{ "data": { "similar": [ { "grade": "BB", "json": "https://www.anchorterminal.com/tools/zeroclaw.json", "name": "ZeroClaw", "score": 70.2, "shared": [ "assistant.memory", "assistant.self-hosted", "agent.mcp-client" ], "slug": "zeroclaw" }, { "grade": "B", "json": "https://www.anchorterminal.com/tools/nanoclaw.json", "name": "NanoClaw", "score": 68.3, "shared": [ "assistant.memory", "assistant.self-hosted", "agent.mcp-client" ], "slug": "nanoclaw" }, { "grade": "B", "json": "https://www.anchorterminal.com/tools/hermes-agent.json", "name": "Hermes Agent", "score": 67.9, "shared": [ "assistant.memory", "assistant.self-hosted", "agent.mcp-client" ], "slug": "hermes-agent" }, { "grade": "B", "json": "https://www.anchorterminal.com/tools/openclaw.json", "name": "OpenClaw", "score": 67.1, "shared": [ "assistant.memory", "assistant.self-hosted", "agent.mcp-client" ], "slug": "openclaw" }, { "grade": "B", "json": "https://www.anchorterminal.com/tools/ironclaw.json", "name": "IronClaw", "score": 66.7, "shared": [ "assistant.memory", "assistant.self-hosted", "agent.mcp-client" ], "slug": "ironclaw" }, { "grade": "B", "json": "https://www.anchorterminal.com/tools/nanobot.json", "name": "nanobot", "score": 62.4, "shared": [ "assistant.memory", "assistant.self-hosted", "agent.mcp-client" ], "slug": "nanobot" } ], "tool": { "slug": "atticus", "name": "Atticus", "vendor": "SaarthurR (Saarth Ranka)", "vendorUrl": "https://saarthurr.github.io/atticus-mac/", "kind": "platform", "category": "personal-assistants", "summary": "Atticus is an open-source macOS menu bar assistant that takes spoken or typed requests and operates apps, windows, files and the web, using the owner's Claude Code or Devin CLI plan as its model.", "url": "https://www.anchorterminal.com/tools/atticus", "markdownUrl": "https://www.anchorterminal.com/tools/atticus.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/atticus.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/atticus.json", "repo": "https://github.com/SaarthurR/atticus-mac", "license": "MIT", "transports": [], "packages": [], "auth": "none", "authNotes": "No Atticus account. The app calls `claude -p` on the owner's signed-in Claude Pro or Max plan, or the Devin CLI on a Devin plan, so no API key is pasted. A $5 Gumroad licence check existed until 11 October 2026 and is switched off in the source.", "pricing": "byo-plan", "pricingNotes": "Free under MIT. It needs a paid Claude Pro or Max plan through Claude Code, or a Devin plan through the Devin CLI. The README estimates about 0.18 US cents of plan usage per AI request at API list rates. The source keeps a Gumroad product ID for \"when sales start\".", "priceSummary": "Your plan", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the source, the README or the project site (checked 2026-10-15). The app has nothing to buy.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 163, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-15" }, "docsUrl": "https://github.com/SaarthurR/atticus-mac#readme", "capabilities": [ "assistant.memory", "assistant.self-hosted", "agent.mcp-client", "desktop.control", "meetings.transcript", "meetings.summary" ], "tags": [ "not-for-agents", "open-source", "local", "free", "no-card", "byo-plan", "mit", "macos", "swift", "python", "voice", "claude-code", "desktop-app", "telemetry-default-on", "approvals" ], "lastRelease": "2026-10-14", "graded": true, "anchor": { "graded": true, "score": 42.9, "grade": "E", "agentReady": false, "rank": 974, "ranked": true, "rankOf": 1094, "categoryRank": 16, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 9, "maintenance": 51, "payments": 60, "reliability": 68, "schema": 15, "security": 49, "transparency": 56 }, "pending": [ "performance", "tasks" ], "breakdown": [ { "key": "reliability", "name": "Reliability", "weight": 16, "effectiveWeight": 20, "score": 68, "points": 13.6, "reason": "Read with the local-software lines, as software the owner runs. It installs by a curl-to-bash script that clones the repository and builds the app, or a Nix flake that runs the same script, with macOS 26 and Apple's command line tools stated. No package or built binary is published (15 of 20). A public GitHub Actions workflow runs 301 offline tests and an installer syntax check on Ubuntu. 