Mobile AI Dev Tools — procurement report
ProductArena · rankings as of 2026-09-16 · evidence as of 2026-09-16 · 6 products · 69 judged requirements · 414 judged cells
Methodology: Every product is judged against a shared taxonomy of user stories using cited evidence — hands-on probes > repository code > independent community sources > vendor claims — never opinion. Full writeup: https://ultrametric.ai/productarena/methodology
Leaderboard
| # | Product | PA Score | Coverage score | Applicable cells | Confidence |
|---|---|---|---|---|---|
| 1 | Working Copy | 19.0 | 35.9 | 52/69 | C |
| 2 | GitHub Mobile | 14.3 | 24.5 | 28/69 | C |
| 3 | Termius | 11.3 | 28.7 | 39/69 | C |
| 4 | Tailscale | 9.7 | 20.5 | 31/69 | B |
| 5 | Blink Shell | 7.1 | 26.8 | 29/69 | B |
| 6 | a-Shell | 4.0 | 8.3 | 47/69 | D |
PA Score = agent-readiness blend (see methodology). Coverage score = weighted share of judged requirements met. Confidence = how much of the score rests on tested vs claimed evidence (A–D).
Uncertainty note
The current #1/#2 gap in this arena is not close enough to qualify for the multi-judge uncertainty pass (or the pass has not covered it yet) — no extra caveat applies beyond the per-product confidence grades above.
Buyer checklist (RFP)
The arena's 69 judged user stories as requirements, grouped by theme. Priorities mirror the story weights our scoring uses (3 = must-have, 2 = should-have, 1 = nice-to-have). Interactive version with per-requirement verdicts for the top products: /arena/mobile-dev/checklist
Agenticness — how well agents can access and operate the productAgenticness
How well agents can access and operate the product
- ai-native userPlug MCP servers into this product so it can use their toolsmust-have
- ai-native userConnect an agent via an official MCP servermust-have
- ai-native userDrive the product through a documented public APImust-have
- ai-native userDelegate tasks to a built-in AI assistant inside the productmust-have
- ai-native userPoint an agent at llms.txt or agent-oriented docsshould-have
- ai-native userRun the product headlessly / in CI for automationshould-have
- ai-native userUse an official CLIshould-have
- ai-native userIssue scoped/least-privilege API credentials for an agentshould-have
- ai-native userBuild against official SDKsshould-have
- ai-native userSubscribe to events via webhooksshould-have
- ai-native userGet AI-generated insights and suggestions from my data inside the productshould-have
- ai-native userSet up automations that run autonomously in the backgroundshould-have
- ai-native userOperate the product with natural-language commandsshould-have
- ai-native userExplore an interactive API reference with runnable examplesshould-have
- ai-native userDownload a machine-readable API spec (OpenAPI or equivalent)should-have
- ai-native userRely on versioned APIs with a documented deprecation policyshould-have
- ai-native userTest against a sandbox environment without touching production datanice-to-have
Automation depth — how much of the product can run unattendedAutomation depth
How much of the product can run unattended
- ai-native userDefine rules that trigger actions automatically on eventsmust-have
- ai-native userPerform bulk operations across many items at onceshould-have
- ai-native userSchedule recurring jobs or workflowsshould-have
- ai-native userVersion, review, and roll back my automationsnice-to-have
Git code — core git and code operations — cloning, branching, pushing, code browsingGit code
Core git and code operations — cloning, branching, pushing, code browsing
- developerClone Git repositories over HTTPS, SSH, or the Git protocolmust-have
- developerCommit and push changes directly from my devicemust-have
- developerCreate pull requests on hosted Git platforms directly from my devicemust-have
- developerReview pull requests from my phone while on the gomust-have
- power-userAmend the latest commit or undo unpushed commits to fix or split themshould-have
- developerSearch and navigate code content using fuzzy matching, filters, and regular expressionsshould-have
- power-userVisualize the full commit graph across branchesshould-have
- power-userInteractively rewrite history by deleting, editing, squashing, or reordering commitsshould-have
- developerResolve merge conflicts across many files at once with a dedicated toolshould-have
- power-userStash and unstash changes to temporarily clear my working directoryshould-have
- developerPreview Markdown, HTML, and other rendered files with live reloadshould-have
- power-userSign my commits with a GPG or SSH key for verificationnice-to-have
- power-userClone, update, and manage Git submodules within a repositorynice-to-have
Networking access — stories about networking access in this arenaNetworking access
Stories about networking access in this arena
- developerGet secure infrastructure access to resources wherever they live, including Kubernetes clustersmust-have
- power-userConnect directly to my servers without relying on a cloud relay, proxy, or VPNshould-have
