Tag:agents
All the articles with the tag "agents".
What's actually in your agent's context
How coding agents assemble model input, what fills the context across 264 real Pi sessions, and what compaction keeps or leaves out.
A minimal agent loop and the four ways it breaks
(updated )I build a minimal agent loop in TypeScript and run it on a local model. It stops too early, crashes on a bad tool call, overflows its context and trusts what it reads. Each failure points to a part of the harness.
Linux Lost the Human Desktop. Can It Win the Agent Desktop?
The config files, shell commands, manuals, and source code that frustrated normal users may be exactly the handles AI agents need.
tl : a task ledger (cli) for humans and coding agents
I built a Git-native task ledger to coordinate work between myself and AI agents. Here is how it works, why I made it, and what the agent handoff looks like in practice.
Six weeks with coding agents
A personal note on my first real weeks with coding agents: OpenClaw, Codex, Claude Code, Pi, too many tokens, and a surprising amount of shipped code.
Beads: issue tracking for agent work
My notes on using Beads/bd as an issue tracker for AI-assisted coding
How I migrated this blog to Astro with Codex
(updated )Notes on migrating the old Hugo article archive into this Astro blog together with Codex, with bd as the task tracker and guardrail.
Field Notes
Proper agent names with Beads
Small shell helpers for giving Claude, Codex, Gemini, Pi and human roles distinct BEADS_ACTOR names.