Blog

apic turns any HTTP API into a command line tool: it reads the API definition (OpenAPI / Swagger, or a few lines of YAML) and builds one command per endpoint, with parameters as options and shell completion.

• Definitions become commands: a service with an OpenAPI document is one site add away; for an internal service without one, list its endpoints in a few lines of YAML. apic link also gives a site its own command, such as petctl.
• Environments and authentication: separate base URLs and credentials for dev and prod; bearer, basic, apikey, log-in-for-a-token and token-from-a-command auth; writes to production need --yes.
• Picking, paging, formatting: --pick takes fields from any level and renames them, --all-pages walks and merges the pages, -o table / yaml makes the result readable.
• For people and AI agents: stdout carries only the response body, exit codes have fixed meanings, and apic skill writes a SKILL.md for agents. Secrets are masked in -v, --dry-run and error messages.

With three or four Claude Code and Codex sessions open across two computers and a container, I kept losing track of simple things. Which session is waiting for me? What did the agent I asked to fix a test change, and did it run the tests? The job I handed out last night: did it finish, get stuck, or crash an hour in? And when I’m away from my desk, can I check from my phone and approve something?

gofer is the tool I wrote for that. In one line: your agents, your machines, one control plane. It runs Claude Code, Codex, ACP agents or plain commands as tracked, reviewable jobs on every machine you own, with no cloud in between and no inbound ports to open on the workers.

Keep an agent in one session long enough and three things go wrong. The context fills up and gets compacted, and the part that gets dropped is the constraint you gave it in the first turn. Every request carries a few thousand tokens of fixed overhead, so long sessions get expensive. And when something breaks, there is no record of what the agent did.

suga is a personal coding agent I write in Go. The goal is a session that can stay with me for a full working day. This post covers the trade-offs it makes for long sessions, which of them are backed by data and which experiments failed, and how it works with gofer, my job platform. suga itself is built on gofer, one batch of agent jobs at a time.

The current version is v0.49. It is v0, so minor releases may break things. It is MIT licensed. What follows is an introduction to suga.

The last post about miglite covered v0.4.0 in June. In the three months since then, it reached v0.8.0 through four releases and 69 commits (v0.4.0..v0.8.0). The main problem I wanted to solve was carrying a migrations/ directory alongside the binary. A few flags that were accepted but did nothing also needed fixing.

Many CLI tools start with a parser, a few commands, and some fmt.Println calls. That works until the tool needs readable config output, clear errors, prompts, progress bars, and logs that do not break in CI.

github.com/gookit/cliui is for that middle ground: not a full-screen TUI, but more than loose terminal prints. It splits the common pieces into three packages: show for structured output, interact for prompts and selections, and progress for long-running work.