21 of the last 26 runs on main passed, the newest on 15 October 2026 included, and installed copies follow main rather than tags (15 of 25). Five issues and pull requests, all from one contributor. Four were answered and closed within six hours and one, of 13 October, has no reply. No crash reports filed (18 of 25). Two tagged releases with notes. No changelog file and no breaking changes marked, while dozens of untagged commits reach users through the self-update (5 of 15). Tagged v1.0 on 13 October 2026 (15). Total 68." }, { "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": 15, "points": 2.44, "reason": "Graded on the interface an outside agent can use. Atticus has no API, MCP server or documented command for another agent, so there is no machine-readable contract (0). No llms.txt on the project site (404) (0). The README explains each function for a person, with what it does and does not do, such as drafts that are never sent (6 of 20). No typed inputs (0). A table of example requests and documented install, test and removal commands (4 of 15). Two tagged releases with dated notes, no changelog file (5 of 15). The internal `atticus.py` flags its own model calls are not documented as an interface. Total 15." }, { "key": "ergonomics", "name": "Agent ergonomics", "weight": 13, "effectiveWeight": 16.25, "score": 9, "points": 1.46, "reason": "These lines measure an interface an agent calls, and Atticus has none. No response sizing (0) and no pagination or filtering (0). Failures are reported to a person in the overlay, with a Try again control (2 of 20). Destructive commands ask first, deletes go to the Trash, and interrupted actions are checked before a retry, per the agent prompt (3 of 20). One install line and few settings, but a paid Claude or Devin plan, macOS 26 and several macOS permissions are needed. No SDK (4 of 15). Total 9." }, { "key": "security", "name": "Security \u0026 auth", "weight": 14, "effectiveWeight": 17.5, "score": 49, "points": 8.57, "reason": "Harness reading of the framework checklist, as for other software that acts on the owner's machine. 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. Speech is turned into text on the Mac. Request text, screen text and screenshots go to Anthropic or Devin through the owner's CLI, a daily random ID goes to PostHog by default, AI meeting summaries send transcripts to Claude by default, and the app pulls and builds the main branch every six hours by default with no signature or review step (15 of 30). Safe mode is on by default. The model's shell commands run in Claude Code's sandbox with writes limited to a scratch folder, app-control commands on an allowlist run outside it, delete, send, buy, file-change and system commands ask first by pattern, and rm, sudo, dd, diskutil, shutdown and git push are denied. Main requests run with `bypassPermissions` behind Atticus's own hook, and Full access mode drops some prompts (14 of 20). Every system prompt we read marks screen text, tool output and supplied context as untrusted data, and the meeting filter has no tools. No user-facing guidance on prompt injection (9 of 15). Every request, step and cost goes to ~/.config/atticus/log.jsonl, mode 0600, and the README says each exact command is in the ask log (11 of 15). No SECURITY.md, security.txt, bug bounty or advisories (0 of 20). Total 49." }, { "key": "payments", "name": "Payments \u0026 pricing", "weight": 10, "effectiveWeight": 12.5, "score": 60, "points": 7.5, "reason": "No payment protocol (0). Read with the self-hosted rule. Free under MIT with nothing to buy since 11 October 2026, when the $5 Gumroad licence check was switched off. The source keeps the product ID for when sales start (20). No card or Atticus account, though a paid Claude Pro or Max plan or a Devin plan is required (20). Install with one command and no signup with Atticus (20). Total 60." }, { "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": 51, "points": 4.46, "reason": "v1.1 on 14 October 2026 (30). Two tagged releases in the project's five days. The checklist asks for three (0). Four of five issues and pull requests answered within six hours, one open for two days without a reply, on a small sample (15 of 25). Not an MCP server and no SDK (0). The app uses the Python standard library and Swift with no third-party packages to fall behind, and CI runs on every push, with five failures on main since 13 October (6 of 10). Total 51." }, { "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7, "effectiveWeight": 8.75, "score": 56, "points": 4.9, "note": "editorial 58, provenance 53", "reason": "MIT in LICENSE and as detected by GitHub, with