Search the index

Search titles, creators and short descriptions. Filters combine. Nothing you type is sent or saved.

125 resources

• AGENTS.md · AGENTS.md (multi-vendor open format)

  Open format for a repo instruction file that coding agents read.

• Interactive prompt engineering tutorial · Anthropic

  Hands-on notebook course: you edit prompts and see results, no coding needed.

• Prompt engineering overview (Claude docs) · Anthropic

  Official starting point for prompting Claude; points to the best-practices reference and the interactive tutorials.

• Prompt Engineering Guide · DAIR.AI

  Broad, frequently updated reference of named prompting techniques.

• Prompt design strategies (Gemini API) · Google

  Google's official prompting guide with clear before/after examples.

• The Illustrated Transformer · Jay Alammar

  See how attention and encoder-decoder blocks fit together.

• Learn Prompting · Learn Prompting

  A provider hub with free learning paths and separate commercial courses.

• A practical guide to building agents (PDF) · OpenAI

  Plain-language foundations: when to build an agent, orchestration, guardrails.

• Prompt engineering (OpenAI API docs) · OpenAI

  OpenAI's official baseline on message roles, instructions and examples.

• Andrej Karpathy on X · Andrej Karpathy

  AI explanations and practical model-use observations from a neural-network educator.

• GigaChat Python SDK · GigaChain / AI Forever

  An SDK reference for calling the GigaChat service from Python.

• Neural Networks: Zero to Hero · Andrej Karpathy

  Learn neural networks by implementing them in Python.

• Equipping agents for the real world with Agent Skills · Anthropic

  Packaging instructions and scripts as loadable skills.

• Anthropic Engineering blog · Anthropic

  Find first-party accounts of engineering decisions behind Claude systems.

• Building Effective AI Agents · Anthropic

  Workflows vs agents and the core patterns; argues to start simple. Readable without code.

• Best practices for Claude Code · Anthropic

  Concrete coding-agent workflow habits: plan, verify, manage context.

• Claude Cookbooks · Anthropic

  Code recipes for integrating Claude capabilities into applications.

• Prompting best practices (Claude docs) · Anthropic

  Current-model guidance in one page: XML structure, examples, thinking, agentic use. (Old use-xml-tags, multishot and extended-thinking-tips URLs redirect here.)

• Effective context engineering for AI agents · Anthropic

  Treats context as a finite budget: compaction, notes, sub-agents.

• Responsible Scaling Policy · Anthropic

  Read a lab’s published risk-governance commitments and revision history.

• Artificial Analysis · Artificial Analysis

  Compare model and provider characteristics in one public analysis hub.

• DeepSeek API Docs · DeepSeek

  Start a DeepSeek API integration from the provider's own documentation.

• DeepSeek on GitHub (model repos, tech reports, open-infra-index) · DeepSeek

  A first-party directory of DeepSeek repositories.

• Epoch AI - Data on the trajectory of AI · Epoch AI

  Explore longitudinal datasets about models, compute and infrastructure.

• Prompting Fundamentals and How to Apply them Effectively · Eugene Yan

  Practitioner write-up applying core techniques to real tasks.

• Google DeepMind Research · Google DeepMind

  Locate DeepMind research and the projects behind it.

• Gemini API cookbook · Google

  Explore Gemini features through official notebooks and examples.

• Structured outputs (Gemini API) · Google

  Gemini's equivalent: constrain responses to a JSON schema.

• AI Evals FAQ · Hamel Husain and Shreya Shankar

  Practical answers about error analysis, annotation and reliable evaluators.

• Your AI Product Needs Evals · Hamel Husain

  Build a feedback loop from real failures, not general benchmark scores.

• AI Agents Course · Hugging Face

  Free course from 'what is an agent' to building one.

• Hugging Face Daily Papers · Hugging Face

  A community-curated route into newly discussed AI papers.

• Hugging Face LLM Course · Hugging Face

  A structured route through the Hugging Face ecosystem.

• Agents · Chip Huyen

  Long-form essay on tools, planning, failure modes and evaluating agents.

• Critiquing Anthropic’s Variant of Pacing the Frontier (ChinAI) · Jeffrey Ding

  A free ChinAI essay examining arguments about international AI competition.

• Letta documentation · Letta

  Explore documentation for agents that keep state across interactions.

• Model Context Protocol docs · MCP project

  The spec and docs for connecting tools and data to agents.

• Llama Cookbook · Meta

  First-party examples for building applications around Llama.

• Prompt engineering how-to (Llama docs) · Meta

  Official guide for prompting open-weight Llama models.

• Mistral AI docs · Mistral AI

  Find Mistral's API and model-integration documentation.

• Mistral cookbook · Mistral AI

  Notebook examples from Mistral and its contributors.

• Kimi API Platform docs · Moonshot AI

  Follow the official quickstart for the hosted Kimi API.

