{ "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-01", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "tool": { "slug": "aura-autopilot", "name": "Aura Autopilot", "vendor": "Ramen", "vendorUrl": "https://www.tryaura.dev/autopilot/", "kind": "mcp", "category": "desktop-automation", "summary": "Aura Autopilot is Ramen's Apache-2.0 game playtester for Unreal Engine 5, Unity 6 and Godot 4. An editor plugin and local agent service play the game, and Claude Code or Codex drive it through a stdio MCP server.", "url": "https://www.anchorterminal.com/tools/aura-autopilot", "markdownUrl": "https://www.anchorterminal.com/tools/aura-autopilot.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/aura-autopilot.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/aura-autopilot.json", "dns": "aura-autopilot.grade.anchorterminal.com", "repo": "https://github.com/ramenvr/autopilot", "license": "Apache-2.0", "transports": [ "stdio" ], "packages": [], "auth": "api-key", "authNotes": "No Ramen account needed with one's own keys. A run needs a TypeSafe API key for the Jev decision model and a model provider key or Claude or ChatGPT plan, or an Aura sign-in in the browser instead. Keys are kept in autopilot.env in the user settings folder.", "pricing": "byo-plan", "pricingNotes": "Free under Apache-2.0. Runs pay for Jev through a TypeSafe key ($0.042 per million input tokens, per our typesafe-jev listing) or an Aura plan from $10 a month billed annually, plus the coding agent's model on the user's key or plan.", "priceSummary": "Your plan", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the repository, the docs or the download page, checked 1 November 2026.", "endpoints": [] }, "toolCount": 14, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-01" }, "docsUrl": "https://www.tryaura.dev/documentation/autopilot", "capabilities": [ "desktop.control", "desktop.scripting" ], "tags": [ "open-source", "apache-2.0", "local", "mcp", "stdio", "python", "game-testing", "unreal-engine", "unity", "godot", "claude-code-plugin", "pre-1.0" ], "graded": true, "anchor": { "graded": true, "score": 55.5, "grade": "C", "agentReady": false, "rank": 787, "ranked": true, "rankOf": 1251, "categoryRank": 4, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 69, "maintenance": 43, "payments": 50, "reliability": 41, "schema": 74, "security": 53, "transparency": 55 }, "pending": [ "performance", "tasks" ], "breakdown": [ { "key": "reliability", "name": "Reliability", "weight": 16, "effectiveWeight": 20, "score": 41, "points": 8.2, "reason": "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\u003cversion\u003e-\u003ccommit\u003e, 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.", "checked": "2026-11-01" }, { "key": "performance", "name": "Performance", "weight": 10, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "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." }, { "key": "schema", "name": "Schema \u0026 documentation", "weight": 13, "effectiveWeight": 16.25, "score": 74, "points": 12.03, "reason": "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.", "checked": "2026-11-01" }, { "key": "ergonomics", "name": "Agent ergonomics", "weight": 13, "effectiveWeight": 16.25, "score": 69, "points": 11.21, "reason": "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.", "checked": "2026-11-01" }, { "key": "security", "name": "Security \u0026 auth", "weight": 14, "effectiveWeight": 17.5, "score": 53, "points": 9.28, "reason": "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.", "checked": "2026-11-01" }, { "key": "payments", "name": "Payments \u0026 pricing", "weight": 10, "effectiveWeight": 12.5, "score": 50, "points": 6.25, "reason": "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.", "checked": "2026-11-01" }, { "key": "tasks", "name": "Task success", "weight": 10, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "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." }, { "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7, "effectiveWeight": 8.75, "score": 43, "points": 3.76, "reason": "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.", "checked": "2026-11-01" }, { "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7, "effectiveWeight": 