8 articles · 4 projects
Digging through five generations of agent frameworks, from raw API loops to federated swarms. How the developer went from outer shell to inner kernel, why each generation compressed faster than the last, and why the cycle is restarting.
I launched an orchestrator that managed 7 Claude Code peers across repos simultaneously. They found SQL injections, fixed a 9x cost bug, built new features, and shipped 130+ commits while I slept.
Autonomous AI agents degrade over long-horizon tasks through accumulated context pollution, not single failures. What agent drift is, why it happens, and how to architect against it.
Build AI agents from the inside out — start with behavior in CLAUDE.md, add capabilities via MCP, then wrap in code with the Claude Agent SDK.
Agents are stateful logic, not stateless apps. The cloud primitives — durable execution, agent identity, MCP — that AI agents need to run reliably.
AI agent memory management mirrors database design. Agent state needs persistence, retries, and checkpointing — the same problems backend systems solved.
Torale monitors the web so you don't have to. How ambient AI turns passive monitoring into proactive intelligence — and how Gemini made it possible.
A practical comparison of AI agent frameworks — OpenAI Agents SDK, Google ADK, AWS Bedrock, and Smol Agents — covering architecture, multi-agent systems, and emerging trends.
Turn AI agents into production-ready A2A services with pluggable runtime backends
A community-driven, open-source directory of AI agents using the A2A Protocol
JWT-based authentication framework for AI agent networks using Supabase - making agent-to-agent communication secure and effortless
AI-powered web monitoring platform that tracks topics and alerts you when meaningful changes occur across the internet