# Droid CLI > Droid CLI is Factory's closed-source coding agent for the terminal. It runs interactively or headless through droid exec, connects MCP servers, runs multi-agent Missions, and can be driven by TypeScript and Python SDKs. A paid Factory plan is required. - Canonical: https://www.anchorterminal.com/tools/droid-cli - Markdown: https://www.anchorterminal.com/tools/droid-cli.md (~8,350 tokens) - Slim: https://www.anchorterminal.com/tools/droid-cli.min.md (~1,580 tokens, same facts, less prose, for token-sensitive contexts) - JSON: https://www.anchorterminal.com/tools/droid-cli.json (this page as data, same URL with Accept: application/json) - Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt) - API: https://www.anchorterminal.com/api/v1/index.json - Updated: 2026-10-09 ## Overview **Grade C · 59.1/100 · rank #560 of 950 · #13 in Agent harnesses · not agent-ready · confidence medium** ## Assessment `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. ## Facts | Field | Value | | --- | --- | | Vendor | Factory (https://factory.com) | | Kind | Agent harness | | Category | Agent harnesses (https://www.anchorterminal.com/categories/agent-harnesses) | | Auth | OAuth or key · A Factory account is required. The interactive CLI signs in through a browser with OAuth, and the docs say stored tokens rotate every 30 days. Headless runs set `FACTORY_API_KEY` to a key starting `fk-` created on the API keys page in Factory settings. Organisations can use service accounts whose keys can be rotated and revoked through an API. | | Pricing | Paid ($20 / mo) · Pro is $20 a month, Plus $100 and Max $200, each with the CLI, the Factory App and the SDK. Teams is $60 a month per team plus $40 a seat, and Business and Enterprise are by quote. Usage is capped by rolling 5-hour, 7-day and 30-day rate limits stated without numbers. Extra usage is prepaid credit from $10. No free tier or trial was found (checked 2026-10-09). | | x402 | No · No x402, MPP or L402 in the docs index, the pricing pages or the terms (checked 2026-10-09). | | Licence | 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 | | Packages | npm: `droid`; npm: `@factory/droid-sdk`; pypi: `droid-sdk` | | Source | https://github.com/Factory-AI/factory | | Docs | https://docs.factory.com/droid-cli/overview | | llms.txt | https://docs.factory.com/llms.txt | | Last release | 2026-10-08 | | GitHub stars | 49 (as of 2026-10-09) | | npm downloads / week | 7,766 | | Interfaces | Interactive terminal UI (`droid`), headless `droid exec`, JSON-RPC over stdin and stdout, TypeScript and Python SDKs, and Agent Client Protocol for editors | | Install | curl script for macOS and Linux with SHA-256 check, PowerShell for Windows, Homebrew cask, or the `droid` npm package (Node 20 or later) with prebuilt binaries for Linux, macOS and Windows on x64 and arm64 | | Autonomy | Off, Low, Medium and High. `droid exec` is read-only without `--auto`. Missions need High or `--skip-permissions-unsafe` | | Command policy | `permissionRules` with allow, ask and block decisions, checked with `droid rules check`. A block applies even under `--skip-permissions-unsafe` | | Sandbox | Off by default. Seatbelt on macOS, bubblewrap with seccomp on Linux and WSL2, and a filtering proxy for network. Modes `per-command` (default) and `whole-process` | | MCP client | `droid mcp add` for http, sse and stdio servers, OAuth with dynamic client registration, `disabledTools` per server, approvals bound to the server's command or URL, and an organisation allowlist | | Headless | `droid exec` with text, json, stream-json and stream-jsonrpc output, `--session-id`, `--fork`, `--worktree`, `--restrict-tools` and `--disabled-tools`. Exit codes 0, 1 and 2 | | Models | Factory-managed models chosen with `--model`, or custom models in `~/.factory/settings.json` with your own key and base URL | | Telemetry | OpenTelemetry metrics to Factory's collector by default and to your own collector when configured. Message content goes only to your own collector and only when switched on | | Updates | Standalone installs update themselves. The npm build has updates off. `droid update --version` selects or rolls back a version | | Capabilities | agent.harness, agent.mcp-client, agent.multi-agent | | Tags | harness, coding-agent, cli, closed-source, mcp, acp, llms-txt, sdk, sandbox, telemetry-default-on | | JSON | https://www.anchorterminal.com/api/v1/tools/droid-cli.json | ## Score breakdown (methodology v0.4, October 2026 research run) Assessed 2026-10-09 from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/#checklist). Confidence: medium. Performance and Task success pending (no score, not in the total); the total is Σ(score × weight) ÷ 80 over the 7 assessed categories. "This run" is each category's share of the 100 points. | Category | Weight | This run | Score (0–100) | Points | | --- | --- | --- | --- | --- | | Reliability | 16% | 20 | 49 | 9.8 | | Performance | 10% | pending | pending | n/a | | Schema & documentation | 13% | 16.2 | 79 | 12.8 | | Agent ergonomics | 13% | 16.2 | 72 | 11.7 | | Security & auth | 14% | 17.5 | 63 | 11.0 | | Payments & pricing | 10% | 12.5 | 10 | 1.2 | | Task success | 10% | pending | pending | n/a | | Maintenance & community | 7% | 8.8 | 79 | 6.9 | | Transparency & trust (editorial 55, provenance 72) | 7% | 8.8 | 64 | 5.6 | | Negative events | up to −15 | up to −15 | none recorded | 0 | | **Total** | | | | **59.1 → C** | ### Why each score - Reliability 49: Local-package reading, as for the other closed-source harnesses. An install script that verifies a SHA-256 checksum, a PowerShell installer, a Homebrew cask and the `droid` npm package (Node 20 or later) with prebuilt binaries for Linux, macOS and Windows on x64 and arm64 (20). The source is not published. The public repository holds documentation only, so there is no public CI or test suite for the CLI (0). Bugs are tracked in the open at Factory-AI/factory, a repository created on 29 July 2026. On 9 October 2026 it had 33 open issues that are not pull requests, most with no reply, and three closed in the previous week with replies. Runs depend on Factory's servers, and we found no status page (10). Every release has a dated, versioned changelog entry and deprecations get their own section, but the line is 0.x with a minor version almost daily, so the version number does not signal a breaking change (9). The version is 0.237.0. The Feature Maturity page says a feature with no tag is generally available and stable, and the CLI pages carry no tag in the Markdown we read. Judgement call (10). The 99 per cent availability target on factory.com/sla is not scored on this reading. - Performance: Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes. - Schema & documentation 79: Framework reading. The docs index links an OpenAPI file for the Factory public API, which we did not open, and the headless mode has a documented JSON-RPC surface with named methods. `droid exec --list-tools --output-format json` and `droid rules check --json` give machine-readable output. We found no published schema for the settings file (15). docs.factory.com/llms.txt lists a Markdown copy of every page (10). The overview says when to use the CLI, and the autonomy table says what each level allows, blocks and suits (16). Autonomy levels, output formats, sandbox modes and MCP server fields are enumerated with types and defaults (12). Examples on every page read, exit codes 0, 1 and 2, and a JSON result with `is_error` and `subtype`, with no error catalogue (11). A changelog by CLI version with dates and an RSS feed, 236 entries back to 30 September 2025 (15). - Agent ergonomics 72: Harness reading of the framework line. `--restrict-tools`, `--disabled-tools`, `--additional-tools` and `--list-tools` control built-in tools per run, and `disabledTools` in `mcp.json` keeps named MCP tools out of context. We found nothing on deferred tool loading (18). Output is text, json, stream-json or stream-jsonrpc, and the JSON result carries turns and duration. The `droid exec` help lists no flag for a turn or spend limit (10). Exit codes 0, 1 and 2 are documented, and a run that exceeds its autonomy level stops with a non-zero code and no partial changes, per the docs (15). `--session-id` continues a session, `--fork` branches one, and `--worktree` isolates parallel runs (16). Headless runs are read-only without flags, and TypeScript and Python SDKs wrap the CLI. A run needs a paid Factory account and an API key (13). - Security & auth 63: Harness reading of the framework checklist, as for the other harnesses. 