Aura Autopilot vs Beam (beam.win)

Aura Autopilot 69

MCP reading. 14 tools (15 for 11 to 30), with long descriptions on probe and run_harness and a long INSTRUCTIONS.md the skill says to read in full, with no toolsets (13 of 25). read_file takes offset and limit up to 2,000 lines, list_files returns at most 500, search at most 200 with a glob, frames up to 12 and run_harness takes seconds of play (16 of 20). Errors come back as isError with what to do next (open the editor, update the agent service, call wait), and headless runs exit 0, 1, 2 or 3 (16 of 20). readOnlyHint is set on the seven read tools and destructiveHint false on all, including probe, which the description says can change the game directly. One call runs at a time and a long one answers "still going" for wait to collect (14 of 20). Two required parameters on start_run with defaults of 10 minutes of exploration and a 30-minute limit; no SDKs, which a playtester doesn't need (10 of 15). 69 in all.

Beam (beam.win) 0

Graded on the interface an outside agent can use. Beam has none, so context cost, output controls, errors, retries and defaults score nothing (0 on each line). For the record, the only command-line use documented is a doctor that checks permissions and network on a Mac and names the missing step.

Aura Autopilot 74

MCP reading. All 14 tools (start_run, wait, probe, run_harness, snapshot, describe_frames, restart_level, report, frames and five file tools) have JSON Schema inputs, read in autopilot/mcp.py, session.py, external.py and files.py (25). No llms.txt on www.tryaura.dev (404). The agent skill, INSTRUCTIONS.md and KIT.md are Markdown written for the agent, and the README and CONTRIBUTING.md are in the repository (7 of 10). Descriptions say what each tool does and when not to use it (frames is for a describer subagent only, describe_frames is a fallback), with server instructions (17 of 20). Required fields and an enum on kind, but report.outcome is a free string with its values only in the description, numeric ranges sit in descriptions rather than the schema, and probe takes free-form Python (9 of 15). Prompt examples in the README and skill, plain-language errors in the MCP server and documented exit codes for headless runs (11 of 15). Version numbers and a protocol version, but no public changelog, and GitHub release notes couldn't be read (5 of 15). 74 in all.

Beam (beam.win) 10

Graded on the interface an outside agent can use, which is none. No API, MCP server, URL scheme or scripting dictionary was found, and the command line is documented only by its doctor command, so the contract, description, typed-input and example lines score nothing (0 of 25, 0 of 20, 0 of 15, 0 of 15). beam.win/llms.txt describes the product, requirements, privacy, pricing and support in Markdown (10). No versioned changelog (0 of 15).

Aura Autopilot 53

Local-software reading, as tokeneconomizer was read: 30 for what leaves the machine and credentials, 20 approvals and sandboxing, 15 injection, 15 audit, 20 programme. Run sharing is on by default and sends recordings, screenshots, agent traces with the code the agent read and, for MCP runs, the user's own Claude Code or Codex conversation to app.tryaura.dev, after redacting secrets, paths, user and host names and email addresses. Keys sit in plain text in autopilot.env, the file tools never read *.env, and the localhost control endpoint carries a random secret (12). File tools write only the run's folder, notes.md and lib.py, and the user can stop or steer a run from the tab. autopilot connect codex sets default_tools_approval_mode to approve, and on Windows and macOS the sandbox is a plain child process without keys but with network and disk (10). sandbox.py names prompt injection from a game's code as the reason for the sandbox, and the frame describer is given only open questions (11). Each run keeps its agent log, harness versions, traces, decisions, report and recording, and the Feed tab shows activity (13). SECURITY.md asks for GitHub private vulnerability reporting; no security.txt on www.tryaura.dev (404), no bounty or certification found, advisories couldn't be read. Releases are signed and immutable, and pull requests need a code owner's approval (7). 53 in all.

