Agents and harnesses
26 resources
AGENTS.md
by AGENTS.md (multi-vendor open format)
Open format for a repo instruction file that coding agents read.
Building Effective AI Agents
by Anthropic
Workflows vs agents and the core patterns; argues to start simple. Readable without code.
AI Agents Course
by Hugging Face
Free course from 'what is an agent' to building one.
A practical guide to building agents (PDF)
by OpenAI
Plain-language foundations: when to build an agent, orchestration, guardrails.
Equipping agents for the real world with Agent Skills
by Anthropic
Packaging instructions and scripts as loadable skills.
Best practices for Claude Code
by Anthropic
Concrete coding-agent workflow habits: plan, verify, manage context.
Effective context engineering for AI agents
by Anthropic
Treats context as a finite budget: compaction, notes, sub-agents.
12-Factor Agents
Principles for agents that hold up in production.
Agents
by Chip Huyen
Long-form essay on tools, planning, failure modes and evaluating agents.
LLM Powered Autonomous Agents
by Lilian Weng
Classic overview of planning, memory and tool use in agents.
Model Context Protocol docs
by MCP project
The spec and docs for connecting tools and data to agents.
OpenAI Agents SDK
by OpenAI
Lightweight framework: handoffs, guardrails, tracing.
Context Engineering for Agents
by Lance Martin
Write/select/compress/isolate taxonomy of context strategies.
Effective harnesses for long-running agents
by Anthropic
Harness design for agents that work across many context windows.
How we built our multi-agent research system
by Anthropic
Real production lessons on orchestrator/sub-agent design and its costs.
Writing effective tools for AI agents
by Anthropic
How to design, evaluate and improve the tools an agent calls.
Context Rot: How Increasing Input Tokens Impacts LLM Performance
by Chroma
Measures how output quality drops as input length grows.
Don't Build Multi-Agents
by Cognition
The counter-argument: context sharing beats splitting work across agents.
Context Engineering for AI Agents: Lessons from Building Manus
by Manus
KV-cache-aware design, file system as memory, keep errors in context.
MCP reference servers
by MCP project
Reference implementations to learn MCP server design from.
OpenHands
Open-source coding-agent platform worth reading as a reference harness.
The lethal trifecta for AI agents
A defensive framework for recognizing risky combinations of agent capabilities and untrusted inputs.
Design Patterns for Securing LLM Agents against Prompt Injections
Summary of a paper's defensive agent architectures.
Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection
Foundational public research on indirect prompt injection. Linked only; no payloads reproduced.
SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
Research on how the agent-computer interface influences software-engineering performance.
ReAct: Synergizing Reasoning and Acting in Language Models
Research on combining reasoning with environment actions, a useful reference for agent-loop design.