| TypeDiffers | Open source | Startup | Open source |
|---|
| Categories | | | |
|---|
| In one line | Anthropic's agentic coding tool for the terminal, IDE and GitHub. | Droids: AI workers for software teams. | AI pair programming in your terminal. |
|---|
| Stage & funding | — | — | — |
|---|
| GitHub starsDiffers | ≈154k | — | ≈50k |
|---|
| LicenseDiffers | Proprietary (Anthropic Commercial Terms) | — | Apache-2.0 |
|---|
| LanguageDiffers | TypeScript | — | Python |
|---|
| Last pushDiffers | — | — | May 22, 2026 |
|---|
| Works with | — | — | — |
|---|
| Built onDiffers | — | — | |
|---|
| Built on itDiffers | | — | — |
|---|
| Similar toDiffers | — | — | |
|---|
| People linkedDiffers | 3 | 2 | 1 |
|---|
| 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]
| - +DocsFactory's Droid agent posted a leading 58.75% on Terminal-Bench when Factory published the result.[1]
- +DocsThe $20/month Pro plan bundles the Factory app, Droid CLI, Droid SDK, local and cloud background agents and Managed Droid Computers.[1]
- +DocsBYOK is free up to an allowance on all individual plans, and a free pool of open-weight models (Droid Core) stays available after standard usage runs out.[1]
- +DocsExtra-usage credits are prepaid with a $10 minimum and never expire.[1]
| - +User reportsCredited by users as the tool that defined terminal coding agents, with plan-style modes before Claude Code.[1][2][3]
- +User reportsUsers praise architect mode, where a pricier model plans and a cheaper one edits, as cost-effective.[1][2][3]
- +User reportsWorks with many models, including local ones via Ollama, and can be scripted.[1][2]
- +MetadataApache-2.0 and git-native: it commits its changes, so they are easy to review and revert.[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]
| - −DocsThree independent rolling rate-limit windows (5-hour, 7-day and 30-day) govern usage, and Missions require Extra Usage and pause when they hit a limit.[1]
- −Independent testPricing has changed sharply, from $80/user token-metered tiers in early 2025 to rate-limited seats starting at $20, which makes long-term cost planning harder.[1]
- −Independent testBenchmark standing depends on the underlying model: one comparison lists Droid at 58.8% with Opus 4.1 and 52.5% with GPT-5 (medium).[1]
- −MetadataThe agent is proprietary, unlike open-source CLIs such as Aider or OpenCode, so you cannot self-host or audit it.[1]
| - −User reportsLess autonomous: users note it lacked an automatic write-run-fix loop and defaulted to limited multi-turn recursion.[1][2]
- −User reportsSome users find it feels like chat in a terminal, with nagging prompts and 'too much busywork'.[1][2]
- −MetadataDevelopment has slowed: the last release was v0.86.0 (Aug 2025), the last push was May 2026, and 1,408 issues are open. Users report moving to newer harnesses.[1][2][3]
- −User reportsUsers report quality dropping in long conversations and heavy token use (2M tokens a day for one user).[1][2]
|
|---|
| Best for | Developers who want the most capable out-of-the-box coding agent with Claude models and a deep extension surface. | Engineering teams that want one model-agnostic coding agent across CLI, IDE and background cloud runs. | Developers who want a controlled, git-native pair programmer with explicit file context and any model. |
|---|
| Watch out for | You are locked to Anthropic's quotas and terms; plan for usage caps and measure the context overhead. | Long Missions can hit the rolling rate limits and run up Extra Usage charges. | Slowing development and a less agentic loop than current harnesses. |
|---|
| Links | | | |
|---|