AGENT-ARCHITECTURE
4 items
4 posts
Blog
pi Deep Dive: The Minimal Architecture Behind 95,000 GitHub Starspi coding agent toolkit deep dive: five packages, branching JSONL session trees, four run modes, and why it refuses to build sub-agents, plan mode or MCP.
Blog
Self-Improving Agents in 5 Minutes: Reflect, Refine, RepeatSelf-improving agents explained: reflection loops, Reflexion, LATS tree search, and meta agents, plus how to ground the critique step so the loop converges.
Blog
Managed Agents vs LangGraph vs Rolling Your Own: Who Should Run Your Agent Loop in 2026Managed agents vs LangGraph vs a DIY while-loop - compare state, sandboxing, cost, lock-in and compliance to decide who should run your agent loop in 2026.
Blog
Multi-Stream LLMs Hint at the Next Agent ArchitectureMulti-Stream LLMs argue agents are bottlenecked by single chat streams. The practical takeaway: design agent runtimes around separated channels now.

Get Smarter About AI Dev
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.
One email per weekReal code, not theoryFree forever