# charmbracelet/crush

Glamourous agentic coding for all 💘

Repository: https://github.com/charmbracelet/crush
Canonical: https://ross.abutalabs.com/products/crush
Language: Go
License: NOASSERTION
License Family: other
Topics: agentic-ai, ai, llms, ravishing
Last push: 2026-08-26T19:39:13+00:00

## Health v2 (maintenance only)
Score: 82/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 33
- inputs: {"age_days": 469, "days_push": 7, "days_rel": 7, "gap_med": 1.0, "n_releases_24m": 181}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 27713, forks 2188 (observed 2026-08-28T04:11:47.979833+00:00)

## What it is
Crush is a terminal-based agentic coding assistant from Charm that wires your codebase, tools, and workflows into the LLM of your choice. It supports multiple models, session-based context, LSP integration, and extensibility via MCP servers.

## Use cases
- ai coding assistant in the terminal
- refactor code with an llm agent
- chat with an ai about my codebase
- switch between llm providers while coding
- extend a coding agent with mcp tools
- run an ai pair programmer on windows or bsd

## When to choose
- you want an open-source terminal coding agent with multi-model support
- you need LSP-enhanced context and MCP extensibility
- you work across many platforms including BSD and Android terminals

## When to avoid
- you prefer a GUI-based AI IDE like Cursor
- you need a fully self-hosted local model workflow without API keys
- you dislike terminal-based interfaces

## Facets
- artifact type: cli-tool
- maturity: active
- function: agent-framework, llm-inference, cli, developer-tools, mcp
- domain: developer-tools, large-language-models
- platform: cli, windows, cross-platform, bsd
- tags: agentic-coding, terminal-ui, charm, coding-assistant, lsp, multi-model, command-line, ai-agents, macos, linux, android

## Member repositories
- charmbracelet/crush (main) score 82

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:47.979833+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:54:29.766666+00:00, confidence not recorded.
  - readme: https://github.com/charmbracelet/crush (fetched 2026-08-28T04:11:47.979833+00:00, sha 625bda4cb942)
- Data as of 2026-08-30T08:39:29.467469+00:00.