How much does Charm cost?

Crush is free to install and source available under FSL-1.1-MIT, with developers bringing their own model provider API keys, so the running cost is the token usage they pay their chosen provider. Charm's optional Hyper inference service is free with 100 monthly credits or $20 a month for 250 daily refreshing credits, with prepaid bundles from $5 and zero data retention. No enterprise pricing for Crush is published.

What are the best alternatives to Charm?

Based on documented capability coverage across the Agentic Index 14 point taxonomy, the closest alternatives to Charm among coding agents are OpenCode, Poolside, Ellipsis, JetBrains AI. Each is graded on the same public evidence, and no vendor pays for placement.

Does Charm support MCP and tool calling?

Full under the Agentic Index verification standard. Charm publishes public evidence of Model Context Protocol (MCP) support, tool calling, and API or SDK extensibility for connecting agents to external tools. Evidence basis: Fantasy, the Go agent framework Charm built to power Crush, is a library with a multi provider API and custom tools. Crush can be driven from scripts through crush run with stdin and stdout, and extended with Agent Skills. MCP support lets. Graded from public evidence only against the Agentic Index 14 point capability taxonomy. No vendor pays for placement.

Can Charm be self hosted or run in a private VPC?

Full under the Agentic Index verification standard. Charm publishes public evidence of self hosted or private VPC deployment, along with data residency options for controlling where agent data is processed and stored. Evidence basis: Code stays on the developer's machine because Crush runs locally in the terminal. It works air gapped once provider auto update is switched off and providers are updated manually, and can use local models through Ollama or LM Studio. github. Graded from public evidence only against the Agentic Index 14 point capability taxonomy. No vendor pays for placement.

Does Charm give you tracing and observability into agent runs?

Full under the Agentic Index verification standard. Charm publishes public evidence of tracing, observability and audit logging into agent runs, so a team can see what an agent did and why. Evidence basis: Crush writes a per project JSON log with timestamps and session IDs that records each tool call, such as a bash command, and each prompt sent and response received. The log can be viewed with crush logs, tailed or followed live, and debug m. Graded from public evidence only against the Agentic Index 14 point capability taxonomy. No vendor pays for placement.

Back to vendors

Charm

Q: Who is Charm for?

Developers and engineering teams, Terminal first developers, Teams wanting model provider optionality

Also known as: Charm, Charmbracelet, Charm (charmbracelet), Charmbracelet, Inc., Crush, charm.land, Charm Hyper, Catwalk, Fantasy

Visit site

Coding agentindependentVerified 2026-09-29

Entry priceFree (source available); bring your own model keysFull pricing detail

Terminal native AI coding agent from Charm with a broad choice of model providers, mid session model switching that keeps context, language server code intelligence, MCP and Agent Skills extensibility, and permission prompts before tool calls, running locally including air gapped.

Charm, the company behind the charmbracelet open source ecosystem, makes the command line glamorous with a suite of Go based terminal libraries and tools. Its flagship agentic product is Crush, a terminal native AI coding agent that connects to large language models and gives them tools to read, write, and execute code directly in the terminal.

Crush offers broad model provider flexibility, letting developers choose among Anthropic, OpenAI, Gemini, Bedrock, Copilot, Vertex, Groq, and local models and switch mid session, with a Catwalk provider database that keeps model metadata current. It pulls in code intelligence through Language Server Protocols, reads project context files, persists sessions and history in SQLite, extends through Model Context Protocol servers and agent skills, and gives teams fine grained control over permissions and repo local configuration. Because it runs locally in the terminal it supports air gapped and local model workflows, and it works across macOS, Linux, Windows, and the BSDs.

Vendor details

Canonical URL

https://charm.land

Subcategory

Terminal-native coding agent (BYOK, multi-provider)

Funding status

Seed stage, based in New York, founded by Christian Rocha; the round amount is not stated. Charm is the company behind a widely adopted open-source terminal tooling ecosystem including Bubble Tea, Lip Gloss, Glow and Gum, with the vendor stating the Charm ecosystem powers more than 25,000 applications. Crush itself has roughly 25,000 GitHub stars and 1,800 forks since the repository was created in May 2025, with daily commits as of mid-2026. Charm now also operates Hyper, a subscription model provider with a free tier, which is its first documented commercial product line.

