Crush

byCharmlisted Nov 16, 2026

Coding AgentsFreeEasy setupAny model (BYO key), incl. Anthropic, OpenAI, Gemini, OpenRouter, Charm Hyper, any OpenAI- or Anthropic-compatible API

Terminal coding agent from Charm that wires your tools, code, and workflows into a chosen LLM. It supports multiple sessions per project, switching models mid-session, LSP context, and MCP servers over http, stdio, and sse. It runs in terminals on macOS, Linux, Windows, Android, and the BSDs.

Freshness note: AI-agent behavior can change after model releases, client updates, pricing changes, or new default settings. Use the aggregate score as a historical baseline and check recent reviews plus model/runtime context before deciding.

Pricing
Free to use; source-available under FSL-1.1-MIT, which converts to MIT after two years. Bring your own API keys; model usage is billed separately. Charm's optional Hyper model provider has subscription and prepaid options (prices not verified).
Model backbone
Any model (BYO key), incl. Anthropic, OpenAI, Gemini, OpenRouter, Charm Hyper, any OpenAI- or Anthropic-compatible API
Setup complexity
Easy setup
Last reviewed
Awaiting reviews
Recent signal
Awaiting reviews
Evidence sources: No published editorial evaluation is available yet. Editorial evaluations are Ruling research, not community testimonials, and do not contribute to the community score.

Build Crush? Get a claim link →

What reviewers consistently say.

No reviewer patterns for Crush yet.

No consensus yet

Once people review Crush, Ruling will summarize recurring strengths and limitations here.

Write the first review

No community reviews yet.

Used Crush? Your field report can seed the first Ruling signal.

Be the first to review Crush

Share where it worked, where it failed, and whether it deserves a spot in a real team workflow.

Write a review
Write a review