# andreylukin/bough

> A terminal coding agent where the model writes a single JavaScript program instead of calling tools one at a time. Every part — provider, loop, tools, UI, MCP — is a plugin configured in YAML.

- Magnitude: 0.0 out of 10 — Quiet
- Stars: 9 total · +0 stars on 2026-10-02 (UTC), ≈ 0 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: Go · License: Apache-2.0 · Created: 2026-06-18 · Last push: 2026-10-02
- GitHub: https://github.com/andreylukin/bough · Page: https://gitnova.dev/en/r/andreylukin/bough

## Useful for

- Run the agent inside a git repo so it patches files and runs tests in one program
- Plug in your own Anthropic, OpenAI, OpenRouter or Cerebras key and work in the TUI
- Run bough --headless in a script or benchmark and consume events as JSON

## Why it’s here

- Hacker News: “Show HN: Bough, the agent I built to replace Claude Code at work” — 10 points, 17 days 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: 1
- Issues and pull requests: 93
- Watchers: 1
- Average over the last week: 0 per day
- Usual pace: 0 per day
- Latest release: v0.2.7 (2026-09-15)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-10-05 … 2026-11-03: None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None

## Magnitude by day, last 14 days

09-19 0.4, 09-20 0.4, 09-21 0.3, 09-22 0.3, 09-23 0.2, 09-24 0.2, 09-25 0.1, 09-26 0.1, 09-27 0.1, 09-28 0.1, 09-29 0.1, 09-30 0.1, 10-01 0.1, 10-02 0.0

## Hacker News

- Show HN: Bough, the agent I built to replace Claude Code at work — 10 points, 5 comments: https://news.ycombinator.com/item?id=49711939

---

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 2026-10-02 13:20 UTC, updated every 30 minutes.