Index additions: 2026-W42
Resources added to the index in this ISO week. This is a website archive, not a sent newsletter.
125 resources · page 1 of 4
Agents and harnesses
A practical guide to building agents (PDF)
by OpenAI
Plain-language foundations: when to build an agent, orchestration, guardrails.
Building Effective AI Agents
by Anthropic
Workflows vs agents and the core patterns; argues to start simple. Readable without code.
Best practices for Claude Code
by Anthropic
Concrete coding-agent workflow habits: plan, verify, manage context.
AI Agents Course
by Hugging Face
Free course from 'what is an agent' to building one.
Agents
by Chip Huyen
Long-form essay on tools, planning, failure modes and evaluating 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.
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.
Browser Use
Inspect a Python library for model-driven browser interaction.
Don't Build Multi-Agents
by Cognition
The counter-argument: context sharing beats splitting work across agents.
12-Factor Agents
Principles for agents that hold up in production.
LLM Powered Autonomous Agents
by Lilian Weng
Classic overview of planning, memory and tool use in agents.
MCP reference servers
by MCP project
Reference implementations to learn MCP server design from.
OpenHands Agent Canvas
Inspect the OpenHands control center and its supported execution backends.
OpenHands Software Agent SDK
by OpenHands
Open-source agent SDK behind OpenHands, worth reading as a reference harness.
Qwen-Agent
A Qwen-focused framework for tool-using applications.
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.
Context Engineering
AGENTS.md
by AGENTS.md (multi-vendor open format)
Open format for a repo instruction file that coding agents read.
Equipping agents for the real world with Agent Skills
by Anthropic
Packaging instructions and scripts as loadable skills.
Effective context engineering for AI agents
by Anthropic
Treats context as a finite budget: compaction, notes, sub-agents.
Letta documentation
by Letta
Explore documentation for agents that keep state across interactions.
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.
Context Rot: How Increasing Input Tokens Impacts LLM Performance
by Chroma
Measures how output quality drops as input length grows.
Context Engineering for AI Agents: Lessons from Building Manus
by Manus
KV-cache-aware design, file system as memory, keep errors in context.
A Survey of Context Engineering for LLMs (arXiv 2507.13334)
by Mei et al. (Chinese Academy of Sciences et al.)
A research map of retrieval, context processing and memory systems.
RAG Techniques
by Nir Diamant and contributors
Compare retrieval designs through code-oriented examples.
Lab Practices
GigaChat Python SDK
An SDK reference for calling the GigaChat service from Python.
Anthropic Engineering blog
by Anthropic
Find first-party accounts of engineering decisions behind Claude systems.
Claude Cookbooks
by Anthropic
Code recipes for integrating Claude capabilities into applications.