# sshah03/recalc

> A local spreadsheet where each cell can be a value, formula, terminal command, or a Claude Code or Codex agent, letting you coordinate multiple AI agents on one shared grid.

- Magnitude: 4.2 out of 10 — Early signal
- Stars: 42 total · +9 stars measured 2026-11-10, 00:29–06:04 UTC, ≈ 35 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: Rust · License: Apache-2.0 · Created: 2026-11-03 · Last push: 2026-11-09
- GitHub: https://github.com/sshah03/recalc · Page: https://gitnova.dev/en/r/sshah03/recalc

## Useful for

- Put a test-runner cell next to an agent's 'done' cell so failing tests are visible immediately.
- Run one agent per row to process many documents or tasks and track progress in one screen.
- Export agent-filled answers to Excel once you've reviewed and marked the verified cells.

## Why it’s here

- Star-counter measurements on 2026-11-10 (UTC), 00:29–06:04: 33 → 42 stars (+9). This is the change over that interval.
- Estimated end-of-day forecast: about +35 stars, using observed gains and the previous day.
- The repository is 7 days old and already has 42 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Hacker News: “Show HN: Recalc – Spreadsheet where cells can be Claude Code or Codex terminals” — 29 points, 1 day ago.
- Recent forks include notable developers: @dorucioclea (317 followers).

## 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: 3
- Issues and pull requests: 2
- Watchers: 1
- Average over the last week: 11 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 1
- Latest release: v0.1.3 (2026-11-08)

## Stars per day, last 8 days (oldest → newest, today is partial)

2026-11-03 … 2026-11-10: 1, 2, 0, 0, 0, 5, 35, 9

## Magnitude by day, last 2 days

11-09 2.8, 11-10 4.3

## Hacker News

- Show HN: Recalc – Spreadsheet where cells can be Claude Code or Codex terminals — 29 points, 8 comments: https://news.ycombinator.com/item?id=50413970

## Spotted in now

- Spotted on Hacker News

## More in this category

1. **janestreet/agent_skills** — 8.6 · Breakout · AI agents · +399 stars measured 2026-11-10, 00:26–06:03 UTC, ≈ 1,625 by evening
   A collection of skills for AI agents and chatbots from Jane Street: each skill is a directory with a SKILL.md file containing instructions. The first skill, socratic-tutor, turns an LLM into a strict personal tutor that teaches a chosen…
   Full card: https://gitnova.dev/en/r/janestreet/agent_skills.md
2. **ZhuLinsen/daily_stock_analysis** — 8.2 · Breakout · AI agents · Python · +345 stars measured 2026-11-10, 00:26–06:03 UTC, ≈ 1,055 by evening
   LLM-powered multi-market stock analysis system: gathers quotes, news and fundamentals for A-shares, Hong Kong, US, Japan, Korea and Taiwan, produces a daily decision dashboard and pushes it to messengers. Runs on a schedule in GitHub…
   Full card: https://gitnova.dev/en/r/ZhuLinsen/daily_stock_analysis.md
3. **vercel-labs/agent-browser** — 7.4 · Breakout · AI agents · Rust · +227 stars measured 2026-11-10, 00:26–06:03 UTC, ≈ 799 by evening
   A Rust CLI for browser automation aimed at AI agents: it opens pages, clicks elements, fills forms, and takes screenshots via simple commands.
   Full card: https://gitnova.dev/en/r/vercel-labs/agent-browser.md
4. **homeassistant-ai/ha-mcp** — 7.3 · Breakout · AI agents · Python · +181 stars measured 2026-11-10, 00:26–06:03 UTC, ≈ 661 by evening
   An MCP server that lets AI assistants (Claude, ChatGPT, etc.) control Home Assistant: toggle devices, query states, call services and automations in natural language.
   Full card: https://gitnova.dev/en/r/homeassistant-ai/ha-mcp.md
5. **garrytan/gbrain** — 7.2 · Breakout · AI agents · TypeScript · +155 stars measured 2026-11-10, 00:26–06:03 UTC, ≈ 536 by evening
   A personal and company memory layer for AI agents: stores facts with sources, supports corrections and sharing across agents, and adds semantic search, answer synthesis, and a knowledge graph. Runs as a local daemon with background…
   Full card: https://gitnova.dev/en/r/garrytan/gbrain.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 2026-11-10 06:13 UTC, updated every 30 minutes.