Reading up on Claude Agent SDK
11 deep · digging since nov 27, 25
- The evolution of agentic surfaces: building with Claude Managed Agents
Claude Managed Agents decouples model reasoning from code execution to let teams deploy production-grade agents without building custom infrastructure.
- An update on recent Claude Code quality reports
Three separate changes to Claude Code's reasoning effort, session caching, and system prompt caused degraded performance for users between March and April 2025, all now resolved.
- Harness design for long-running application development
Anthropic engineer Prithvi Rajasekaran builds a multi-agent harness with planner, generator, and evaluator agents that produces full-stack applications over multi-hour autonomous coding sessions.
- What we wish we knew about building AI agents
PostHog shares lessons from two years building AI agents, urging teams to validate demand with simpler interfaces like MCP servers before committing to custom agents.
- The Software Factory: Why Your Team Will Never Work the Same Again
AI coding agents like Claude Code already enable software factories where developers design specs and agents implement, shrinking teams and shipping features in hours instead of weeks.
- GitHub - ComposioHQ/open-claude-cowork: Open Source version of Claude Cowork built with Claude Code and Composio Tool Router
An open-source desktop chat application that integrates Claude Agent SDK and Composio Tool Router to automate work across desktop and 500+ SaaS apps.
- The Complete Guide to Building Agents with the Claude Agent SDK
A guide to building a code review agent using the Claude Agent SDK, covering setup, tools, custom tools, subagents, hooks, and structured output.
- The importance of Agent Harness in 2026
By 2026, agent harnesses will become essential infrastructure for building reliable AI systems that can execute complex, multi-day tasks.
- Anthropic acquires Bun
Anthropic has acquired Bun, the JavaScript runtime, to power Claude Code and AI coding tools, with Bun remaining open-source and MIT-licensed.
- Effective harnesses for long-running agents \ Anthropic
Anthropic developed a two-fold harness with an initializer agent and a coding agent to enable long-running agents to make incremental progress across multiple context windows.