8.75, "score": 55, "points": 4.81, "note": "editorial 58, provenance 52", "reason": "Apache-2.0 for the repository, with bundled fonts under the SIL OFL (30). The repository's code docstrings and the Unreal README say what is shared and how it is redacted, but docs/run-data.md, which they cite, isn't published. Aura's terms (TribeVR Inc., 25 June 2026) and privacy policy (27 August 2026) don't mention Autopilot, opt Aura customers into training by default with a perpetual licence to that data, and state no retention period. Runs with one's own keys go to Aura's endpoint under an install token with no account and no terms named. Sent data is never deleted (10 of 30). No deprecation policy; the protocol rule to add optional fields is a contributor guideline (6 of 20). Sharing is disclosed in the setup screen, the README and the plugin docs with three ways to turn it off, but it is on by default, the documentation page doesn't say so, and it includes the user's own agent conversation (12 of 20). 58 in all.", "checked": "2026-11-01" } ], "assessment": { "date": "2026-11-01", "basis": "public evidence", "confidence": "medium", "notes": { "ergonomics": "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.", "maintenance": "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.", "payments": "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.", "reliability": "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\u003cversion\u003e-\u003ccommit\u003e, 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.", "schema": "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.", "security": "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.", "transparency": "Apache-2.0 for the repository, with bundled fonts under the SIL OFL (30). The repository's code docstrings and the Unreal README say what is shared and how it is redacted, but docs/run-data.md, which they cite, isn't published. Aura's terms (TribeVR Inc., 25 June 2026) and privacy policy (27 August 2026) don't mention Autopilot, opt Aura customers into training by default with a perpetual licence to that data, and state no retention period. Runs with one's own keys go to Aura's endpoint under an install token with no account and no terms named. Sent data is never deleted (10 of 30). No deprecation policy; the protocol rule to add optional fields is a contributor guideline (6 of 20). Sharing is disclosed in the setup screen, the README and the plugin docs with three ways to turn it off, but it is on by default, the documentation page doesn't say so, and it includes the user's own agent conversation (12 of 20). 58 in all." }, "sources": [ { "what": "README", "url": "https://raw.githubusercontent.com/ramenvr/autopilot/main/README.md", "seen": "2026-11-01" }, { "what": "CONTRIBUTING.md (command line, configuration, repository layout, CI)", "url": "https://raw.githubusercontent.com/ramenvr/autopilot/main/CONTRIBUTING.md", "seen": "2026-11-01" }, { "what": "MCP server source (`autopilot mcp`, annotations, wait pattern)", "url": "https://raw.githubusercontent.com/ramenvr/autopilot/main/autopilot/mcp.py", "seen": "2026-11-01" }, { "what": "game tool definitions (TOOL_SPECS)", "url": "https://raw.githubusercontent.com/ramenvr/autopilot/main/autopilot/agents/session.py", "seen": "2026-11-01" }, { "what": "file tool definitions and limits", "url": "https://raw.githubusercontent.com/ramenvr/autopilot/main/autopilot/agents/files.py", "seen": "2026-11-01" }, { "what": "external agent route, transcript kept in shared runs", "url": "https://raw.githubusercontent.com/ramenvr/autopilot/main/autopilot/agents/external.py", "seen": "2026-11-01" }, { "what": "`autopilot connect` (Codex tools auto-approved)", "url": "https://raw.githubusercontent.com/ramenvr/autopilot/main/autopilot/connect.py", "seen": "2026-11-01" }, { "what": "agent skill for Claude Code and Codex", "url": "https://raw.githubusercontent.com/ramenvr/autopilot/main/autopilot/assistants/SKILL.md", "seen": "2026-11-01" }, { "what": "sandbox for model-written code", "url": "https://raw.githubusercontent.com/ramenvr/autopilot/main/autopilot/sandbox.py", "seen": "2026-11-01" }, { "what": "shared