--- id: "/new/2026-w42/" title: "Index additions: 2026-W42" creator: null creator_url: null url: "https://skillissue.dev/new/2026-w42/" level: null level_max: null category: null subcategory: null region: null license: null license_scope: null models: null source_date: null date_added: null --- # Index additions: 2026-W42 Resources added to the index in this ISO week. This is a website archive, not a sent newsletter. [Beginner](/levels/beginner/index.md) [Intermediate](/levels/intermediate/index.md) [Advanced](/levels/advanced/index.md) [Expert](/levels/expert/index.md) 133 resources · page 1 of 5 ## Agents and harnesses - ### [A practical guide to building agents (PDF)](/agents/agent-design-patterns/openai-practical-guide-to-building-agents/index.md) by [OpenAI](https://cdn.openai.com/business-guides-and-resources/a-practical-guide-to-building-agents.pdf) Plain-language foundations: when to build an agent, orchestration, guardrails. Beginner · West · closed resource · en - ### [GigaChain agent cookbook](/agents/tool-use-and-mcp/ai-forever-gigachain-cookbook/index.md) by [GigaChain / ai-forever](https://github.com/ai-forever/gigachain) Russian notebooks connect GigaChat to typed functions, retrieval and MCP tools. Intermediate · RU · open resource · ru - ### [Building Effective AI Agents](/agents/agent-design-patterns/anthropic-building-effective-agents/index.md) by [Anthropic](https://www.anthropic.com/engineering/building-effective-agents) Workflows vs agents and the core patterns; argues to start simple. Readable without code. Intermediate · West · closed resource · en - ### [Best practices for Claude Code](/agents/coding-agents/anthropic-claude-code-best-practices/index.md) by [Anthropic](https://code.claude.com/docs/en/best-practices) Concrete coding-agent workflow habits: plan, verify, manage context. Intermediate · West · closed resource · en - ### [Hello-Agents: build agents in Chinese](/agents/agent-design-patterns/datawhale-hello-agents/index.md) by [Sizhou Chen, Tao Sun, Shufan Jiang and Datawhale contributors](https://github.com/datawhalechina/hello-agents) Chinese explanations and code move from model calls to ReAct, planning and reflection. Intermediate · CN · closed resource · zh - ### [AI Agents Course](/agents/agent-design-patterns/hf-ai-agents-course/index.md) by [Hugging Face](https://huggingface.co/learn/agents-course/unit0/introduction) Free course from 'what is an agent' to building one. Intermediate · West · closed resource · en - ### [Agents](/agents/agent-design-patterns/huyenchip-agents/index.md) by [Chip Huyen](https://huyenchip.com/2025/01/07/agents.html) Long-form essay on tools, planning, failure modes and evaluating agents. Intermediate · West · closed resource · en - ### [Model Context Protocol docs](/agents/tool-use-and-mcp/mcp-model-context-protocol-docs/index.md) by [MCP project](https://modelcontextprotocol.io/) The spec and docs for connecting tools and data to agents. Intermediate · other · closed resource · en - ### [OpenAI Agents SDK](/agents/harnesses-and-frameworks/openai-agents-sdk/index.md) by [OpenAI](https://openai.github.io/openai-agents-python/) Lightweight framework: handoffs, guardrails, tracing. Intermediate · West · closed resource · en - ### [How we built our multi-agent research system](/agents/multi-agent-systems/anthropic-multi-agent-research-system/index.md) by [Anthropic](https://www.anthropic.com/engineering/multi-agent-research-system) Real production lessons on orchestrator/sub-agent design and its costs. Advanced · West · closed resource · en - ### [Writing effective tools for AI agents](/agents/tool-use-and-mcp/anthropic-writing-tools-for-agents/index.md) by [Anthropic](https://www.anthropic.com/engineering/writing-tools-for-agents) How to design, evaluate and improve the tools an agent calls. Advanced · West · closed resource · en - ### [Browser Use](/agents/computer-and-browser-use/browser-use-browser-use/index.md) by [Browser Use contributors](https://github.com/browser-use/browser-use) Inspect a Python library for model-driven browser interaction. Advanced · other · open resource · en - ### [Don't Build Multi-Agents](/agents/multi-agent-systems/cognition-dont-build-multi-agents/index.md) by [Cognition](https://cognition.com/blog/dont-build-multi-agents) The counter-argument: context sharing beats splitting work across agents. Advanced · West · closed resource · en - ### [12-Factor Agents](/agents/agent-design-patterns/humanlayer-12-factor-agents/index.md) by [HumanLayer (Dex Horthy)](https://github.com/humanlayer/12-factor-agents) Principles for agents that hold up in production. Advanced · West · open resource · en - ### [LLM Powered Autonomous Agents](/agents/agent-design-patterns/lilianweng-llm-powered-autonomous-agents/index.md) by [Lilian Weng](https://lilianweng.github.io/posts/2023-06-23-agent/) Classic overview of planning, memory and tool use in agents. Advanced · West · closed resource · en - ### [MCP reference servers](/agents/tool-use-and-mcp/mcp-reference-servers/index.md) by [MCP