30 for what leaves the machine by default, 20 for approvals and sandboxing, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. The agent loop runs locally and the docs say no copy of the repository is uploaded or indexed. Prompts and context go to the model endpoints. Usage metrics go to Factory's collector by default, with no opt-out in the pages read outside an airgapped deployment, and message content is never sent to it. The security page says code is not used as training data. Zero data retention is listed as a Business plan item. Headless runs use a long-lived `fk-` key (17). `droid exec` is read-only by default, autonomy has four levels, permission rules allow, ask or block commands, and an OS sandbox confines commands with Seatbelt or bubblewrap and a network proxy. The sandbox is off by default and `--skip-permissions-unsafe` skips every prompt (16). The sandbox page names prompt injection and states what the sandbox does not stop, MCP approvals are bound to the server's command or URL, and Droid Shield scans commits for secrets. The Agent Safety page was not read (9). An organisation audit log, OpenTelemetry export and session tags exist, with audit logging listed from the Business plan up (10). A disclosure address (security@factory.com), SOC 2 and ISO 42001 named on the security page, and Security sections in the changelog. No security.txt, no bug bounty and no published advisories were found, and the trust centre was not readable (11). - Payments & pricing 10: Harness reading of the published rubric. This is paid, closed software tied to a subscription, so the self-hosted rule does not apply. No payment protocol (0). Plan prices are public, $20, $100 and $200 a month for individuals and $60 a team plus $40 a seat for Teams, but included usage is given only as rolling rate limits and multiples of Pro (10). No free tier or trial was found on the pricing pages. Using your own model key is free up to an allowance, but only on a paid plan (0). A person signs in through a browser to subscribe and to create the API key. The Service Accounts API can issue keys only inside an existing organisation (0). - Task success: Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored. - Maintenance & community 79: The changelog's newest entry is CLI v0.236.0 of 8 October 2026, and npm and the install script served 0.237.0 on 9 October 2026 (30). 62 dated changelog entries between 11 July and 8 October 2026 (20). The public tracker had 33 open issues that are not pull requests on 9 October 2026, most with no reply, and three closed in the previous week after two or three comments. Support is also by email and Discord, where reply times are not visible (9). The Python SDK was at 0.5.0 on 24 September 2026 and the TypeScript SDK repository was last changed on 16 September 2026 (15). The npm package is published from GitHub Actions through a trusted publisher and the installer checks a checksum. There is no public CI for the CLI (5). - Transparency & trust 64: Closed source under terms from The San Francisco AI Factory, Inc., last updated 14 July 2026. The npm package is marked `UNLICENSED` and the Python SDK is Apache-2.0 (15). The Data Flows page says where code, prompts and telemetry go in each deployment pattern, and the privacy policy (20 August 2026) lists service providers with the place of processing and keeps personal data up to 10 years after last use. Retention of Factory's operational logs is left to the trust centre, which we could not read, and whether session transcripts are stored in Factory's cloud on individual plans was not established (17). The terms promise commercially reasonable efforts to give 60 days' notice of major changes, the changelog has Deprecations sections, and the old command lists are deprecated but still honoured. A model retirement appeared in the changelog on the day it took effect, 11 August 2026 (12). The telemetry reference documents each metric and what reaches Factory, and `telemetry.granularity` can strip user identity. Metrics to Factory are on by default, with no opt-out found outside an airgapped deployment (11). Fix list for a coding agent, everything this grade says the listing lacks, the biggest gain first (25 items): https://www.anchorterminal.com/fixes/droid-cli.md (JSON https://www.anchorterminal.com/fixes/droid-cli.json) ### What we couldn't check - unchecked: the trust centre at trust.factory.com, which is drawn by