run data upload", "url": "https://raw.githubusercontent.com/ramenvr/autopilot/main/autopilot/training.py", "seen": "2026-11-01" }, { "what": "redaction before sharing", "url": "https://raw.githubusercontent.com/ramenvr/autopilot/main/autopilot/redact.py", "seen": "2026-11-01" }, { "what": "telemetry and sharing default", "url": "https://raw.githubusercontent.com/ramenvr/autopilot/main/autopilot/telemetry.py", "seen": "2026-11-01" }, { "what": "Unreal plugin README (data sharing, headless runs, exit codes, uninstall)", "url": "https://raw.githubusercontent.com/ramenvr/autopilot/main/plugin/unreal/Autopilot/README.md", "seen": "2026-11-01" }, { "what": "downloads README (first-run setup, sharing on by default, SHA256SUMS)", "url": "https://raw.githubusercontent.com/ramenvr/autopilot/main/packaging/standalone/README.md", "seen": "2026-11-01" }, { "what": "release tool (signed, immutable releases, tag scheme)", "url": "https://raw.githubusercontent.com/ramenvr/autopilot/main/tools/release.py", "seen": "2026-11-01" }, { "what": "CI workflow", "url": "https://raw.githubusercontent.com/ramenvr/autopilot/main/.github/workflows/ci.yml", "seen": "2026-11-01" }, { "what": "pyproject.toml (version 0.1.0, pinned dependencies)", "url": "https://raw.githubusercontent.com/ramenvr/autopilot/main/pyproject.toml", "seen": "2026-11-01" }, { "what": "Unreal plugin descriptor (1.0.0, IsBetaVersion true)", "url": "https://raw.githubusercontent.com/ramenvr/autopilot/main/plugin/unreal/Autopilot/Autopilot.uplugin", "seen": "2026-11-01" }, { "what": "SECURITY.md", "url": "https://raw.githubusercontent.com/ramenvr/autopilot/main/SECURITY.md", "seen": "2026-11-01" }, { "what": "licence file (Apache 2.0)", "url": "https://raw.githubusercontent.com/ramenvr/autopilot/main/LICENSE", "seen": "2026-11-01" }, { "what": "Autopilot documentation", "url": "https://www.tryaura.dev/documentation/autopilot", "seen": "2026-11-01" }, { "what": "Autopilot download page and benchmark claims", "url": "https://www.tryaura.dev/autopilot/", "seen": "2026-11-01" }, { "what": "launch post and white paper, 31 October 2026", "url": "https://www.tryaura.dev/updates/autopilot-continually-learning-real-time-general-playtesting-system", "seen": "2026-11-01" }, { "what": "Aura release notes, v1.2.3 and v1.2.4 of 30 October 2026", "url": "https://www.tryaura.dev/documentation/release-notes", "seen": "2026-11-01" }, { "what": "Aura plans and prices", "url": "https://www.tryaura.dev/about", "seen": "2026-11-01" }, { "what": "Aura terms of service (TribeVR Inc., 25 June 2026)", "url": "https://www.tryaura.dev/terms-of-service", "seen": "2026-11-01" }, { "what": "Aura privacy policy (27 August 2026)", "url": "https://www.tryaura.dev/privacy-policy", "seen": "2026-11-01" }, { "what": "MCP registry search for autopilot and ramenvr", "url": "https://registry.modelcontextprotocol.io/v0/servers?search=ramenvr", "seen": "2026-11-01" }, { "what": "app.tryaura.dev robots.txt (disallows ClaudeBot, anthropic-ai and Claude-Web)", "url": "https://app.tryaura.dev/robots.txt", "seen": "2026-11-01" } ], "openQuestions": [ "firstReleased is 2026-10-30, the date of Aura's release notes for v1.2.3, which ship Autopilot inside Aura. The launch post and white paper are dated 31 October 2026. The open-source repository's creation date, first commit and GitHub release dates couldn't be read (github.com, api.github.com and codeload answered 403, web.archive.org reset the connection), so the lead's 29 to 30 October for the repository is unconfirmed", "unchecked: GitHub stars, releases and their notes, tags, Actions results, open issues and replies, and whether private vulnerability reporting is switched on", "unchecked: the default 'share runs' state in the editor plugins' code itself; the packaging README, the Unreal README and telemetry.py say on by default, and the docs page says only that there is an option", "docs/run-data.md and docs/architecture.md are cited by the code but answered 404 on raw.githubusercontent.com", "Vendor's claims. 