- power-userRoute all my internet traffic through a specific device on my network using an exit nodeshould-have
- developerUse subnet routers to reach devices outside my local network as if I were on itshould-have
Offline sync — stories about offline sync in this arenaOffline sync
Stories about offline sync in this arena
- developerAccess and work with files and repositories from other apps' sandboxes on my deviceshould-have
- power-userSync my saved hosts and connection settings across all my devicesshould-have
Openness — open source, data portability, and self-hosting storiesOpenness
Open source, data portability, and self-hosting stories
- ai-native userExport all of my data in open formats and leavemust-have
- ai-native userSelf-host the core productmust-have
- ai-native userDo everything through the API that I can do in the UIshould-have
- ai-native userRead the product's source under an open licenseshould-have
Privacy posture — data-handling and privacy storiesPrivacy posture
Data-handling and privacy stories
- ai-native userPrevent my data from being used to train AI modelsmust-have
- ai-native userChoose where my data is stored (region/residency)should-have
- ai-native userControl data retention and deletionshould-have
- ai-native userOpt out of telemetry and usage trackingshould-have
Running agents — operating agents in production — sessions, persistence, recoveryRunning agents
Operating agents in production — sessions, persistence, recovery
- ai-native userHave an AI agent analyze my pull requests and suggest code improvements from my phonemust-have
- ai-native userDirect an AI agent to browse, search, edit, commit, pull, and push in a repository via conversationmust-have
- ai-native userAssign an issue to an AI coding agent and receive a ready-to-review pull requestmust-have
- ai-native userGet AI-generated commit message suggestions based on my staged changesshould-have
- ai-native userConverse with an AI agent in natural language to get insights into repositories and open pull requestsshould-have
- developerManage and track cloud-based coding agent tasks from my phoneshould-have
- ai-native userDescribe what I want in plain language and have the tool generate the corresponding shell commandshould-have
Security — security posture and hardening storiesSecurity
Security posture and hardening stories
- developerProtect my remote connections with biometric authentication like Face ID or fingerprintshould-have
- developerStore credentials once in a secure vault and reference them from multiple hostsshould-have
- power-userStore my SSH keys in a hardware-backed secure enclave protected by biometricsshould-have
Terminal ssh — terminal and SSH workflows — shells, sessions, remote accessTerminal ssh
Terminal and SSH workflows — shells, sessions, remote access
- developerRun local UNIX commands like ls, grep, cat, tar, and curl directly in the appmust-have
- power-userOpen multiple terminal sessions, each with its own context, appearance, and historymust-have
- power-userKeep my terminal session alive across network changes and device sleepmust-have
- developerConnect to remote servers using SSH with Ed25519, ECDSA, or RSA keysmust-have
- developerEdit files with a terminal-based editor and run syntax/lint checkers inside the appshould-have
- developerInstall additional pure-Python packages using pip directly on my deviceshould-have
- power-userGroup multiple terminal sessions together and broadcast the same command to all of themshould-have
- developerTransfer files to and from remote hosts via scp and sftp using my configured keysshould-have
- power-userGenerate SSH key pairs for password-less access to my serversshould-have
- power-userConnect to a saved host with one tap without re-entering credentialsshould-have
Ux ergonomics — stories about ux ergonomics in this arenaUx ergonomics
Stories about ux ergonomics in this arena
- power-userCustomize the font, colors, and cursor appearance of my terminal and persist the settingsshould-have
Appendix: recorded probes
No replayable probe recordings exist for this arena yet. Probe-tier evidence (hands-on checks) still backs verdicts where cited — see each product page for the evidence trail.
Cite as: ProductArena by Ultrametric Inc, Mobile AI Dev Tools arena, rankings as of 2026-09-16 — https://ultrametric.ai/productarena/arena/mobile-dev
License: © 2026 Ultrametric Inc. Brief quotation of individual verdicts, scores, or evidence excerpts is permitted with attribution to "ProductArena by Ultrametric Inc (ultrametric.ai/productarena)", as is use of the data to evaluate, contest, or contribute corrections. Bulk copying, redistribution, or use to build competing datasets requires prior written permission (see DATA-LICENSE in the repository).
No liability: rankings, verdicts, and scores are research outputs derived from the cited evidence at a point in time, provided "as is", without warranties. Ultrametric Inc accepts no responsibility for procurement, purchasing, or other decisions made in reliance on them — verify against the cited evidence before acting (https://ultrametric.ai/productarena/terms).