Company status

independent

Use cases & customers

Primary use cases

Terminal native agentic codingCodebase analysis and refactoringModel provider experimentationAir gapped and local model coding workflows

Target customers

Developers and engineering teamsTerminal first developersTeams wanting model provider optionality

Deployment options

Local (terminal, runs on your machine)Air gappedSelf-hosted local models

Integrations

Crush connects to LLM providers (Anthropic, OpenAI, Gemini, Bedrock, Copilot, Vertex, Groq, and local models), uses Language Server Protocols for code intelligence, extends via Model Context Protocol servers over stdio, http, and sse, and can call local tools like git, docker, and npm.

In practice

You want a coding agent in your terminal that keeps your code on your own machine. Crush runs locally, works with local models through Ollama or LM Studio, and can run air gapped once provider auto update is switched off.

You want an AI review on every pull request without anyone starting it. Crush's non interactive crush run mode fits into CI, and a published GitHub Actions workflow runs it on each pull request to review the diff.

You want to move between Anthropic, OpenAI and a local model without losing your place. Crush lets you pick from 17 providers or your own compatible endpoint, and switch models mid session while keeping the conversation.

Sources & related URLs

Related / legacy domains

https://charmbracelet-crush.mintlify.app/ https://github.com/charmbracelet/crush https://charm.land/blog/crush-comes-home/ https://github.com/charmbracelet https://charm.land/discord

Research sources

https://charm.land/ https://charmbracelet-crush.mintlify.app/ https://github.com/charmbracelet/crush https://charm.land/blog/crush-comes-home/

Agentic Index coverage score

10.0 / 14 capabilities · 71%

Integrations & Tool Calling	Full
Crush connects to MCP servers over stdio, HTTP and SSE, uses language servers for diagnostics and references, fetches web pages, and runs the developer's own toolchain through its bash tool, alongside built in tools to view, grep, glob, edit and write files. SourceCrush docs (configuration/mcp, tools overview) and github.com/charmbracelet/crushread 2026-09-29
Workflow Orchestration	Partial
One agent works through a loop of file, search, language server and shell tools, with several sessions per project and models switchable mid session. There are no subagents, handoffs, branching or coordination across agents. SourceCrush docs (tools overview, sessions) and github.com/charmbracelet/crushread 2026-09-29
Knowledge Grounding & RAG	Partial
Context is assembled per run from the repository through view, grep and glob tools, language server diagnostics and references, and project context files such as AGENTS.md and CRUSH.md. There is no index, graph or embeddings layer that persists and can be queried. SourceCrush docs (context files, tools) and github.com/charmbracelet/crushread 2026-09-29
Human Oversight & Guardrails	Full
Crush asks the developer for permission before it runs tool calls, including in non interactive runs, with an allow list for trusted tools and a --yolo flag that skips the prompts only when the developer chooses it. Sourcegithub.com/charmbracelet/crush and Crush docs (permissions, crush run)read 2026-09-29
Security, Identity & Governance	Partial
Provider keys are supplied locally on the developer's own machine, where Crush runs. Usage metrics can be switched off, and prompts and responses are never collected. Ignore files limit what Crush reads, and Charm's optional Hyper inference service offers zero data retention. No certification, single sign on, role based access or audit logging is offered. Sourcegithub.com/charmbracelet/crush, Crush docs (metrics and privacy) and hyper.charm.landread 2026-09-29
Observability & Auditability	Full
Crush writes a per project JSON log with timestamps and session IDs that records each tool call, such as a bash command, and each prompt sent and response received. The log can be viewed with crush logs, tailed or followed live, and debug mode adds language server traffic. Sessions and their history are kept in a local SQLite database. SourceCrush docs (logging, sessions) and github.com/charmbracelet/crushread 2026-09-29
Memory & State Persistence	Partial
Sessions persist across restarts in a per project SQLite database and can be reopened, but the model remembers only the current session, and no context carries from one session to another. Project context files are instructions the developer writes. Sourcegithub.com/charmbracelet/crushread 2026-09-29
Deployment & Data Residency	Full
Code stays on the developer's machine because Crush runs locally in the terminal. It works air gapped once provider auto update is switched off and providers are updated manually, and can use local models through Ollama or LM Studio. Sourcegithub.com/charmbracelet/crush and Crush docs (air gapped, local models)read 2026-09-29
Prebuilt Agents / Templates / Packs	Partial
Skills follow the open Agent Skills standard, with SKILL.md packages discovered from a skills directory. Crush ships no built in skills or catalog and points to Anthropic's public skills repository for examples, so customers assemble the skills themselves. Sourcegithub.com/charmbracelet/crushread 2026-09-29
Triggers & Channel Coverage	Full
The crush run command is a non interactive mode for scripts and CI/CD pipelines. A published GitHub Actions workflow runs it on every pull request to review the diff, so work reaches the agent without a person starting it. The interactive terminal is the other surface. Sourcegithub.com/charmbracelet/crushread 2026-09-29
Model Flexibility & Routing	Full
The developer picks the provider and model from 17 providers, including Anthropic, OpenAI, Google Gemini, AWS Bedrock, Azure, Groq, OpenRouter and Hugging Face, or uses custom OpenAI compatible or Anthropic compatible endpoints and local models. Models can be switched mid session while keeping the conversation. SourceCrush docs (configuration/providers) and github.com/charmbracelet/crushread 2026-09-29
APIs / SDKs / MCP Extensibility	Full
Fantasy, the Go agent framework Charm built to power Crush, is a library with a multi provider API and custom tools. Crush can be driven from scripts through crush run with stdin and stdout, and extended with Agent Skills. MCP support lets Crush reach other systems. Sourcegithub.com/charmbracelet/fantasy and Crush docs (cli/run)read 2026-09-29
Testing, Debugging & Optimization	Partial
The agent runs project commands and tests through its bash tool and reads language server diagnostics, and debug logging exposes agent and language server behavior. These check the customer's code and help troubleshoot a run, but there is no harness to evaluate or regression test the agent's own behavior. Sourcegithub.com/charmbracelet/crushread 2026-09-29
Browser / Computer-use	Not documented
Everything runs through file tools, shell commands, language servers, MCP servers and a fetch tool that retrieves pages. Crush does not control a browser or operate software through a graphical interface. Sourcegithub.com/charmbracelet/crushread 2026-09-29

