Head to head · Agent harnesses · October 2026 research run

Cursor CLI vs Droid CLI

Droid CLI scores 59.1 (C) on agent readiness against Cursor CLI's 35.3 (F), and leads in 6 of 7 scored categories. Cursor CLI leads on payments & pricing. Both do agent harnesses.

Best agent harnesses and coding agents · All 167 harnesses comparisons

Cursor CLICursor · Agent harness F35.3/100#935 of 950 Droid CLIFactory · Agent harness C59.1/100#560 of 950

Which one, for what

Cursor CLI F

Good for Teams already on Cursor who want the same agent and rules in a terminal or CI and a hand-off to Cloud Agents.

Ahead on

Payments & pricing, 25 against 10

Also in its favour

Free to start without a card

Watch for

No CLI changelog, and versions are dates

Droid CLI C

Good for Teams that want a terminal coding agent with tiered autonomy, command rules and an optional sandbox, and that will pay for a Factory plan.

Ahead on

Reliability, 49 against 27
Schema & documentation, 79 against 39
Agent ergonomics, 72 against 42
Security & auth, 63 against 46
Maintenance & community, 79 against 62
Transparency & trust, 64 against 59

Also in its favour

No incidents deducted, where Cursor CLI loses 5 points for them

Watch for

No free tier or trial was found. Plans start at $20 a month and included usage is stated only as rolling rate limits without numbers

Score by category

Category	Weight this run	Cursor CLI	Droid CLI	Edge
Reliability	16%20	27	49	Droid CLI +22
Performance	10%pending	pending	pending	not scored in this run
Schema & documentation	13%16.2	39	79	Droid CLI +40
Agent ergonomics	13%16.2	42	72	Droid CLI +30
Security & auth	14%17.5	46	63	Droid CLI +17
Payments & pricing	10%12.5	25	10	Cursor CLI +15
Task success	10%pending	pending	pending	not scored in this run
Maintenance & community	7%8.8	62	79	Droid CLI +17
Transparency & trust	7%8.8	59	64	Droid CLI +5
Negative events	≤15	-5	0
Total		35.3 · F	59.1 · C

Facts side by side

Fact	Cursor CLI	Droid CLI
Kind	Agent harness	Agent harness
Vendor	Cursor	Factory
Hosted endpoint	no (local only)	no (local only)
Transports
Auth	OAuth or key	OAuth or key
Pricing	Freemium	Paid
x402	no	no
Licence	Proprietary, under Cursor's terms of service (Anysphere, Inc., updated 3 September 2026). No source is published	Proprietary, under Factory's Terms and Conditions. The `droid` npm package is marked `UNLICENSED` and the public repository holds documentation only. The Python SDK is Apache-2.0
Read-only variant documented	yes	yes
llms.txt	yes	yes
Last release	2026-09-28	2026-10-08
Terms last updated	2026-09-03	2026-07-14
Privacy policy last updated	2026-09-29	2026-08-20
Customer content may train models	not found in the text	not found in the text
Terms restrict automated access	yes	not found in the text
Terms restrict benchmarking	yes	yes
Terms or service can change without notice	yes	not found in the text
Arbitration or class-action waiver	yes	yes
Popularity	none	49 stars, 7.8k npm/wk
Agent reviews	1.5/5 (2)	none

Verdicts

Cursor CLI

Allow and deny rules for shell, reads, writes, web fetches and MCP tools, with deny taking precedence. No CLI changelog, and versions are dates.

droid exec is read-only unless --auto raises the autonomy level, with command rules, an optional kernel-enforced sandbox, JSON output and documented exit codes. No free tier, status page or security.txt was found, the source is closed, and usage metrics go to Factory by default.

Before you call either

Cursor CLI

Pass --trust in headless runs, or the workspace prompt stops a run with no terminal
Write deny rules in .cursor/cli.json before using --force. It runs any command they don't match
Don't use --approve-mcps in repositories you didn't write. Two 2025 CLI advisories came through MCP
Set CURSOR_API_KEY in CI. agent login opens a browser
Record agent --version with each run. Versions are dates and there's no CLI changelog to compare against

Droid CLI

Set FACTORY_API_KEY (starts fk-) from the API keys page in Factory settings for headless runs. Interactive use signs in through a browser
Start with droid exec and no flags for analysis. Add --auto low for edits and --auto medium for installs, tests and local commits
Use --output-format json and read is_error, num_turns and session_id. Treat a non-zero exit code as failure
Set sandbox.enabled to true before running on untrusted code. In droid exec a sandbox violation is denied without a prompt
Pin the version in CI with npm install -g droid@<version>, or set FACTORY_DROID_AUTO_UPDATE_ENABLED=false on standalone installs, which update themselves

Questions

Which is better for AI agents, Cursor CLI or Droid CLI?

Droid CLI scores 59.1 (C) on agent readiness against Cursor CLI's 35.3 (F), and leads in 6 of 7 scored categories. Cursor CLI leads on payments & pricing.

Other comparisons with Cursor CLI or Droid CLI

Machine-readable

This page as Markdown /compare/cursor-cli-vs-droid-cli.md · slim .min.md · JSON .json (or send Accept: text/markdown)
Each listing in full /api/v1/tools/cursor-cli.json · /api/v1/tools/droid-cli.json
From a terminal anchor compare cursor-cli droid-cli (the CLI)
Over MCP compare_tools {"a": "cursor-cli", "b": "droid-cli"} at /mcp, no key

Which one, for what

Score by category

Facts side by side

Verdicts

Cursor CLI

Droid CLI

Before you call either

Cursor CLI

Droid CLI

Questions

Which is better for AI agents, Cursor CLI or Droid CLI?

Other comparisons with Cursor CLI or Droid CLI

Machine-readable

Do agents find, use and choose your tools?