Beam (beam.win) 0

Graded on the interface an outside agent can use. With none, the credential, least-privilege, injection and audit lines score nothing (0 of 30, 0 of 20, 0 of 15, 0 of 15). For the record, people sign in through Clerk, each new Mac must be approved, connections are encrypted and pinned to approved Macs, share links are view only by default, and hidden windows and password managers never reach the picker. The security programme line doesn't need an interface and is scored. beam.win/.well-known/security.txt returns 404, and no disclosure policy, bug bounty or certification was found (0 of 20).

Aura Autopilot 50

Open-source software with paid parts around it, so the pricing lines are read for what a run needs. No payment protocol (0). TypeSafe publishes Jev's price per million input tokens and Aura's plans are public, Indie from $10 a month billed annually (20). Autopilot is free under Apache-2.0, and Aura's two-week trial needs no card (20). No Ramen account is needed with one's own keys, but a person installs the editor plugin and gets a TypeSafe key or signs in to Aura in a browser, so 10 rather than the self-hosted rule's 20 (10). 50 in all.

Beam (beam.win) 30

No x402, MPP or L402 (0). Plan prices are public without a login, $12 a month, $84 a year, $199 once and $12 a seat a month for teams, plan-only (10). Free tier with 20 minutes a day of use and no card (20). Access needs a person to download the app and sign in, and the 14-day trial needs a card (0).

Aura Autopilot 41

Local-software reading, as a stdio MCP server with engine plugins. Official downloads per engine and OS from GitHub Releases, signed and listed in SHA256SUMS.txt, with Unreal 5.4 to 5.8, Unity 6000.0 or later, Godot 4.7 or later, Windows and macOS and Python 3.12 or later stated. The agent service isn't on a package registry; the plugin installs it, with uv and Bun, on first run (17 of 20). .github/workflows/ci.yml runs ruff and pytest on Linux, Windows and macOS with Python 3.12 and 3.13 plus a Codex end-to-end job, and CONTRIBUTING.md names download and uninstall end-to-end workflows. Whether runs pass wasn't checked, as github.com couldn't be read (15 of 25). Open issues couldn't be read, and the repository is days old (5 of 25). No changelog; releases are tagged v<version>-<commit>, the plugin protocol is versioned and the contributing rules say to add optional fields rather than change existing ones (4 of 15). Python package 0.1.0 and the Unreal plugin marked IsBetaVersion (0). 41 in all.

Beam (beam.win) 25

Graded on no interface an outside agent can call, and read with the local-software lines since Beam is a Mac app. The app is a public DMG from the vendor with requirements stated, Apple silicon on macOS 14 or later (20 of 20). No public CI or test suite (0 of 25). No public issue tracker to count, support is by email. Judgement call (5 of 25). No changelog or release notes, and the version labels disagree, 1.0.3 on the download link and 0.3.1 in the 20 October post (0 of 15). Not declared stable, given the conflicting labels (0 of 15). The account server that meters Free minutes has no status page, which the hosted lines would also score low.

Aura Autopilot 43

The launch post is dated 31 October 2026 and Aura 1.2.3 and 1.2.4 of 30 October 2026 ship Autopilot, so the last change is within 30 days (30). GitHub releases couldn't be read, and the two Aura release-note entries aren't three (0). Issue and pull-request replies couldn't be read; the project is days old, with Discord and support email as other channels (5 of 25). Not in the official MCP registry under any namespace (searched for autopilot and ramenvr) (0). Pinned dependencies, per-platform locks in packaging/, CI on three operating systems, conventional-commit checks and code-owner review (8 of 10). 43 in all.

Beam (beam.win) 35

Read for a closed product. Plans, accounts and new pricing launched on 14 October 2026 per the terms, and a 20 October post names Beam 0.3.1, so the last dated product change is within 30 days (30). No changelog or release notes, so no three dated entries in 90 days can be counted (0 of 20). Support is an email address, hello@beam.win, with no public changelog or community channel, not tested (5 of 15). No SDK and no MCP registry entry (0). No package or CI to judge (0).