• State of AI Report 2026 · Nathan Benaich / Air Street Capital

  A yearly synthesis of AI research, industry and policy developments.

• The current balance of power in open models (Interconnects) · Nathan Lambert

  A free Interconnects essay distinguishing open-weight and closed-model ecosystems.

• NIST AI Risk Management Framework · NIST

  A government reference for organizing AI risk-management work.

• OpenAI Agents SDK · OpenAI

  Lightweight framework: handoffs, guardrails, tracing.

• GPT-5 prompting guide · OpenAI

  Model-specific advice on agentic eagerness, tool preambles and instruction conflicts.

• OpenAI Cookbook · OpenAI

  Browse worked examples for OpenAI APIs and applications.

• Reasoning best practices · OpenAI

  When to pick a reasoning model and how prompting them differs from chat models.

• Structured model outputs · OpenAI

  How to get schema-valid JSON instead of hoping the model formats it right.

• OWASP Top 10 for LLM Applications 2025 · OWASP Gen AI Security Project

  Use a shared vocabulary for discussing risks in LLM applications.

• Qwen blog · Qwen team, Alibaba

  Follow Qwen's own release notes and technical introductions.

• Qwen documentation · Qwen team, Alibaba

  Navigate Qwen deployment, inference and adaptation guidance.

• Qwen3 repo · Qwen team, Alibaba

  Find Qwen3 checkpoints and model-specific usage guidance.

• Context Engineering for Agents · Lance Martin

  Write/select/compress/isolate taxonomy of context strategies.

• GigaChat API documentation · Sber

  A Russian-language first-party guide to integrating GigaChat.

• LLMs-from-scratch (book code) · Sebastian Raschka

  Follow a GPT implementation rather than treating the model as a black box.

• Simon Willison on prompt injection · Simon Willison

  Follow an ongoing public record of prompt-injection research.

• Simon Willison's Weblog · Simon Willison

  Follow hands-on notes and commentary on model releases and tools.

• A local build is not a release · skill issue

  Our original build account separates generated-page checks from browser testing and release authorization.

• AI Index (Stanford HAI) · Stanford HAI

  Compare AI developments through a broad annual statistical report.

• SWE-bench Leaderboards · SWE-bench team (Princeton/Stanford)

  Understand coding-agent scores in terms of resolved repository tasks.

• The lethal trifecta for AI agents · Simon Willison

  A defensive framework for recognizing risky combinations of agent capabilities and untrusted inputs.

• Chip Huyen on X · Chip Huyen

  AI system-design notes that connect model behavior, tools and production choices.

• Eugene Yan on X · Eugene Yan

  Applied AI systems and evaluation lessons from a practitioner’s public technical writing.

• Simon Willison on X · Simon Willison

  Practical LLM experiments and software-building notes, with links back to detailed write-ups.

• grok-prompts (published system prompts) · xAI

  Inspect system prompts published by their original provider.

• xAI / Grok API docs · xAI

  The official entry point for Grok API capabilities and integration guides.

• Applied LLMs: What We've Learned From A Year of Building with LLMs · Yan, Bischof, Frye, Husain, Liu, Shankar

  Cross-functional lessons from building language-model applications.

• Yandex AI Studio SDK · Yandex Cloud

  Use the official Python client to understand YandexGPT integrations.

• Z.ai developer docs · Zhipu / Z.ai

  An official starting point for accessing Z.ai's GLM service.

• Agentic misalignment · Anthropic

  A controlled study of risky behavior under conflicting agent incentives.

• Effective harnesses for long-running agents · Anthropic

  Harness design for agents that work across many context windows.

• How we built our multi-agent research system · Anthropic

  Real production lessons on orchestrator/sub-agent design and its costs.

• Writing effective tools for AI agents · Anthropic

  How to design, evaluate and improve the tools an agent calls.

• Browser Use · Browser Use contributors

  Inspect a Python library for model-driven browser interaction.

• Context Rot: How Increasing Input Tokens Impacts LLM Performance · Chroma

  Measures how output quality drops as input length grows.

• Don't Build Multi-Agents · Cognition

  The counter-argument: context sharing beats splitting work across agents.

• lm-evaluation-harness · EleutherAI

  Run model benchmarks through reusable task and backend interfaces.

• Evaluating the Effectiveness of LLM-Evaluators (LLM-as-Judge) · Eugene Yan

  Compare model-based graders against the judgments they must approximate.

• Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection · Kai Greshake et al.

  Foundational public research on indirect prompt injection. Linked only; no payloads reproduced.

• LlamaFactory · hiyouga (Yaowei Zheng) et al.

  Compare adaptation methods within a shared training interface.

• TRL - Transformers Reinforcement Learning · Hugging Face

  Find training interfaces for supervised and preference-based adaptation.

• 12-Factor Agents · HumanLayer (Dex Horthy)

  Principles for agents that hold up in production.

• Embrace The Red · Johann Rehberger

  Public case reports about security failures in deployed AI products.