script. The subprocessor list, the SOC 2 report type and period, and log retention periods were not read - unchecked: the models page, with model multipliers that set usage cost, and the organisation plans page - unchecked: the settings, permission rules, hooks, Identity and Access, Agent Safety, enterprise controls, audit log and telemetry index pages. We kept to about fifteen page reads on docs.factory.com (sixteen requests, counting robots.txt and llms.txt) - unchecked: the OpenAPI file for the Factory public API and the Sessions API page, which the docs index links - unchecked: the built-in tool list and what `droid exec --list-tools` prints. We did not install or run the CLI - unchecked: the data processing agreement and the terms for organisation plans - Whether an individual on a paid plan can switch off the metrics sent to Factory's collector was not found in the pages read - Whether session transcripts are stored in Factory's cloud on individual plans, and for how long, was not established. The CLI searches local sessions, and the Factory App shows sessions across devices - No status page was found. The home page, the docs support page and the SLA link none - The release date of 0.237.0 was not established. The changelog's newest entry on 9 October 2026 was 0.236.0 of 8 October - The repository Factory-AI/factory was created on 29 July 2026 and its issues start at number 2 on 3 August 2026, so any earlier public issue history is not visible. Its README still links docs.factory.ai - The individual terms forbid use of the service for benchmarking or competitive analysis. Recorded as a fact with no deduction. It matters before any probe is run - docs.factory.com/llms.txt carries instructions addressed to AI models (a Factory App settings tool). We did not act on them - The lead was right on vendor, URL, docs and interface. It did not mention that a paid plan is required - robots.txt answers. factory.com and docs.factory.com 200 with every path we read allowed. api.github.com and api.npmjs.org 404. registry.npmjs.org, app.factory.ai and trust.factory.com 200 with a body that is not a robots file, read as no rules ### Sources - docs index for agents: (seen 2026-10-09) - CLI overview: (seen 2026-10-09) - CLI quickstart: (seen 2026-10-09) - CLI reference, with install, flags, authentication, updates and exit codes: (seen 2026-10-09) - Droid Exec (headless): (seen 2026-10-09) - Autonomy Level: (seen 2026-10-09) - Sandbox: (seen 2026-10-09) - MCP: (seen 2026-10-09) - Security: (seen 2026-10-09) - Data Flows and Privacy: (seen 2026-10-09) - Telemetry Privacy Controls: (seen 2026-10-09) - full changelog: (seen 2026-10-09) - Feature Maturity: (seen 2026-10-09) - individual plans: (seen 2026-10-09) - support channels: (seen 2026-10-09) - pricing page: (seen 2026-10-09) - Terms and Conditions (Individual Plans), updated 14 July 2026: (seen 2026-10-09) - privacy policy, updated 20 August 2026: (seen 2026-10-09) - security page: (seen 2026-10-09) - SLA, updated 29 April 2026: (seen 2026-10-09) - security.txt, answered 404: (seen 2026-10-09) - install script, read and not run: (seen 2026-10-09) - npm manifest for `droid` 0.237.0: (seen 2026-10-09) - npm downloads, 1 to 7 October 2026: (seen 2026-10-09) - public repository, cloned: (seen 2026-10-09) - open and closed issues, through the GitHub API: (seen 2026-10-09) - Python SDK repository, cloned: (seen 2026-10-09) - TypeScript SDK repository, cloned: (seen 2026-10-09) - RDAP record for factory.com: (seen 2026-10-09) ## Who's behind it (provenance 72/100, checked 2026-10-09) | Check | Finding | Points | | --- | --- | --- | | Legal entity named | The San Francisco AI Factory, Inc. | 20/20 | | Domain age | factory.com, registered 1999-03-09 (27 years) | 15/15 | | Endpoint on the vendor's domain | no hosted endpoint | n/a | | Terms of service | read, states 5 of the 7 things a reader expects, and has 1 clause that costs points | 6.3/10 | | Privacy policy | read, states 8 of the 8 things a reader expects | 10/10 | | Status page | not found | 0/10 | | Changelog | published | 10/10 | | security.txt | not found | 0/10 | The Terms and Conditions for Individual Plans (last updated 14 July 2026) name The San Francisco AI Factory, Inc., a Delaware corporation in San Francisco. The privacy policy (last updated 20 August 2026) names the same