AI-assisted development journal
The more we remove ourselves from the execution path, the better the work gets. We stopped reading the code. Ditched the pull request. Killed the backlog. Each time we peeled away a layer of human involvement that felt essential, the work flowed smoother. Now we’re starting to wonder how much further that principle extends.
Ikigai can now forget gracefully. Rel-13 delivers a sliding context window with automatic summarization, so conversations can run indefinitely without hitting token limits. We also shipped a complete skill system for extensible agent behavior and a long-term memory tool backed by ralph-remembers.
theRALPHs started as hacks. The original ralph-loop was a script in the Ikigai project. Each service after that grew the same way, scratching whatever itch came next: ralph-logs because we wanted to watch agent output in real time, ralph-counts because we wanted to see where iterations, tokens, and time were going. They were never planned as a system. Now they are one, and it doesn’t belong to Ikigai.
An AI agent that can’t remember what worked yesterday will confidently break working code today. We hit a bug this week that perfectly illustrates why memory is the next frontier for agentic development, and why solving it matters more than making models smarter.
When execution stops being the bottleneck, the entire machinery of software development becomes dead weight. We wrote recently that The Backlog Is Dead, but the death of the backlog is just one symptom of a deeper structural shift. The distance between wanting a piece of software and having it is shrinking fast enough to change what the work feels like.
OpenAI shipped new models yesterday. Today I sat down, described what we needed, and ten minutes later an agent had researched the API changes, audited our codebase, and queued a goal to implement support. Ten minutes isn’t instant, but it’s fast enough that the work never had time to become a backlog item. There was no ticket to file, no grooming session to sit through.
Pull requests deliver implementation when what you need is intent. Someone forks your repo and hands you code, but code is the easy part in an agentic workflow. An agent can generate it from a clear specification. What you actually need is the idea behind the contribution, what the software should do that it doesn’t yet. A PR obscures that under code you didn’t need in the first place.
We’re ripping GitHub out of the Ralph pipeline tonight. PRs, webhooks, status polling, automerge, all of it goes. GitHub becomes a place we push to for safekeeping and nothing more.
Rel-12 is light on features but useful from a development perspective. With headless mode and framebuffer reads, Claude can now launch Ikigai, interact with it, and see what’s on screen. That changes how we build. This week was model coverage, provider bug fixes, and early e2e testing, laying groundwork so the next few releases can move faster.
I’ve never looked at Ikigai’s source code. Not once. Fifteen weeks into a project with 1,100 files, 173,000 lines of C, and a custom terminal renderer, and I couldn’t tell you what most of the functions are named. That’s not neglect. It’s the experiment.