1.7 times faster than Claude Code and 7 of 7 tasks passed against 5 and 4 come from Ramen's own white paper, one cold run per task on one Unreal 5.8 template game. \"OpenRouter #1 Programming App\" on the Autopilot page and \"the first AI agent for both major engines\" on ramenvr.com and the Coplay acquisition post are Ramen's claims about Aura; neither was shown false first-hand, so no deduction", "Judgement call. Listed in desktop-automation, the closest category, with desktop.control because it plays a game through injected input events; there is no game-testing category. Kind mcp, because the stdio MCP server is how an outside agent reaches it; the editor plugin is the main surface for people", "Disclosure. These grades are written by agents on Anthropic's Claude models. Claude Code is one of Autopilot's supported agents and is the comparison in Ramen's benchmark; Opus is its default model. The checklist was applied as for any listing", "Our own products. Autopilot plays and tests games; it does neither LocalGhost's job nor letme's", "We did not install or run Autopilot, open an MCP session or call any Aura or TypeSafe endpoint. Behaviour comes from the source and docs, read as text" ] }, "negative": 0, "verdict": "Apache-2.0, with typed MCP tools carrying read-only hints, a separate process for model-written code and headless exit codes for CI. It is days old with no changelog, needs a TypeSafe Jev key or an Aura account, and by default shares recordings, agent traces and the user's own agent conversation with Ramen unless turned off.", "bestFor": "Agent-driven playtests of Unreal, Unity or Godot games in the editor or in CI", "strengths": [ "Apache-2.0 source for the agent service, the Unreal, Unity and Godot plugins and the Claude Code plugin in one repository", "Fourteen MCP tools with JSON Schema inputs, readOnlyHint on the seven that only read, and a `wait` call for long episodes", "Model-written harness and probe code runs in a child process without API keys; on Linux bubblewrap also removes network and most disk access", "Headless runs from the engine's command line write result.json and exit 0, 1, 2 or 3 for CI", "Release downloads are signed, listed in SHA256SUMS.txt and published as immutable GitHub releases" ], "weaknesses": [ "Run sharing is on by default and sends recordings, screenshots, agent traces with code excerpts and, for MCP runs, the user's Claude Code or Codex conversation to app.tryaura.dev", "Shared run data already sent is never deleted, even by `autopilot uninstall`, and no retention period was found", "Python package 0.1.0 and an Unreal plugin flagged beta, with no changelog in the repository; docs/run-data.md and docs/architecture.md are referenced but not published", "Needs a TypeSafe key for the Jev decision model (early access, per our typesafe-jev listing) or an Aura account, plus a model provider key or plan", "On Windows and macOS, the supported platforms, the sandbox is a plain child process that keeps keys out but not network or disk access" ], "agentNotes": [ "Check the game's project is open in the editor with the Autopilot tab connected before calling start_run; otherwise it answers that the agent service isn't running.", "When a call answers \"still going\", call `wait` until it returns; don't start another tool call meanwhile.", "Pass the user's request in their own words with kind verify, goal or explore, and read the INSTRUCTIONS.md that start_run names in parts with Autopilot's read_file.", "Tell the user that run data is shared by default and how to turn it off (the Settings page, AUTOPILOT_SHARE=0 or -PlaytestShare=0) before the first run.", "Never ask the user to paste a TypeSafe or provider key into the conversation; keys belong in autopilot.env or the Autopilot tab." ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 55.5 } ], "editorialScores": { "ergonomics": 69, "maintenance": 43, "payments": 50, "reliability": 41, "schema": 74, "security": 53, "transparency": 58 }, "provenanceScore": 52, "checked": { "categories": { "ergonomics": "2026-11-01", "maintenance": "2026-11-01", "payments": "2026-11-01", "reliability": "2026-11-01", "schema": "2026-11-01", "security": "2026-11-01", "transparency": "2026-11-01" }, "last": "2026-11-01", "oldest": "2026-11-01", "stale": false, "staleAfterDays": 90 }, "scoreHistory": [ { "date": "2026-11-01", "grade": "C", "kind": "listed", "method": "0.7", "score": 55.5 } ] }, "connect": { "install": "# Download the plugin for your engine and OS from https://www.tryaura.dev/autopilot/ and finish the first-run setup in the editor's Autopilot tab\nautopilot connect claude\nautopilot connect codex", "claudeCode": "claude plugin install autopilot --marketplace ramenvr/autopilot", "config": { "mcpServers": { "autopilot": { "args": [ "mcp" ], "command": "autopilot" } } } }, "letme": { "capability": "https://letme.dev/desktop.control", "tool": "https://letme.dev/aura-autopilot" }, "notable": [ "Launch post and white paper by Nyx Iskandar and Andy Tsen of Ramen, dated 31 October 2026 (https://www.tryaura.dev/updates/autopilot-continually-learning-real-time-general-playtesting-system)", "Aura v1.2.3 of 30 October 2026 ships Autopilot inside Aura, and v1.2.4 the same day changes its indexing status (https://www.tryaura.dev/documentation/release-notes)", "Run sharing is on by default. It sends recordings, screenshots, agent traces and, for MCP runs, the user's Claude Code or Codex conversation to app.tryaura.dev, redacted first (https://raw.githubusercontent.com/ramenvr/autopilot/main/plugin/unreal/Autopilot/README.md)", "Model-written code runs in a child process without API keys, with bubblewrap on Linux; on Windows and macOS it keeps keys out but not network or disk (https://raw.githubusercontent.com/ramenvr/autopilot/main/autopilot/sandbox.py)", "Ramen's white paper reports 7 of 7 tasks passed and 1.7 times the speed of Claude Code on one Unreal 5.8 template game, Ramen's own measurement (https://www.tryaura.dev/autopilot/)", "Ramen (TribeVR Inc. in Aura's terms) started in Y Combinator's Summer 2019 batch as the studio behind Zenith: The Last City (https://www.ramenvr.com/who-we-are)" ], "area": "developer", "details": [ { "label": "Surface listed", "value": "The ramenvr/autopilot repository at main (Python agent service 0.1.0; Unreal, Unity and Godot plugins; the Claude Code plugin) read from raw.githubusercontent.com, with the docs, download page and launch post on tryaura.dev, on 1 November 2026. Nothing was installed or run" }, { "label": "How an agent reaches it", "value": "`autopilot mcp`, a stdio MCP server that forwards each call to the agent service the editor plugin started. The game must be open in the editor with the Autopilot tab connected. Headless runs start from the engine's command line with -Playtest=explore, verify or goal" }, { "label": "MCP tools", "value": "start_run, wait, probe, run_harness, snapshot, describe_frames, restart_level, report and frames, plus read_file, list_files, search, write_file and edit_file held to the game's folder. Writes only to the run's folder, notes.md and lib.py" }, { "label": "How it plays", "value": "A coding agent (OpenCode by default, Claude Code or Codex) reads the game's code and writes a Python harness; TypeSafe's Jev decision model picks actions in real time, and the plugin injects real input events. What it learns is kept per project as memory files" }, { "label": "Engines and platforms", "value": "Unreal Engine 5.4 to 5.8, Unity 6 (6000.0 or later) and Godot 4.7 or later, on Windows and macOS. Building from source is supported for Unreal only, on Windows" }, { "label": "Data sharing", "value": "On by default. Recordings, screenshots, agent traces and memories, and for MCP runs the user's agent conversation, go to app.tryaura.dev after redaction. The codebase export is never sent. Off from the Settings page, AUTOPILOT_SHARE=0 or -PlaytestShare=0; sent data is never deleted" }, { "label": "Headless exit codes", "value": "0 confirmed, achieved or explored; 2 denied; 3 inconclusive; 1 not achieved or an error. result.json holds the verdict, evidence and findings" }, { "label": "Company", "value": "Ramen (ramenvr.com), makers of Aura; Aura's terms and privacy policy name TribeVR Inc. Y Combinator Summer 2019, led by CEO Andy Tsen" }, { "label": "Category", "value": "Listed in desktop-automation, the closest category, because it plays a game through injected input events. No category covers game