# Balanov/uncut

> A tiny headless coding-agent harness in Go for shell pipelines, CI, and local models. Sends the full conversation on every call without truncating context or output.

- Magnitude: 5.6 out of 10 — Early signal
- Stars: 249 total · +47 stars measured 2026-11-02, 00:07–02:12 UTC, ≈ 295 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: Go · License: MIT · Created: 2026-11-01 · Last push: 2026-11-02
- GitHub: https://github.com/Balanov/uncut · Page: https://gitnova.dev/en/r/Balanov/uncut

## Useful for

- Review a git diff by piping it into the agent without editing files
- Run the agent in a CI job to inspect a repository and fix failing tests
- Resume a long refactor across steps using an append-only JSONL session

## Why it’s here

- Star-counter measurements on 2026-11-02 (UTC), 00:07–02:12: 202 → 249 stars (+47). This is the change over that interval.
- Estimated end-of-day forecast: about +295 stars, using observed gains and the previous day.
- The repository is 1 day old and already has 249 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #126.

## 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: 4
- Average over the last week: 274 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 27
- Latest release: v0.1.1 (2026-11-01)

## Stars per day, last 2 days (oldest → newest, today is partial)

2026-11-01 … 2026-11-02: 254, 47

## Spotted in now

- Top new repositories this week: #126

## More in this category

1. **deepseek-ai/dsh-superagent-prototype** — 9.5 · Breakout · AI agents · TypeScript · +828 stars measured 2026-11-02, 00:07–02:12 UTC, ≈ 4,904 by evening
   Research prototype of a proactive coding agent for a single GitHub repository, packaged as a bundle for DeepSeek Harness: it listens to GitHub and Feishu, opens work items and replies in the original conversation, for example with a pull…
   Full card: https://gitnova.dev/en/r/deepseek-ai/dsh-superagent-prototype.md
2. **pingdotgg/t3code** — 8.8 · Breakout · AI agents · TypeScript · +263 stars measured 2026-11-02, 00:07–02:12 UTC, ≈ 2,263 by evening
   T3 Code is an agent harness control surface for agents on your machine, with mobile (iOS, Android), web and Electron desktop apps. It works with your Claude Code, Codex, Cursor, Grok Build, OpenCode and Google Antigravity subscriptions if…
   Full card: https://gitnova.dev/en/r/pingdotgg/t3code.md
3. **storytold/craft-anything** — 8.4 · Early signal · AI agents · Rust · +239 stars measured 2026-11-02, 00:07–02:12 UTC, ≈ 1,330 by evening
   A pure-Rust reverse-engineering engine with 284 tools that inspects websites, apps and games, then has a coding agent rebuild a similar version and checks the result against the original.
   Full card: https://gitnova.dev/en/r/storytold/craft-anything.md
4. **Donchitos/Claude-Code-Game-Studios** — 7.8 · Breakout · AI agents · Shell · +131 stars measured 2026-11-02, 00:07–02:12 UTC, ≈ 1,074 by evening
   A Claude Code configuration that turns a single session into a structured game studio: 49 specialized subagents, 74 slash-command skills, hooks, rules and templates mirroring a real studio hierarchy. It adds design reviews, QA passes and…
   Full card: https://gitnova.dev/en/r/Donchitos/Claude-Code-Game-Studios.md
5. **lightpanda-io/browser** — 7.5 · Breakout · AI agents · Zig · +131 stars measured 2026-11-02, 00:07–02:12 UTC, ≈ 927 by evening
   Lightpanda is a headless browser written from scratch in Zig, designed for AI agents and automation. It is not a Chromium fork and uses ~16x less memory and runs ~9x faster than headless Chrome.
   Full card: https://gitnova.dev/en/r/lightpanda-io/browser.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 2026-11-02 02:24 UTC, updated every 30 minutes.