
Retrieval-Augmented Generation arxiv.org
Combined parametric language models with external retrieval for knowledge-intensive tasks.
-
Scaling Laws for Neural Language Models arxiv.org
Explored relationships between model performance, data, and compute.
-
How We Built Our Multi-Agent Research System anthropic.com
Production lessons on orchestrator-worker agents, parallel search, evaluation, and operational reliability.
-
Effective Harnesses for Long-Running Agents anthropic.com
Patterns for agents that make progress across multiple context windows and recover from failure.
-
Demystifying Evals for AI Agents anthropic.com
A practical method for building task suites, graders, transcripts, and evaluation harnesses.
-
Artificial Intelligence: A Modern Approach aima.cs.berkeley.edu
The broad reference for classical AI, including search, reasoning, planning, learning, and robotics.
-
AI Engineer aiengineer.co
A paid program for agentic coding and building, testing, and shipping production AI systems.
-
Pydantic AI ai.pydantic.dev
Typed agent development built around Pydantic.
-
Gemini and Temporal Durable Agent ai.google.dev
A concrete implementation of durable execution, retries, and human approval for an agent workflow.
-
Agent2Agent Protocol a2a-protocol.org
A vendor-neutral specification for agent discovery, task delegation, streaming, asynchronous updates, and cross-platform communication.