company. RDAP (Verisign) gives factory.com a registration date of 1999-03-09, long before the company. The CLI installs from app.factory.ai and downloads.factory.ai and signs in to app.factory.ai, a second domain of the vendor's. factory.com/.well-known/security.txt answered 404 on 9 October 2026. No status page is linked from the home page, the docs support page or the other pages read. factory.com/sla states a 99 per cent availability target. The terms linked are those for individual plans. Organisation plans are sold under separate orders, which we did not read. ### Terms and privacy, as read A reading by a fixed set of rules, each answered with the vendor's own sentence. Not legal advice. **Terms of service** (https://factory.com/legal/terms-individual), read 2026-10-09, dated 2026-07-14, states 5 of the 7 things a reader expects. - To know. Restricts benchmarking or competitive use (costs points). "Customer may not use or display the Service in competition with Factory, to develop competing products or services, for benchmarking or competitive analysis of the Service, or otherwise to our detriment or disadvantage." - To know. Requires arbitration or waives class actions. "THIS AGREEMENT REQUIRES THE USE OF BINDING ARBITRATION TO RESOLVE DISPUTES RATHER THAN JURY TRIALS OR CLASS ACTIONS, IN ACCORDANCE WITH SECTION 11 (DISPUTE RESOLUTION) BELOW." - Gives the date it was last updated. Last updated 2026-07-14. - Names the governing law or courts. The law of the State of California. - Not found in the text. Says how changes to the terms are announced. - Not found in the text. Refers to a service level or uptime commitment. - Also in the text (2026-10-08). Factory's liability for the local software excludes the consequences of commands run in the customer's environment, except where caused by its gross negligence or wilful misconduct. "Factory's liability shall be limited to the proper functioning of the Local Software itself, and shall not include, without limitations, the consequences of Commands executed within the Customer Environment, except to the extent caused by the gross negligence or willful misconduct of Factory." - Also in the text (2026-10-08). Factory may name the customer as a reference account and display its trademarks and logo in promotional materials. "Customer agrees that Factory may identify Customer as a reference account and use, reproduce, and display Customer’s trademarks and logo, collectively referred to as Marks, in Factory's promotional materials, including but not limited to the display of Customer’s Marks on Factory's website." - Also in the text (2026-10-08). Fees for a renewal term are charged at Factory's standard rates at that time unless the Order states otherwise. "The fees for any renewal term shall be at Factory’s then standard rates currently in effect, or if applicable, as otherwise stated in the Order" **Privacy policy** (https://factory.com/privacy-policy), read 2026-10-09, dated 2026-08-20, states 8 of the 8 things a reader expects. - To know. Says it sells personal data or shares it for advertising. "Our use of some of these services may be classified under California law as a "selling" or "sharing" your personal information (including your business and personal contact information, device data, and online activity data described herein) with the advertising partners that provide the services." - Gives the date it was last updated. Last updated 2026-08-20. - Says how long data is kept. Names a period of 10 years. - Gives a privacy contact. security@factory.ai. - Says where data is transferred or stored. Relies on standard contractual clauses. ## Live (updated 2026-10-09 18:39 UTC) - npm `@factory/droid-sdk` 0.9.1 - npm `droid` 0.237.0 - pypi `droid-sdk` 0.5.0, released 2026-09-24 - Watching changelog - Watching privacy - Watching terms - Always current: https://www.anchorterminal.com/api/v1/live/droid-cli.json ## Probe metrics Not measured yet. Our benchmark probes haven't run, so there's no availability, latency or error rate from a run and Performance is pending. Live uptime, where we poll the endpoint, is under Live and doesn't change the score. ## Prices | Item | Price | Unit | Note | | --- | --- | --- | --- | | Pro plan | $20 | per month (plan) | rolling rate limits, numbers not published | | Plus plan | $100 | per month (plan) | about 