# metahumansworld/SIwithin

> Runs an agent CLI (Claude Code, Codex) unattended on a brief, restricting access to given folders and a dollar budget, and leaves one ledger line per run.

- Magnitude: 0.5 out of 10 — Quiet
- Stars: 3 total · +0 stars measured 2026-10-22, 00:03–04:59 UTC, ≈ 0 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: Python · License: Apache-2.0 · Created: 2026-10-13 · Last push: 2026-10-19
- GitHub: https://github.com/metahumansworld/SIwithin · Page: https://gitnova.dev/en/r/metahumansworld/SIwithin

## Useful for

- Run Claude Code or Codex CLI unattended on a task with folder and budget limits.
- Cap agent API spending via a proxy with per-run and total budget limits.
- Get a per-run ledger line recording cost and completion status.

## Why it’s here

- Star-counter measurements on 2026-10-22 (UTC), 00:03–04:59: 3 → 3 stars (+0). This is the change over that interval.
- The repository is 9 days old and already has 3 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Hacker News: “Show HN: Run Claude Code unattended inside a fence, under a dollar budget” — 8 points, 1 day ago.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 0
- Issues and pull requests: 0
- Watchers: 0
- Average over the last week: 0 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 0
- Latest release: v0.5.0 (2026-10-19)

## Stars per day, last 10 days (oldest → newest, today is partial)

2026-10-13 … 2026-10-22: 0, 0, 0, 0, 0, 0, 0, 3, 0, 0

## Magnitude by day, last 2 days

10-21 1.0, 10-22 0.6

## Hacker News

- Show HN: Run Claude Code unattended inside a fence, under a dollar budget — 8 points, 3 comments: https://news.ycombinator.com/item?id=50167456

## Spotted in now

- Spotted on Hacker News

## More in this category

1. **google-research/harness2** — 7.8 · Peaking · AI agents · Python · +150 stars measured 2026-10-22, 00:37–04:49 UTC, ≈ 1,080 by evening
   A framework for recursive optimization of AI agent harnesses (prompts, tools, memory, skills) without fine-tuning model weights, with JobBench, LAB and WorkBuddy-Bench benchmarks.
   Full card: https://gitnova.dev/en/r/google-research/harness2.md
2. **ai-job-search-dev/ai-job-search** — 7.2 · Peaking · AI agents · Python · +104 stars measured 2026-10-22, 00:37–04:49 UTC, ≈ 1,216 by evening
   A job application framework built on Claude Code: evaluates postings, tailors CVs, and writes cover letters. Runs locally, focused on the Danish job market.
   Full card: https://gitnova.dev/en/r/ai-job-search-dev/ai-job-search.md
3. **Graphify-Labs/graphify** — 6.9 · Breakout · AI agents · Python · +239 stars measured 2026-10-22, 00:37–04:49 UTC, ≈ 1,232 by evening
   Turns any codebase, docs, SQL schemas, configs, and PDFs into a queryable knowledge graph. Works as a /graphify skill in Claude Code, Cursor, Codex, and Gemini CLI with local deterministic AST parsing.
   Full card: https://gitnova.dev/en/r/Graphify-Labs/graphify.md
4. **DietrichGebert/ponytail** — 6.3 · Breakout · AI agents · JavaScript · +357 stars measured 2026-10-22, 00:37–04:49 UTC, ≈ 1,757 by evening
   A skill for AI coding agents (Claude Code, Codex, Copilot CLI, OpenCode) that enforces writing only the minimum necessary code via a laziness ladder: YAGNI, reuse, stdlib, native features. Benchmarks show ~54% less code and ~20% cheaper…
   Full card: https://gitnova.dev/en/r/DietrichGebert/ponytail.md
5. **aicodeking/pandacode** — 6.1 · Early signal · AI agents · Rust · +14 stars measured 2026-10-22, 00:37–04:49 UTC, ≈ 168 by evening
   A native desktop workspace for managing and running coding agents. It unifies projects, Git, terminal, and LLM tools in one window.
   Full card: https://gitnova.dev/en/r/aicodeking/pandacode.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-22 05:00 UTC, updated every 30 minutes.