# charmbracelet/crush

> Terminal-based agentic coding tool that wires your tools, code, and workflows into the LLM of your choice. Supports multiple models, sessions, LSP context, and MCP extensions.

- Magnitude: 2.2 out of 10 — Steady
- Stars: 28,856 total · +4 stars measured 2026-10-29, 00:08–04:21 UTC, ≈ 20 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: Go · Created: 2025-05-21 · Last push: 2026-10-29
- GitHub: https://github.com/charmbracelet/crush · Page: https://gitnova.dev/en/r/charmbracelet/crush

## Useful for

- Run the agent in a terminal to edit and refactor code in a project
- Switch LLMs mid-session while preserving conversation context
- Connect MCP servers to extend the agent's capabilities

## Why it’s here

- Star-counter measurements on 2026-10-29 (UTC), 00:08–04:21: 28852 → 28856 stars (+4). This is the change over that interval.
- Estimated end-of-day forecast: about +20 stars, using observed gains and the previous day.
- Recent forks include notable developers: @moul (1,656 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: 2,334
- Issues and pull requests: 3,844
- Watchers: 138
- Average over the last week: 20 per day
- Usual pace: 21 per day
- Stars in the last hour (measured): 1
- Latest release: nightly (2026-10-29)

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

2026-09-30 … 2026-10-29: 50, 28, 24, 20, 14, 13, 22, 20, 21, 28, 14, 16, 19, 21, 22, 29, 10, 18, 13, 24, 19, 25, 19, 26, 21, 21, 20, 17, 19, 4

## Magnitude by day, last 14 days

10-04 1.8, 10-05 1.6, 10-06 1.7, 10-07 2.2, 10-08 2.2, 10-09 2.5, 10-10 2.6, 10-11 2.2, 10-12 2.5, 10-25 2.0, 10-26 2.3, 10-27 2.2, 10-28 2.2, 10-29 2.2

## Similar by description

1. **CodebuffAI/freebuff** — 1.9 · Steady · AI agents · TypeScript · +3 stars measured 2026-10-29, 00:07–04:22 UTC, ≈ 17 by evening
   Freebuff is a free coding agent suite (CLI, desktop, web, cloud, chat) that runs specialized agents with a choice of models to edit code, build apps, and research. It targets developers who want agentic coding without subscriptions or API…
   Full card: https://gitnova.dev/en/r/CodebuffAI/freebuff.md
2. **aaif-goose/goose** — 2.4 · Steady · AI agents · Rust · +4 stars measured 2026-10-29, 00:06–04:20 UTC, ≈ 30 by evening
   An open source, extensible AI agent that runs locally: desktop app, CLI, and API built in Rust. Supports 15+ LLM providers and 70+ MCP extensions for code, automation, and data analysis.
   Full card: https://gitnova.dev/en/r/aaif-goose/goose.md
3. **sourcepro5/WeChatAgent** — 2.1 · Cooling · AI agents · JavaScript · +12 stars measured 2026-10-29, 00:07–04:21 UTC, ≈ 64 by evening · unusual star pattern (heuristic)
   A Windows app that turns WeChat into an AI chat companion with persona dialogues and separate context per friend/group, plus a remote entry point for tasks via DSH.
   Full card: https://gitnova.dev/en/r/sourcepro5/WeChatAgent.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 2026-10-29 04:27 UTC, updated every 30 minutes.