testing" } ], "unitPrices": [ { "item": "Aura Indie, billed monthly", "unit": "month", "usd": 20, "note": "Includes Autopilot; $10 a month billed annually ($120 a year). Two-week trial, no card" }, { "item": "Aura Pro", "unit": "month", "usd": 40, "note": "Includes Autopilot; $360 a year billed annually" }, { "item": "Aura Ultimate", "unit": "month", "usd": 200, "note": "Includes Autopilot; $1,800 a year billed annually" } ], "provenance": { "legalEntity": "TribeVR Inc. (named in Aura's terms of service and privacy policy), trading as Ramen", "domain": "tryaura.dev", "domainRegistered": "2025-04-29", "endpointOnVendorDomain": null, "terms": "https://www.tryaura.dev/terms-of-service", "privacy": "https://www.tryaura.dev/privacy-policy", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-11-01", "notes": [ "The repository's licence file is Apache 2.0; Aura's terms (25 June 2026) and privacy policy (27 August 2026) are TribeVR Inc.'s and don't mention Autopilot.", "RDAP gives tryaura.dev a registration date of 29 April 2025 and ramenvr.com of 16 February 2019.", "www.tryaura.dev/.well-known/security.txt answered 404. SECURITY.md in the repository asks for GitHub private vulnerability reporting.", "app.tryaura.dev, where shared run data goes and where sign-in happens, disallows ClaudeBot, anthropic-ai and Claude-Web in robots.txt and carries Content-Signal ai-train=no, so nothing on it was read.", "Local software, so there is no status page. Aura's release notes mention Autopilot; the repository has no changelog." ], "score": 52, "checks": [ { "check": "Legal entity named", "value": "TribeVR Inc. (named in Aura's terms of service and privacy policy), trading as Ramen", "points": 20, "max": 20, "state": "ok" }, { "check": "Domain age", "value": "tryaura.dev, registered 2025-04-29 (1 year)", "points": 3, "max": 15, "state": "part" }, { "check": "Endpoint on the vendor's domain", "value": "no hosted endpoint", "points": 0, "max": 0, "state": "na" }, { "check": "Terms of service", "value": "read, states 6 of the 7 things a reader expects", "points": 9.1, "max": 10, "state": "part" }, { "check": "Privacy policy", "value": "read, states 5 of the 8 things a reader expects", "points": 7.8, "max": 10, "state": "part" }, { "check": "Status page", "value": "not found", "points": 0, "max": 10, "state": "no" }, { "check": "Changelog", "value": "not found", "points": 0, "max": 10, "state": "no" }, { "check": "security.txt", "value": "not found", "points": 0, "max": 10, "state": "no" }, { "check": "People named", "value": "2 named with their role, none with a public profile", "points": 7, "max": 10, "state": "part" }, { "check": "Support route", "value": "a support address, help pages, a community", "points": 5, "max": 5, "state": "ok" } ], "policies": [ { "kind": "terms", "url": "https://www.tryaura.dev/terms-of-service", "state": "read", "readAt": "2026-11-01", "statedDate": "2026-06-25", "words": 6942, "points": 9.1, "max": 10, "expected": [ { "key": "terms.date", "label": "Gives the date it was last updated", "found": true, "quote": "Last updated·June 25, 2026", "says": "Last updated 2026-06-25" }, { "key": "terms.law", "label": "Names the governing law or courts", "found": true, "quote": "These Terms will be interpreted, construed, and enforced in all respects in accordance with the laws of the State of California, without reference to its choice of law rules and not including the provisions of the 1980 U.N.", "says": "The law of the State of California" }, { "key": "terms.liability", "label": "States a limit on its liability", "found": true, "quote": "NOTWITHSTANDING ANYTHING ELSE IN THESE TERMS, COMPANY PROVIDES NO WARRANTY, INDEMNITY, OR SUPPORT FOR EVALUATIONS, AND ITS LIABILITY FOR EVALUATIONS WILL NOT EXCEED US$50.", "says": "Capped at US$50" }, { "key": "terms.termination", "label": "Says how the agreement or account can be ended", "found": true, "quote": "Company may immediately suspend Customer’s access to Aura if: (a) Customer breaches Section 1.4 (Restrictions) or Section 1.5 (Customer Obligations);" }, { "key": "terms.changes", "label": "Says how changes to the terms are announced", "found": true, "quote": "To