• EXAONE 4.0 · LG AI Research

  Official model guidance with reasoning and deployment examples.

• Lil'Log · Lilian Weng

  Research learning notes that connect methods to their literature.

• LLM Powered Autonomous Agents · Lilian Weng

  Classic overview of planning, memory and tool use in agents.

• Prompt Engineering · Lilian Weng

  Dense, research-backed survey of prompting methods with citations.

• Context Engineering for AI Agents: Lessons from Building Manus · Manus

  KV-cache-aware design, file system as memory, keep errors in context.

• MCP reference servers · MCP project

  Reference implementations to learn MCP server design from.

• A Survey of Context Engineering for LLMs (arXiv 2507.13334) · Mei et al. (Chinese Academy of Sciences et al.)

  A research map of retrieval, context processing and memory systems.

• METR · METR

  Follow research on the capabilities and risks of increasingly autonomous systems.

• MiniMax-M2 repo · MiniMax

  Examine MiniMax-M2's model release and agent-oriented evaluation report.

• MITRE ATLAS · MITRE

  Connect AI threats with documented techniques, mitigations and cases.

• Kimi K2 repo · Moonshot AI

  Read the Kimi K2 model overview and deployment material.

• Reinforcement Learning from Human Feedback (book) · Nathan Lambert

  A conceptual path through reward modeling and post-training methods.

• RAG Techniques · Nir Diamant and contributors

  Compare retrieval designs through code-oriented examples.

• garak - LLM vulnerability scanner · NVIDIA

  A public scanner project for understanding classes of model failures.

• simple-evals · OpenAI

  Read reference evaluation code with an explicit maintenance caveat.

• OpenHands Agent Canvas · OpenHands (All Hands AI)

  Inspect the OpenHands control center and its supported execution backends.

• OpenHands Software Agent SDK · OpenHands

  Open-source agent SDK behind OpenHands, worth reading as a reference harness.

• promptfoo · promptfoo

  Inspect a project combining application evaluation and security testing.

• Qwen-Agent · Qwen team, Alibaba

  A Qwen-focused framework for tool-using applications.

• The Prompt Report: A Systematic Survey of Prompt Engineering Techniques · Sander Schulhoff et al.

  A broad research taxonomy for comparing prompting techniques and finding their sources.

• Controlling Reasoning Effort in LLMs (Ahead of AI) · Sebastian Raschka

  A free Ahead of AI article on training controllable reasoning effort.

• DSPy · Stanford NLP

  Build modular model programs and improve them against a metric.

• Inspect · UK AI Security Institute and Meridian Labs

  Compose evaluation datasets, agents, tools and scorers.

• Unsloth · Unsloth

  Study local training and adaptation workflows for supported models.

• Self-Consistency Improves Chain of Thought Reasoning in Language Models · Xuezhi Wang et al.

  Sample several reasoning paths and take the majority answer.

• Chain-of-Thought Prompting Elicits Reasoning in Large Language Models · Jason Wei et al.

  Early research on using worked reasoning examples to improve performance on reasoning tasks.

• Design Patterns for Securing LLM Agents against Prompt Injections · Simon Willison

  Summary of a paper's defensive agent architectures.

• Lilian Weng on X · Lilian Weng

  Research-oriented learning notes on model training, reasoning and agent harnesses.

• SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering · John Yang et al.

  Research on how the agent-computer interface influences software-engineering performance.

• ReAct: Synergizing Reasoning and Acting in Language Models · Shunyu Yao et al.

  Research on combining reasoning with environment actions, a useful reference for agent-loop design.

• Tree of Thoughts: Deliberate Problem Solving with Large Language Models · Shunyu Yao et al.

  Search over branching reasoning steps; basis for many planning approaches.

• GLM-4.5 repo · Zhipu / Z.ai

  Inspect GLM release information and usage examples in the official repository.

• nanochat · Andrej Karpathy

  A compact training harness spanning the model-development lifecycle.

• DeepSeek open-infra-index · DeepSeek

  A directory of DeepSeek's published infrastructure components.

• DeepSeek-R1: Incentivizing Reasoning via RL (arXiv 2501.12948) · DeepSeek

  Study the reported reinforcement-learning recipe behind DeepSeek-R1.

• The Smol Training Playbook · Hugging Face (SmolLM team)

  A training account that includes failed experiments and engineering decisions.

• The Ultra-Scale Playbook · Hugging Face (nanotron)

  Understand how parallelism changes memory use and training throughput.

• The FineWeb Datasets · Guilherme Penedo and coauthors, Hugging Face

  Study how filtering and deduplication affect pretraining data.

• The AI Scientist · Sakana AI and collaborators

  Inspect a research pipeline for automated experiments and scientific writeups.

• verl (HybridFlow) · verl project (originated at ByteDance Seed)

  Explore how an RL training framework coordinates generation and optimization.

Plain-text Markdown copy