| Type | Open source | Open source | Open source |
|---|
| Categories | | | |
|---|
| In one line | Anthropic's agentic coding tool for the terminal, IDE and GitHub. | OpenAI's terminal coding agent. | The open source coding agent — terminal-first, model-agnostic. |
|---|
| Stage & funding | — | — | — |
|---|
| GitHub starsDiffers | ≈154k | ≈131k | ≈223k |
|---|
| LicenseDiffers | Proprietary (Anthropic Commercial Terms) | Apache-2.0 | MIT |
|---|
| LanguageDiffers | TypeScript | Rust | TypeScript |
|---|
| Last pushDiffers | — | Oct 28, 2026 | Oct 28, 2026 |
|---|
| Works with | — | — | — |
|---|
| Built onDiffers | — | — | |
|---|
| Built on itDiffers | | | — |
|---|
| Similar toDiffers | — | | |
|---|
| People linkedDiffers | 3 | 2 | 4 |
|---|
| EventsDiffers | | | 0 |
|---|
| Pros | - +User reportsUsers widely see it as the strongest overall agent with Opus-class models, and strong with skills, hooks and LSPs.[1][2]
- +User reportsRich built-in harness features (subagents, skills, hooks, plugins, headless mode) that other tools can call into.[1][2]
- +User reportsUsers report the flat Max subscription covers far more usage than the same work would cost at API prices.[1][2]
- +MetadataVery fast release cadence (v2.1.312 on Oct 27, 2026).[1]
| - +DocsApache-2.0 open-source CLI that sandboxes by default (workspace-write, using Seatbelt on macOS, bubblewrap on Linux and a native Windows sandbox).[1][2]
- +DocsIncluded in every ChatGPT plan from Free to Enterprise, and Pro currently has no five-hour limit (weekly limits may still apply).[1]
- +User reportsUsers who switched from Claude report comparable coding quality, better value and faster responses on Plus.[1][2]
- +MetadataVery fast release cadence (rust-v0.165.0 on Oct 27, 2026; about 132k stars).[1]
| - +User reportsWorks with any provider or model, with LSP integration and configurable subagents that can each use a different model.[1][2]
- +User reportsUsers measure its prompt overhead as much leaner than Claude Code's (about 7k vs 33k tokens), and it has a plugin ecosystem.[1][2]
- +User reportsA popular fallback and local-model harness when subscription limits run out; 2.0 added background tasks.[1][2]
- +MetadataMIT-licensed, about 223k stars, with near-daily releases (v1.19.5 on Oct 28, 2026).[1]
|
|---|
| Cons | - −User reportsUsage caps and quota changes are a recurring complaint, and people fall back to Codex or OpenCode.[1][2]
- −User reportsUsers measure heavy base context: about 33k tokens before your prompt vs about 7k for OpenCode.[1][2]
- −MetadataSubscriptions can't be used in third-party harnesses, and the CLI has no OSI open-source license; use falls under Anthropic's commercial terms.[1][2]
- −MetadataAbout 16k open GitHub issues and PRs, plus trust worries after the March 2026 source leak.[1][2]
| - −User reportsUsage limits are opaque and shifting; some users hit the five-hour cap on the $20 plan during a basic task.[1][2]
- −User reportsHeavy default context: a Pi user says Codex loads close to 20k tokens of "cruft" before your first message.[1]
- −MetadataAbout 25k open GitHub issues and PRs, and critics point to a bloated Rust dependency tree (109 duplicate transitive deps; 75-minute release builds on a laptop).[1][2][3]
- −User reportsUsers report quality and usage swings after model launches.[1][2]
| - −User reportsIn October 2026 the OpenCode team disclosed unauthorized access to a legacy system that may have exposed BYOK provider keys saved in hosted workspaces.[1][2]
- −User reportsUsers question its security posture: no built-in sandbox, and title generation sent prompts through the Zen gateway by default.[1][2]
- −User reportsUsers say 2.0 moved tool calls into a background process, which silently broke their sandbox wrappers, and that RAM use is high.[1][2]
- −MetadataThousands of open issues and PRs, and some users get better results from other harnesses with the same model.[1][2]
|
|---|
| Best for | Developers who want the most capable out-of-the-box coding agent with Claude models and a deep extension surface. | ChatGPT subscribers who want an open-source, sandboxed-by-default coding agent bundled with their plan. | Developers who want a model-agnostic terminal agent with low prompt overhead and per-subagent model choice. |
|---|
| Watch out for | You are locked to Anthropic's quotas and terms; plan for usage caps and measure the context overhead. | Plan for opaque, changing usage quotas, and trim the default context if token efficiency matters. | Run it inside your own sandbox and set your own small model for auxiliary calls, so prompts don't leave your machine by default. |
|---|
| Links | | | |
|---|