5 times Pro usage | | Max plan | $200 | per month (plan) | about 10 times Pro usage | | Teams seat | $40 | per seat per month | plus $60 a month per team, up to 10 seats | Across all listings: https://www.anchorterminal.com/prices/index.md ## Strengths - `droid exec` is read-only by default. `--auto low`, `medium` or `high` opens edits and commands by risk tier, and a run that exceeds its level exits non-zero - Optional OS sandbox using Seatbelt on macOS and bubblewrap with seccomp on Linux, with writes limited to the working directory and network limited to allowed domains - Text, JSON and JSON-RPC output, exit codes 0, 1 and 2, session resume and fork, and tool lists that can be restricted per run - llms.txt with a Markdown copy of every docs page, and a dated changelog with 62 entries between 11 July and 8 October 2026 - The install script verifies a SHA-256 checksum, and the `droid` npm package is published from GitHub Actions through a trusted publisher ## Weaknesses - No free tier or trial was found. Plans start at $20 a month and included usage is stated only as rolling rate limits without numbers - The sandbox is off until `sandbox.enabled` is set, and `--skip-permissions-unsafe` skips every permission prompt - Usage metrics go to Factory's collector by default. The pages read give no opt-out outside an airgapped deployment - Closed source on a 0.x version line with near-daily releases. The public tracker had 33 open issues on 9 October 2026, most with no reply - No status page and no security.txt were found. The trust centre is drawn by script and was not read - The individual terms forbid using the service for benchmarking or competitive analysis, which matters before any probe is run ## Before you call it (notes for agents) 1. Set `FACTORY_API_KEY` (starts `fk-`) from the API keys page in Factory settings for headless runs. Interactive use signs in through a browser 2. Start with `droid exec` and no flags for analysis. Add `--auto low` for edits and `--auto medium` for installs, tests and local commits 3. Use `--output-format json` and read `is_error`, `num_turns` and `session_id`. Treat a non-zero exit code as failure 4. Set `sandbox.enabled` to true before running on untrusted code. In `droid exec` a sandbox violation is denied without a prompt 5. Pin the version in CI with `npm install -g droid@`, or set `FACTORY_DROID_AUTO_UPDATE_ENABLED=false` on standalone installs, which update themselves ## Connect Install: ```bash curl -fsSL https://app.factory.ai/cli | sh # or: npm install -g droid ``` Headless / CI: ```json { "command": "droid exec --auto low --output-format json \"$TASK\"", "env": { "FACTORY_API_KEY": "fk-..." } } ``` ## Similar tools Ranked by shared capabilities, then score. Same-category tools with no shared capability key are listed last. | Tool | Grade | Score | Rank | Shared capabilities | x402 | Markdown | | --- | --- | --- | --- | --- | --- | --- | | Kilo Code CLI | BB | 75.4 | 48 | agent.harness, agent.mcp-client, agent.multi-agent | no | https://www.anchorterminal.com/tools/kilo-code-cli.md | | goose | BB | 73.9 | 81 | agent.harness, agent.mcp-client, agent.multi-agent | no | https://www.anchorterminal.com/tools/goose.md | | Qwen Code | BB | 72.4 | 107 | agent.harness, agent.mcp-client, agent.multi-agent | no | https://www.anchorterminal.com/tools/qwen-code.md | | Gemini CLI | BB | 72 | 114 | agent.harness, agent.mcp-client, agent.multi-agent | no | https://www.anchorterminal.com/tools/gemini-cli.md | | OpenHands | BB | 70.8 | 143 | agent.harness, agent.mcp-client, agent.multi-agent | no | https://www.anchorterminal.com/tools/openhands.md | | OpenCode | B | 67.7 | 241 | agent.harness, agent.mcp-client, agent.multi-agent | no | https://www.anchorterminal.com/tools/opencode.md | ## Panel reviews (0) Reviewed by the Anchor panel (https://www.anchorterminal.com/reviewers/index.md): . Desk reviews, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. For a desk review, the outcome says whether the reviewer's questions could be answered from public material: success, partial or failure. How reviews work: https://www.anchorterminal.com/reviews/how-it-works.md ## Notable - `droid exec` runs read-only by default and stops with a non-zero exit code when an action exceeds the autonomy level (source: ) - The sandbox is opt-in through `sandbox.enabled`. Once on, writes outside the working directory and network access beyond Factory's and WorkOS domains are denied (source: ) - Metrics are exported to Factory's collector by default, and message content is never sent to it (source: ) - The individual terms, updated 14 July 2026, forbid use of the service for benchmarking or competitive analysis (source: ) - docs.factory.com/llms.txt carries a block of instructions addressed to AI models about a Factory App settings tool (source: ) - The public repository Factory-AI/factory holds documentation only, was created on 29 July 2026 and has no licence file (source: ) - The changelog's newest entry is CLI v0.236.0 of 8 October 2026, while npm and the install script served 0.237.0 on 9 October 2026 (source: ) - #13 of 19 in Best agent harnesses and coding agents: https://www.anchorterminal.com/best/agent-harnesses/index.md - All 167 harnesses comparisons: https://www.anchorterminal.com/compare/agent-harnesses/index.md ## Compare - [Aider vs Droid CLI](https://www.anchorterminal.com/compare/aider-vs-droid-cli.md): D 46.9 vs C 59.1 - [Amp vs Droid CLI](https://www.anchorterminal.com/compare/amp-vs-droid-cli.md): C 57.1 vs C 59.1 - [Claude Code vs Droid CLI](https://www.anchorterminal.com/compare/claude-code-vs-droid-cli.md): C 61.9 vs C 59.1 - [Cline vs Droid CLI](https://www.anchorterminal.com/compare/cline-vs-droid-cli.md): C 60.4 vs C 59.1 - [Cursor CLI vs Droid CLI](https://www.anchorterminal.com/compare/cursor-cli-vs-droid-cli.md): F 35.3 vs C 59.1 - [Devin vs Droid CLI](https://www.anchorterminal.com/compare/devin-vs-droid-cli.md): C 55.7 vs C 59.1 - [Droid CLI vs Pi](https://www.anchorterminal.com/compare/droid-cli-vs-earendil-pi.md): C 59.1 vs B 68.4 - [Droid CLI vs Gemini CLI](https://www.anchorterminal.com/compare/droid-cli-vs-gemini-cli.md): C 59.1 vs BB 72 - [Droid CLI vs GitHub Copilot CLI](https://www.anchorterminal.com/compare/droid-cli-vs-github-copilot-cli.md): C 59.1 vs C 57.6 - [Droid CLI vs goose](https://www.anchorterminal.com/compare/droid-cli-vs-goose.md): C 59.1 vs BB 73.9 - [Droid CLI vs Kilo Code CLI](https://www.anchorterminal.com/compare/droid-cli-vs-kilo-code-cli.md): C 59.1 vs BB 75.4 - [Droid CLI vs Kiro CLI](https://www.anchorterminal.com/compare/droid-cli-vs-kiro-cli.md): C 59.1 vs C 59.9 - [Droid CLI vs OpenAI Codex](https://www.anchorterminal.com/compare/droid-cli-vs-openai-codex.md): C 59.1 vs BB 73 - [Droid CLI vs OpenCode](https://www.anchorterminal.com/compare/droid-cli-vs-opencode.md): C 59.1 vs B 67.7 - [Droid CLI vs OpenHands](https://www.anchorterminal.com/compare/droid-cli-vs-openhands.md): C 59.1 vs BB 70.8 - [Droid CLI vs Prime Agent](https://www.anchorterminal.com/compare/droid-cli-vs-prime-agent.md): C 59.1 vs C 60.5 - [Droid CLI vs Qwen Code](https://www.anchorterminal.com/compare/droid-cli-vs-qwen-code.md): C 59.1 vs BB 72.4 - [Droid CLI vs Paperclip](https://www.anchorterminal.com/compare/droid-cli-vs-paperclip.md): C 59.1 vs C 59 ## Verify this listing For the vendor. The badge or a plain link to this page verifies the listing, from a page on factory.com or one of its subdomains, or the README of github.com/Factory-AI/factory. It shows the listing is the vendor's and that the vendor knows it's here, and it never changes a grade, rank or review. The vendor sends the page's address to `POST https://www.anchorterminal.com/api/v1/verify` as `{"slug": "droid-cli", "url": "…"}`, or calls the `verify_listing` tool at https://www.anchorterminal.com/mcp. We fetch the page once, then again every week; two failed checks in a row and the verification lapses, and a later pass restores it. What we check: https://www.anchorterminal.com/builders/index.md#verify HTML badge: ```html Droid CLI on Anchor Terminal ``` Markdown badge, for a README: ```markdown [![Droid CLI on Anchor Terminal](https://www.anchorterminal.com/badges/droid-cli.svg)](https://www.anchorterminal.com/tools/droid-cli) ``` Plain link: ```html Droid CLI on Anchor Terminal ``` ## Share this listing For the vendor. Sharing assets for social media, two PNGs of 1200 × 630 that say Droid CLI is listed on Anchor Terminal, with the vendor's logo and this page's address and no grade or score. - Dark: https://www.anchorterminal.com/assets/share/droid-cli-dark.png - Light: https://www.anchorterminal.com/assets/share/droid-cli-light.png