Nicheloom visits: 58,050 all-time · 7,694 in the last 7 days

The opportunity tracker for new startups.

Today: 1,953 launches · Niche of the day: specialized calculation tools · See what launched today →

Pu.sh

a full coding-agent harness in 400 lines of shell

Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.

Want to reach these readers? Sponsor an issue.

I originally was just messing with pi-autoresearch. Gave it a sample task to build the most portable coding agent.First cut was 6 KB of shell. Great for one-shots, unusable interactively. I was shocked it actually worked.Started building up -- adding features — but with a self-imposed rule: no new dependencies, and sub 500 LOC. This thing had to be truly portable. Just sh, curl, awk. System primitives only.Which means I did some genuinely disgusting things in awk, including JSON parsing and the OpenAI Responses tool loop with reasoning items carried across turns.It's now ~400 lines. In the box: Anthropic + OpenAI, 7 tools (bash, read, write, edit, grep, find, ls), REPL, auto-compaction, checkpoint/resume, pipe mode, 90 no-API tests. Not in the box: TUI, streaming, images, OAuth, Windows, dignity.Two honest things:1. I stole/modified the system prompt and the architecture. Pi/Claude/Codex wrote the awk. I cannot read most of this code. This wasn't possible for me a year ago.2. Heavily inspired by Pi (pi.dev) — same 7-tool surface, same exact-text edit model. Credit where it's due. Pi is awesome -- you should probably use them.The agent loop itself is tiny. Almost everything else in a "real" agent CLI is DX and hardening. You can probably build your own harness exactly how you like it. Mario Zechner's AI Engineer talk on taking back control of your tools nudged me here.The name is because it's a .sh file. The other thing it sounds like is, regrettably, also accurate.

HN · launched Apr 30, 2026 · 92 upvotes (top 12%) · 0 views

Niche: ai coding agents · 470 launches, 22 in the last 7 days ▼ -48% · Explore this niche →

Category and tags

  • Horizontal
  • Agent / copilot
  • Developer
  • AI-native
  • Hobby / open-source project

Visit website ↗ Source listing ↗

Could you build this?

Yes As noted in the description, it is a minimal 400-line shell script harness calling LLM APIs and executing local commands via bash.

Discussion

20 comments analyzed.

Competitors mentioned: Claude agent SDK, pi-autoresearch, aloop (vendor-agnostic agent harness), Other agentic-loop implementations

Concerns raised: Code readability and maintainability of minified version, Agent tool call recording/replaying for debugging, Agent forgetting or misinterpreting instructions, Excessive LOC constraint limiting practical usability, Confidence in code quality and reliability

Feature requests: Read-only mode toggle, Better tool call recording and failure mode replay, Markdown output formatting, Python package or embeddable SDK version, Just-bash compatibility

Competitors

Other products that read as similar to this one : 967 launches clear the similarity bar, closest 8 shown.

Attention rank: #150 of 968 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).

Launched 182 days after the earliest competitor.

The niche, labels, vibe code rating and competitor comparison on this page are analysis by Nicheloom. If you use them, please credit nicheloom.com. How you may use our data.