Siltpoke is an independent second mind that rides along while you build with your CLI coding agent. It catches what you missed, helps you understand the codebase you shipped, and learns what you actually care about — a pet that earns its opinions, remembers your projects, and is wholly yours. On the token budget you already have.
$ git clone github.com/Victoriakaey/siltpoke ~/siltpoke
$ cd ~/siltpoke && bun install
$ bun run setup_
/\_/\ (o.o) > ^ <
/\_/\ (>.<) > _ <
One pet, one memory, across agents — when one hits its daily limit, switch to another and keep going. Nothing to re-explain.
The ASCII pet is the friendly face on a system that's with you for the long haul — it levels up as you forward good calls, accumulates rules from your feedback, and remembers your projects. Five species, five 0–10 dials, a name and a language of its own.
Three ways to set the dials in the setup wizard — re-roll anytime with bun run first-run.
~/.claude/ files — CLAUDE.md, rules, memory.Pick a species for a preset, then read what each dial changes. Their high/low pattern lands on one of the 16 archetypes below.
Each dial defaults to a neutral 5/10. These presets are illustrative — yours are whatever you set.
Each runs 0–10 (default 5). Their high/low pattern picks the archetype below.
XP only ever climbs — a wrong call gets dismissed, never docks you.
Building something real used to take prompt skills, planning skills, and constant vigilance. With siltpoke and project-life-cycle together, you bring the idea — the system carries the rest to shipped. And it stays after shipping: most tools leave when the code lands — this one keeps the map, the review trail, and the reasons.
Say the rough idea in your own words. It asks the clarifying questions, researches the options, and writes the plan — before any code.
Speak plainly. The intent gate turns a vague ask into a precise, structured prompt before it ever reaches your coding agent.
After each turn, an independent second mind reviews what your agent did, catches what it missed, and points at the exact line. Change a function's signature, and it traces which callers break.
The worst vibe-coding moment: your agent's quota runs out mid-build and everything halts. Not anymore — project memory and the paper trail live on your machine, not inside any one agent, so switching is cheap. Open another agent and pick up mid-task, nothing to re-explain.
Cost-aware habits are built into the workflow — phase handoffs, batched questions, the right model for each job — so usage doesn't silently burn away.
One map of your repo — components and how they call each other. Plus a journal that remembers why each change was made, and which options were rejected.
Wondering why not just use your coding agent alone? Common questions →
siltpoke and project-life-cycle are open and always evolving — star them, file an issue, join the chat, or just say hi.
Want to say hi, ask something, or share an idea directly? Drop a note — it comes straight to me.
Found a bug or want to contribute? Open a GitHub issue →
/\_/\ (o.o) > ^ <
An independent second mind that reviews your work, maps what you built, remembers what you care about, and grows with you — on the token budget you already have.
siltpoke keeps all memory and state on your machine — no siltpoke cloud, no analytics, nothing sent back to anyone. To review or chat, it reuses the CLI login your coding agent already has, so your code takes the exact same path it already takes — and goes nowhere else.