exercise this termination right, Customer must notify Company of its objections within 30 days after Company’s notice of the intended modifications to these Terms.", "says": "Gives 30 days of notice before a change" }, { "key": "terms.use", "label": "Lists what users may not do", "found": true, "quote": "Customer will not (and will not permit Customer’s Users or anyone else to) do any of the following: (a) provide access to, distribute, sell, or sublicense Aura to a third party (other than Users);" }, { "key": "terms.sla", "label": "Refers to a service level or uptime commitment", "found": false } ], "toKnow": [ { "key": "training.optout", "label": "Says it may use customer content to train or improve models, and gives an opt-out", "found": true, "quote": "…royalty-free, perpetual, irrevocable, worldwide, sublicensable, and transferable license to use, reproduce, modify, adapt, publish, translate, and create derivative works from Customer Data solely for the purpose of training and improving Company’s and its affiliates’ artificial intelligence models and algorithms;" } ] }, { "kind": "privacy", "url": "https://www.tryaura.dev/privacy-policy", "state": "read", "readAt": "2026-11-01", "statedDate": "2026-08-27", "words": 1950, "points": 7.8, "max": 10, "expected": [ { "key": "privacy.date", "label": "Gives the date it was last updated", "found": true, "quote": "Last updated·August 27, 2026", "says": "Last updated 2026-08-27" }, { "key": "privacy.collected", "label": "Says what personal data is collected", "found": true, "quote": "This privacy policy (the “Privacy Policy”) explains how we collect, use, and disclose information from users of our Services (“Users”)." }, { "key": "privacy.retention", "label": "Says how long data is kept", "found": false }, { "key": "privacy.processors", "label": "Says who else receives the data", "found": true, "quote": "This Privacy Policy does not apply to the extent we process information in the role of a processor or service provider on behalf of our customers (for example, on behalf of enterprise game developers)." }, { "key": "privacy.sale", "label": "Says whether personal data is sold or shared for advertising", "found": true, "quote": "For advertising purposes, such as measuring the effectiveness of our advertising, delivering interest-based advertising to you on third-party platforms, and building audiences with our advertising partners;" }, { "key": "privacy.rights", "label": "Says what rights people have over their data", "found": false }, { "key": "privacy.contact", "label": "Gives a privacy contact", "found": false }, { "key": "privacy.transfers", "label": "Says where data is transferred or stored", "found": true, "quote": "law, then please note that you are transferring your personal information outside of those regions to the U.S." } ] } ] }, "humans": { "slug": "aura-autopilot", "checked": "2026-11-01", "company": "Ramen", "people": [ { "name": "Andy Tsen", "role": "CEO and Co-founder, Ramen; co-author of the Autopilot white paper", "founder": true, "page": "/people/andy-tsen/" }, { "name": "Nyx Iskandar", "role": "Co-author of the Autopilot launch post and white paper, Ramen team", "page": "/people/nyx-iskandar/" } ], "peopleNote": "Andy Tsen is named CEO and co-founder in Ramen's Coplay acquisition post of 16 March 2026 and as founder on the Y Combinator page, which lists no other founder; the roster may be incomplete. Nyx Iskandar and Andy Tsen wrote the launch post and white paper of 31 October 2026. No personal accounts are linked from Ramen's or Aura's pages, so none is given; the YC page's LinkedIn link for Andy Tsen is a profile-id URL and was left out. The repository's CODEOWNERS names one GitHub account, not tied to a name on any page we read. Aura's terms and privacy policy name TribeVR Inc. as the company. Investors from Ramen's own posts (the Coplay acquisition post and the Series B post on zenithmmo.com), Road to VR's Series A report and the YC page; one web search.", "companySocial": { "linkedin": "https://www.linkedin.com/company/ramen-vr/", "x": "https://x.com/RamenVROfficial", "github": "https://github.com/ramenvr" }, "support": { "emails": [ "support@tryaura.dev" ], "urls": [ "https://www.tryaura.dev/documentation/autopilot", "https://www.tryaura.dev/documentation/troubleshooting", "https://github.com/ramenvr/autopilot/issues" ], "community": [ { "label": "Aura Discord", "url": "https://discord.gg/tryaura", "kind": "discord" }, { "label": "GitHub issues", "url": "https://github.com/ramenvr/autopilot/issues", "kind": "github" }, { "label": "Aura on X", "url": "https://x.com/Aura_Assistant", "kind": "x" }, { "label": "Aura on YouTube", "url": "https://www.youtube.com/@AuraGameAssistant", "kind": "link" } ], "contactEmails": [ "support@tryaura.dev" ], "contactUrls": [ "https://www.ramenvr.com/contact-us" ] }, "sources": [ "https://www.tryaura.dev/updates/ramen-acquires-coplay-making-aura-the-first-ai-agent-for-unity-and-unreal-engine", "https://www.ycombinator.com/companies/ramen-vr", "https://www.tryaura.dev/updates/autopilot-continually-learning-real-time-general-playtesting-system", "https://www.ramenvr.com/who-we-are", "https://www.ramenvr.com/", "https://www.tryaura.dev/documentation/autopilot", "https://www.tryaura.dev/terms-of-service", "https://www.tryaura.dev/privacy-policy", "https://raw.githubusercontent.com/ramenvr/autopilot/main/.github/CODEOWNERS", "https://zenithmmo.com/blogs/news/ramen-vr-closes-35m-series-b-round-led-by-anthos-and-dune", "https://www.roadtovr.com/promising-vr-mmo-zenith-last-city-just-got-huge-boost-10-million-funding/" ], "ownership": { "status": "private", "totalRaised": { "amount": "over $40M", "asOf": "2026-03", "source": "https://www.tryaura.dev/updates/ramen-acquires-coplay-making-aura-the-first-ai-agent-for-unity-and-unreal-engine" }, "checked": "2026-11-01", "sources": [ "https://www.tryaura.dev/updates/ramen-acquires-coplay-making-aura-the-first-ai-agent-for-unity-and-unreal-engine", "https://zenithmmo.com/blogs/news/ramen-vr-closes-35m-series-b-round-led-by-anthos-and-dune", "https://www.roadtovr.com/promising-vr-mmo-zenith-last-city-just-got-huge-boost-10-million-funding/", "https://www.ycombinator.com/companies/ramen-vr" ] }, "investors": [ { "name": "Y Combinator", "kind": "accelerator", "rounds": [ "Summer 2019 batch" ], "url": "https://www.ycombinator.com", "source": "https://www.ycombinator.com/companies/ramen-vr", "quote": "Batch: Summer 2019", "page": "/investors/y-combinator/" }, { "name": "Anthos Capital", "kind": "vc", "rounds": [ "Series A, September 2021", "Series B, March 2022" ], "lead": true, "url": "https://www.anthoscapital.com", "source": "https://zenithmmo.com/blogs/news/ramen-vr-closes-35m-series-b-round-led-by-anthos-and-dune", "quote": "Ramen VR Closes $35M Series B Round Led by Anthos and Dune", "page": "/investors/anthos-capital/" }, { "name": "Dune Ventures", "kind": "vc", "rounds": [ "Series A, September 2021", "Series B, March 2022" ], "lead": true, "source": "https://zenithmmo.com/blogs/news/ramen-vr-closes-35m-series-b-round-led-by-anthos-and-dune", "quote": "Ramen VR Closes $35M Series B Round Led by Anthos and Dune", "page": "/investors/dune-ventures/" }, { "name": "Makers Fund", "kind": "vc", "rounds": [ "Series A, September 2021", "Series B, March 2022" ], "source": "https://www.roadtovr.com/promising-vr-mmo-zenith-last-city-just-got-huge-boost-10-million-funding/", "quote": "raised a $10 million Series A investment with participation from VC firms Makers Fund, Anthos Capital, and Dune Ventures", "page": "/investors/makers-fund/" }, { "name": "Andrew Chen", "kind": "angel", "rounds": [ "Series B, March 2022" ], "source": "https://zenithmmo.com/blogs/news/ramen-vr-closes-35m-series-b-round-led-by-anthos-and-dune", "quote": "personal investments from Andrew Chen and James Gwertzman, general partners at Andreessen Horowitz", "page": "/investors/andrew-chen/" }, { "name": "James Gwertzman", "kind": "angel", "rounds": [ "Series B, March 2022" ], "source": "https://zenithmmo.com/blogs/news/ramen-vr-closes-35m-series-b-round-led-by-anthos-and-dune", "quote": "personal investments from Andrew Chen and James Gwertzman, general partners at Andreessen Horowitz", "page": "/investors/james-gwertzman/" } ] }, "pageJsonUrl": "https://www.anchorterminal.com/tools/aura-autopilot.json" } }