Anthropic's engineering blog packs 28 deep dives on agent memory, Claude Code and in-house source control
bookwormengr · x · 2026-11-12
Anthropic's engineering blog now hosts 28 articles, the latest being "The components of agent memory" (Nov 6, 2026), which explains how "dreaming" helps Claude decide what's worth remembering and correct mistakes.
Recent highlights:
- Redesigning source control at Anthropic: after daily merges grew more than tenfold, the team migrated to an in-house version control system in five months.
- Harness design for long-running application development: how harness design pushed Claude further in frontend design and autonomous software engineering.
- Building a C compiler with a team of parallel Claudes.
- Other topics span Managed Agents scaling, Claude Code auto mode, eval awareness in Opus 4.6's BrowseComp, infrastructure noise in agentic evals, AI-resistant technical evaluations, MCP code execution, and Agent Skills.
The poster also praises the visual design of the blog page.
Related event: Anthropic Details How Claude Agents Build and Consolidate Memory(3 posts)→
More from coding & agent
- Matt Pocock shares the 'Home Repo' pattern for managing agent skills across multiple repos — mattpocockuk · 2026-11-12
- Community-built desktop app runs Grok Build, Codex, Claude Code agents without an IDE — PawelHuryn · 2026-11-12
- AFK Pilot's Agent Board manages parallel AI agents with phases and open decisions — PawelHuryn · 2026-11-12
- Anthropic's 'Worse Together': single coordinator agent beats per-user agent teams in all 4 tests — ombre-ai · 2026-11-12
- Matt Pocock's Home Repo pattern: run coding agents across multiple repos, setup prompt included — mattpocockuk · 2026-11-12
- When policy runs out: should AI support bots decide edge cases no one approved? — ElphieJ · 2026-11-12