The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded

Recent platform changes

2026-07-31·Security / enterpriseVerified

Charm released version 0.88.0 of the Crush terminal coding agent, introducing a scriptable configuration system via crush.sh and crushrc. The update adds explicit tool permissions, allowing users to apply "deny" rules to completely hide specific tools from the AI agent. The release also includes verb-first setup commands for managing MCP servers and LSPs, as well as auto-retry logic for AWS SSO logins.

Bears on: Security / enterprise

View source

2026-07-21·Human approval / guardrailsVerified

Charm released Crush v0.86.0, bringing a new interactive Question Tool to the terminal-based AI coding agent. This capability allows connected models to present developers with single-choice, multiple-choice, and free-form text prompts with mouse support. The release also implements new session-affinity headers to enable provider-side prompt caching.

Bears on: Human approval / guardrails

View source

View all 2 changes for Charm →Tracked since Jul 2026 · Verified from public vendor sources

Pricing

Free (source available); bring your own model keys

Crush itself is free; model usage is paid to the chosen provider, or in Hyper credits on Charm's own inference service.

Free tier

Cost watchouts

The tool is free, but running Crush means paying for model usage, through the developer's own provider or Hyper credits, which scales with how much coding work you drive through it.

Variable cost rationale

Because developers bring their own model keys, the effective cost is LLM token usage paid to the chosen provider, which scales directly with coding activity.

Sales call required

No, self serve available

Key ambiguities

Charm publishes no commercial or enterprise price for Crush itself; the only paid Charm offer is Hyper inference credits.

Agentic Index verified 2026-09-29

Official pricing page

Related vendors

Alternatives to Charm

The closest documented capability profiles to Charm among coding agents tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.

OpenCode10.0 / 14Fuller documented coverage on Workflow OrchestrationCharm vs OpenCode →
Poolside11.0 / 14Fuller documented coverage on Workflow Orchestration and Security, Identity & Governance
Ellipsis10.5 / 14Fuller documented coverage on Workflow Orchestration and Security, Identity & Governance
JetBrains AI10.5 / 14Fuller documented coverage on Workflow Orchestration and Prebuilt Agents, Templates & Packs
Tabnine11.5 / 14Fuller documented coverage on Workflow Orchestration and Knowledge Grounding & RAG
Augment Code12.0 / 14Fuller documented coverage on Workflow Orchestration and Knowledge Grounding & RAG

Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded

Compare Charm with other vendors →Compare all coding agents →See where Charm ranks →

Data confidence: high

Head to head

Charm vs OpenCode Charm vs Aider