
The Agent Loop Explained: How 5 SDKs Run Tools Until Done
An agent loop calls the model, runs tools, feeds results back and repeats until a stop rule fires. Defaults vary: 20 steps, 25 super-steps, 5, 10 or no cap.
10 articles

Seven multi-agent patterns, one diagram each, and which framework ships each natively: OpenAI Agents SDK, LangGraph, Mastra, AI SDK, ADK, CrewAI, A2A v1.0.

An agent loop calls the model, runs tools, feeds results back and repeats until a stop rule fires. Defaults vary: 20 steps, 25 super-steps, 5, 10 or no cap.

Herdr joined Y Combinator weeks after going public. We measured its plugin ecosystem of policy gates, editor bridges and a marketplace to see what it proves.

Steve Yegge's Gas Town thesis is less about one tool than a shift from one coding agent to a durable, supervised colony of workers.

Steve Yegge's Continuous Thunderdome essay, explained: Beads work graphs, all-night agent loops, and the Land Rush that replaces CI/CD. What to copy first.

Steve Yegge's model-welfare essay as agent engineering: persistent seats over sessions, graceful handoffs, and user feedback that flows back to agents.

Agent-Manager, Pane, and Golutra compared: three tools for running multiple CLI coding agents in parallel, by architecture, agent support, and workflow fit.

Loop engineering patterns: plan/act/verify cycles, convergence criteria, retries, budget-bounded loops, and loop-until-dry, so agents stop when they should.

Omnigent is a Databricks meta-harness above Claude Code and Codex that keeps sessions, policies and skills portable. What it does and how to install it.

What it actually takes to wire OpenAI Symphony into a Linear-driven Codex workflow - auth, runs, sandboxes, costs, and the gotchas nobody warned me about.
Showing 9 of 9 articles

New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.
Explore 844 topics
Browse All Topics