AI agents resources for developers

A free Microsoft curriculum on the Model Context Protocol, the standard way for AI apps and agents to connect to tools and data without a custom integration for each. It walks through core concepts, security and authorisation, building servers and clients, testing and deployment, with samples in Python, TypeScript, JavaScript, Java, C# and Rust. It suits developers who have wired an LLM to an internal system by hand and want a reusable approach.

• AI
• AI agents
• Programming

A free Microsoft course on GitHub with 18 lessons on building AI agents, each with a written lesson, video and runnable Python code. It covers agent design patterns (tool use, planning, multi-agent, metacognition), agentic RAG, trustworthy agents, context engineering, memory, MCP and A2A protocols, production deployment and security. It suits developers who have used an LLM API but never built something that takes multiple steps on its own.

• AI
• AI agents
• Programming

A free course from Hugging Face that teaches what an AI agent is, then how to build one with tools, memory and a reasoning loop, using three frameworks: smolagents, LangGraph and LlamaIndex. It ends with a graded final assignment and a free certificate. It suits Python developers who have called an LLM API but have never built something that plans and takes several steps on its own.

• AI
• Machine learning
• AI agents

Vendor-neutral best practices for building LLM apps and agents, checked against the OWASP Top 10 for LLM Applications 2026, the OWASP Agentic Top 10, NIST's Generative AI Profile and official provider docs. It covers prompt design, evals, prompt injection, agent permissions, cost, observability, failure handling and data privacy.

• AI
• AI agents

Tool-neutral best practices for working with AI coding assistants such as Claude Code, GitHub Copilot and Cursor, checked against their official docs, the AGENTS.md convention and the OpenSSF guide to security-focused assistant instructions. It covers instruction files, writing task prompts, verification loops, reviewing generated code, security and dependencies, and managing permissions and context.

• AI
• AI agents

A security checklist for teams putting AI agents and MCP servers into production. It covers tool inventory and least privilege, authentication and authorization for MCP servers, prompt injection that arrives through tool output, human approval for risky actions, sandboxed code execution, secrets handling, logging and incident response, and the supply chain of the MCP servers your agents load, each with a severity and a way to verify it.

• AI
• AI agents
• Security

Vendor-neutral best practices for building AI agents, checked against Anthropic's engineering guidance on agents, tools and context, the MCP specification's security best practices and the OWASP Top 10 for Agentic Applications. It covers choosing between workflows and agents, designing tools, managing context and memory, running a reliable agent loop, securing agents and MCP servers, and evaluating agent behaviour.

• AI
• AI agents

A standalone revision book on evaluating LLM apps and agents, in 10 chapters and 67 concepts: golden datasets, metrics by task type, LLM-as-judge and its biases, RAG and agent metrics, offline, online and CI evals, human review, the main tools as of October 2026 and a starter plan for your first week. It suits developers who change prompts and models and need to know whether things got better. Use it to pick a metric, check a judge and set a CI gate.

• AI
• Testing
• AI agents

A standalone revision book on how a production GenAI app fits together, in 10 chapters and 58 concepts: the request flow, frontend and backend layers, the RAG pipeline, tools and the agent loop, memory, caching and routing, three guard layers, the evaluation folder, observability, a reference project layout and a production checklist. It suits developers turning an LLM demo into an app with real users. Keep it open while you decide where each part of your code lives.

• AI
• Backend
• AI agents

The official docs for LangChain, the open-source framework for building LLM apps and agents. It gives you one interface to many model providers and create_agent, a small configurable agent harness built on LangGraph, with LangSmith for tracing. Read it to judge what a framework adds over plain SDK code.

• AI
• AI agents
• Programming

A free, interactive visual roadmap for designing, building and shipping AI agents: model basics, prompting, tools, memory, agent loops, evaluation and safety. It helps you understand what agent features in tools and frameworks are actually doing, and which parts you still need to learn.

• AI
• AI agents

Awesome AI Agents is a GitHub list from E2B that catalogues AI agent projects, frameworks and companies, split into open-source and closed-source sections, with a category, description and links for each. It is useful for exploring the agent landscape and finding prior art before building. Its product entries have not been substantially updated since late 2024, so treat it as a historical map and check newer sources for recent tools.

• AI
• AI agents

AGENTS.md is an open convention for a Markdown file at the root of a repository that tells AI coding agents how to build, test and work in that project. It is supported by more than 25 agents, including Codex, GitHub Copilot, Cursor, Gemini CLI, Jules and Devin. Adding one stops agents guessing your commands and conventions, and takes minutes.

• AI
• AI agents

An Anthropic engineering article from September 2025 on context engineering: deciding which instructions, tools, examples and history go into a model's limited context window at each step. It is for developers whose agent basically works but degrades on longer or harder tasks. It explains why bigger context windows did not remove the problem and gives concrete techniques such as compaction, note-taking and sub-agents.

• AI
• AI agents

UC Berkeley's Fall 2024 course on large language model agents, taught by Dawn Song and Xinyun Chen and offered free online as a MOOC. Its twelve recorded lectures, mostly by researchers from Google DeepMind, OpenAI, NVIDIA, Meta, Anthropic, Databricks and others, cover reasoning, agent frameworks, retrieval, coding agents, robotics and safety. It suits engineers and students who want the research foundations behind today's agent tools.

• AI
• AI agents