project](https://github.com/modelcontextprotocol/servers) Reference implementations to learn MCP server design from. Advanced · other · closed resource · en - ### [OpenHands Agent Canvas](/agents/harnesses-and-frameworks/openhands-agent-canvas/index.md) by [OpenHands (All Hands AI)](https://github.com/OpenHands/OpenHands) Inspect the OpenHands control center and its supported execution backends. Advanced · West · open resource · en - ### [OpenHands Software Agent SDK](/agents/harnesses-and-frameworks/openhands-openhands/index.md) by [OpenHands](https://github.com/OpenHands/software-agent-sdk) Open-source agent SDK behind OpenHands, worth reading as a reference harness. Advanced · West · open resource · en - ### [Qwen-Agent](/agents/harnesses-and-frameworks/qwen-team-alibaba-qwen-agent/index.md) by [Qwen team, Alibaba](https://github.com/QwenLM/Qwen-Agent) A Qwen-focused framework for tool-using applications. Advanced · CN · open resource · en - ### [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](/agents/coding-agents/yang-swe-agent/index.md) by [John Yang et al.](https://arxiv.org/abs/2405.15793) Research on how the agent-computer interface influences software-engineering performance. Advanced · West · open resource · en - ### [ReAct: Synergizing Reasoning and Acting in Language Models](/agents/agent-design-patterns/yao-react/index.md) by [Shunyu Yao et al.](https://arxiv.org/abs/2210.03629) Research on combining reasoning with environment actions, a useful reference for agent-loop design. Advanced · West · open resource · en ## Context Engineering - ### [AGENTS.md](/context-engineering/agent-instruction-files/agentsmd-agents-md/index.md) by [AGENTS.md (multi-vendor open format)](https://agents.md/) Open format for a repo instruction file that coding agents read. Beginner · other · closed resource · en - ### [Equipping agents for the real world with Agent Skills](/context-engineering/agent-instruction-files/anthropic-agent-skills/index.md) by [Anthropic](https://www.anthropic.com/engineering/equipping-agents-for-the-real-world-with-agent-skills) Packaging instructions and scripts as loadable skills. Intermediate · West · closed resource · en - ### [Effective context engineering for AI agents](/context-engineering/context-management/anthropic-effective-context-engineering/index.md) by [Anthropic](https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents) Treats context as a finite budget: compaction, notes, sub-agents. Intermediate · West · closed resource · en - ### [Letta documentation](/context-engineering/memory/letta-memory-docs/index.md) by [Letta](https://docs.letta.com/) Explore documentation for agents that keep state across interactions. Intermediate · West · closed resource · en - ### [Context Engineering for Agents](/context-engineering/context-management/rlancemartin-context-engineering-for-agents/index.md) by [Lance Martin](https://rlancemartin.github.io/2025/06/23/context_engineering/) Write/select/compress/isolate taxonomy of context strategies. Intermediate · West · closed resource · en - ### [Effective harnesses for long-running agents](/context-engineering/loop-engineering/anthropic-effective-harnesses-long-running-agents/index.md) by [Anthropic](https://www.anthropic.com/engineering/effective-harnesses-for-long-running-agents) Harness design for agents that work across many context windows. Advanced · West · closed resource · en - ### [Context Rot: How Increasing Input Tokens Impacts LLM Performance](/context-engineering/context-management/chroma-context-rot/index.md) by [Chroma](https://www.trychroma.com/research/context-rot) Measures how output quality drops as input length grows. Advanced · West · closed resource · en - ### [Context Engineering for AI Agents: Lessons from Building Manus](/context-engineering/context-management/manus-context-engineering-lessons/index.md) by [Manus](https://manus.im/blog/Context-Engineering-for-AI-Agents-Lessons-from-Building-Manus) KV-cache-aware design, file system as memory, keep errors in context. Advanced · other · closed resource · en - ### [A Survey of Context Engineering for LLMs (arXiv 2507.13334)](/context-engineering/context-management/mei-et-al-a-survey-of-context-engineering-for-llms/index.md) by [Mei et al. (Chinese Academy of Sciences et al.)](https://arxiv.org/abs/2507.13334) A research map of retrieval, context processing and memory systems. Advanced · CN · closed resource · en - ### [RAG Techniques](/context-engineering/retrieval-and-rag/nirdiamant-rag-techniques/index.md) by [Nir Diamant and contributors](https://github.com/NirDiamant/RAG_Techniques) Compare retrieval designs through code-oriented examples. Advanced · other · closed resource · en ## Lab Practices - ### [GigaChat Python SDK](/lab-practices/other-labs/ai-forever-gigachat-sdk/index.md) by [GigaChain / AI Forever](https://github.com/ai-forever/gigachat) An SDK reference for calling the GigaChat service from Python. Intermediate · RU · open resource · en [Next page](/new/2026-w42/page/2/index.md) [Plain-text Markdown copy](/new/2026-w42/index.md)