Charm Crush

https://github.com/charmbracelet/crush

Charm Bracelet's terminal-native AI coding assistant — built in Go atop the Bubble Tea TUI framework. Multi-model via Glamour/Mods integration. Open-sourced 2025; positioned as a TUI-native alternative to web/Electron harnesses for developers who live in the terminal.

At a glance

Type
Terminal-native AI coding agent (Charm; TUI)
Tier
T3
Created
2025
Latest release
crush 0.x rolling
License
MIT
GitHub
~7k★, Go
Pricing
Free (OSS)
Funding
Charm (independent OSS company, small)

Taxonomy

storage
file
retrieval
injection
persistence
cross-session
update
user-edit
unit
document
governance
inspectable
conflict
human-arbitrate

When to use

Optimised for: TUI-native coding agent in Go

Anti-fit: early-stage; smaller community than Aider/Claude Code

Pros & cons

Pros

Beautiful TUI by the team that defined modern terminal UI; Go single-binary distribution is friction-free.

Cons

Early-stage feature surface; lacks the MCP/extension richness of Claude Code or Cline; small contributor base.

Claims & capabilities

Built by Charm (creators of Bubble Tea, Glamour); Go-native; TUI-first; ~7k★ in first year.

Technical surface

API surface
CLI (Go) — TUI
Backend storage
local config
Deployment
Self-host (Go install)
Embedding model
not applicable — not a memory product
Multi-tenancy
single-user
MCP
searched not found
A2A
searched not found
OpenTelemetry
searched not found

Similar systems

Other agent ides & coding harnesses in the catalog, ranked by inbound references.

  • Bedrock AgentCore (AWS) T2

    AWS Bedrock AgentCore — managed runtime to deploy + scale + observe agents. Multi-component: Runtime, Identity, Memory, Gateway, Browser, Code Interpreter, Observability. Distinct from Bedrock Agents (older fixed-config product); AgentCore is the 2025 framework-agnostic runtime for any agent (LangGraph, CrewAI, Strands, OpenAI Agents SDK).

  • Claude Code (Anthropic) T1

    Anthropic's official agentic coding CLI — runs Claude as a long-running coding agent in the developer's terminal. Memory layer = CLAUDE.md (project + user scoped), agent skills, MCP servers. Released GA October 2024; widely adopted as the reference harness for Claude-as-coder. Plan Mode and Compute Use surfaces extend it from coding to broader desktop automation.

  • GitHub Copilot (Agent Mode) T1

    The original AI coding assistant (Copilot in editor; 2021). 2025 evolved into a full agentic surface: chat, completions, Agent Mode (multi-step), and Copilot Workspace. Backed by Microsoft. Distinct row from Workspace — this row covers the everyday in-editor + agent mode product, Workspace covers the hosted spec-driven workflow.

  • Aider (harness) T2

    OSS terminal coding agent by Paul Gauthier — one of the original AI-pair-programmer CLIs (2023). Architect/Editor modes; repo-map for context; uses any LiteLLM-compatible model. Memory via CONVENTIONS.md and .aider.conf.yml — author-edited markdown. Distinct from the separate Aider memory-row in "Coding-agent memory"; this row characterises the harness itself.

  • Amazon Q Developer T1

    Amazon's developer-focused agent — formerly CodeWhisperer (renamed 2024-Q4). Available as IDE plugins (VS Code, JetBrains, Visual Studio, Eclipse), in AWS Console, and CLI. Strong AWS-tooling integration: Q can read CloudWatch, troubleshoot IAM, suggest AWS-SDK code. Companion to Kiro for spec-driven flows.

  • Anthropic Computer Use T1

    Anthropic's API-surface capability that lets Claude control a virtual desktop — see screenshots, type, click. Launched 2024-10 as a public beta. Not a finished IDE itself; it's the substrate that other harnesses (and Anthropic's own Claude apps) use to operate a computer.

Row last verified 2026-05-14. Catalog data is CC-BY-4.0 — see how to read this.