Preview. These maps are our reading of public sources and haven't been checked with the projects' maintainers yet.
Claude Code
Anthropic's agentic coding tool: terminal CLI first, plus VS Code/JetBrains extensions, a desktop app, and cloud sessions on the web that return branches/PRs. Claude models only.
code.claude.com/Active
Release v2.1.310 on 2026-10-23; anthropics/claude-code pushed 2026-10-24 (gh api). (checked 2026-10-25)
In Coding agents
Where it stands apart
- Whose models can you use? Pick the first that applies. one model vendor's models only (5% of 21 others)
What it shares with most of the community
- Is it actively maintained? active (71% of 21 others)
- How is it mainly sustained? company with a paid product, tier, or ads (71% of 21 others)
- Who is it for? developers (95% of 21 others)
- Where do the commands it runs execute by default? on your machine with your user's permissions (86% of 21 others)
- Can users add their own tools through MCP (Model Context Protocol) servers? yes (95% of 21 others)
- Does it read project instructions from AGENTS.md? yes, alongside its own file (52% of 21 others)
Nearest neighbors
- Amp 82% of 17 shared answers match
- Cursor 71% of 17 shared answers match
- GitHub Copilot 71% of 17 shared answers match
Every answer
| Question | Answer | Source |
|---|---|---|
| Is it actively maintained? | active | source 2026-10-25 |
| How is the main thing licensed? | proprietary or closed source '© Anthropic PBC. All rights reserved.' The GitHub repo is for issues/plugins, not source. | source 2026-10-25 |
| How is it mainly sustained? | company with a paid product, tier, or ads Paid via Claude Pro/Max/Team/Enterprise subscriptions or Console API billing. | source 2026-10-25 |
| Can it run entirely on your own device or infrastructure, without the maker's servers? | partly (some features need the maker's servers) Agent runs locally; models are hosted by Anthropic or a cloud provider (Bedrock, Vertex, Foundry). | source 2026-10-25 |
| Do you need an account to use it? | account required Prompts login with Claude or Console account (or cloud provider). | source 2026-10-26 |
| Who is it for? | developers | source 2026-10-25 |
| Which shared standard or format does it mainly build on? | MCP (Model Context Protocol) Anthropic created MCP and it is its extension mechanism; CLAUDE.md (its own) beats AGENTS.md. | source 2026-10-26 |
| Where do you primarily use it? | terminal (CLI or TUI) Also VS Code, JetBrains, desktop app and web; CLI is the full-featured core. | source 2026-10-25 |
| How does finished work usually come back to you? | both are first-class Local sessions edit your tree; web/cloud sessions (claude --cloud, claude.ai/code) push branches and PRs; teleport moves between them. | source 2026-10-25 |
| Whose models can you use? Pick the first that applies. | stands apart one model vendor's models only Claude models via Anthropic, Bedrock, Google Agent Platform, Microsoft Foundry, or an LLM gateway. | source 2026-10-25 |
| Is pointing it at a model running on your own machine (e.g. Ollama, LM Studio) a documented setup? | no No documented local-model setup in Anthropic's docs; community proxies exist. | source 2026-10-25 |
| Out of the box, does it ask you before editing files or running shell commands? | doesn't ask (a sandbox or automatic reviewer may still block risky actions) Since v2.1.283, interactive terminal and VS Code sessions start in 'auto' mode: a classifier reviews actions instead of the user. 'default' (Manual) mode asks before edits and commands and is still the default for claude -p and the SDK. | source 2026-10-25 |
| Where do the commands it runs execute by default? | on your machine with your user's permissions 'The sandbox is off by default.' Opt-in OS sandbox via /sandbox; cloud sessions run in Anthropic VMs. | source 2026-10-25 |
| Can users add their own tools through MCP (Model Context Protocol) servers? | yes | source 2026-10-25 |
| Does it read project instructions from AGENTS.md? | yes, alongside its own file Reads AGENTS.md only when no CLAUDE.md exists (v2.1.277+), or via import/setting; CLAUDE.md remains primary. | source 2026-10-25 |
| Does it use the Agent Client Protocol (ACP) for agent-editor connections? | no No native ACP; an adapter (claude-agent-acp, built on the Agent SDK) lets ACP editors drive it. | source 2026-10-25 |
| When you first set it up, how do you pay for the models it uses by default? | a subscription plan from the tool's maker Pro/Max/Team/Enterprise subscription is the default login; API-key billing is the alternative. | source 2026-10-25 |
Sources
This page was derived from:
- GitHub · github.com/agentclientprotocol/claude-agent-acp · read 2026-10-25
- GitHub · github.com/anthropics/claude-code/blob/main/LICENSE.md · read 2026-10-25
- GitHub · github.com/anthropics/claude-code/releases · read 2026-10-25
- Web page · code.claude.com/ · read 2026-10-25
- Web page · code.claude.com/docs/en/iam · read 2026-10-25
- Web page · code.claude.com/docs/en/llm-gateway · read 2026-10-25
- Web page · code.claude.com/docs/en/memory · read 2026-10-25
- Web page · code.claude.com/docs/en/overview · read 2026-10-25
- Web page · code.claude.com/docs/en/permission-modes · read 2026-10-25
- Web page · code.claude.com/docs/en/sandboxing · read 2026-10-25
Are you a maintainer? Claiming and correcting projects is coming soon.