the bundled thinking-orbs and Plip code under MIT and credited (30). No privacy policy or terms. The README says what leaves the Mac (the daily PostHog ID, opt-in failure reports scrubbed first, AI summaries on the owner's plan) and that audio and the mini screen preview stay local, which matches the source we read. No retention period for PostHog data is stated (12 of 30). No deprecation policy, and the project is five days old (0). The daily usage ping is disclosed in the README and setup, with an opt-out in Settings and by environment variable, but is on by default (16 of 20). Total 58." } ], "assessment": { "date": "2026-10-15", "basis": "public evidence", "confidence": "medium", "notes": { "ergonomics": "These lines measure an interface an agent calls, and Atticus has none. No response sizing (0) and no pagination or filtering (0). Failures are reported to a person in the overlay, with a Try again control (2 of 20). Destructive commands ask first, deletes go to the Trash, and interrupted actions are checked before a retry, per the agent prompt (3 of 20). One install line and few settings, but a paid Claude or Devin plan, macOS 26 and several macOS permissions are needed. No SDK (4 of 15). Total 9.", "maintenance": "v1.1 on 14 October 2026 (30). Two tagged releases in the project's five days. The checklist asks for three (0). Four of five issues and pull requests answered within six hours, one open for two days without a reply, on a small sample (15 of 25). Not an MCP server and no SDK (0). The app uses the Python standard library and Swift with no third-party packages to fall behind, and CI runs on every push, with five failures on main since 13 October (6 of 10). Total 51.", "payments": "No payment protocol (0). Read with the self-hosted rule. Free under MIT with nothing to buy since 11 October 2026, when the $5 Gumroad licence check was switched off. The source keeps the product ID for when sales start (20). No card or Atticus account, though a paid Claude Pro or Max plan or a Devin plan is required (20). Install with one command and no signup with Atticus (20). Total 60.", "reliability": "Read with the local-software lines, as software the owner runs. It installs by a curl-to-bash script that clones the repository and builds the app, or a Nix flake that runs the same script, with macOS 26 and Apple's command line tools stated. No package or built binary is published (15 of 20). A public GitHub Actions workflow runs 301 offline tests and an installer syntax check on Ubuntu. 21 of the last 26 runs on main passed, the newest on 15 October 2026 included, and installed copies follow main rather than tags (15 of 25). Five issues and pull requests, all from one contributor. Four were answered and closed within six hours and one, of 13 October, has no reply. No crash reports filed (18 of 25). Two tagged releases with notes. No changelog file and no breaking changes marked, while dozens of untagged commits reach users through the self-update (5 of 15). Tagged v1.0 on 13 October 2026 (15). Total 68.", "schema": "Graded on the interface an outside agent can use. Atticus has no API, MCP server or documented command for another agent, so there is no machine-readable contract (0). No llms.txt on the project site (404) (0). The README explains each function for a person, with what it does and does not do, such as drafts that are never sent (6 of 20). No typed inputs (0). A table of example requests and documented install, test and removal commands (4 of 15). Two tagged releases with dated notes, no changelog file (5 of 15). The internal `atticus.py` flags its own model calls are not documented as an interface. Total 15.", "security": "Harness reading of the framework checklist, as for other software that acts on the owner's machine. 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. Speech is turned into text on the Mac. Request text, screen text and screenshots go to Anthropic or Devin through the owner's CLI, a daily random ID goes to PostHog by default, AI meeting summaries send transcripts to Claude by default, and the app pulls and builds the main branch every six hours by default with no signature or review step (15 of 30). Safe mode is on by default. The model's shell commands run in Claude Code's sandbox with writes limited to a scratch folder, app-control commands on an allowlist run outside it, delete, send, buy, file-change and system commands ask first by pattern, and rm, sudo, dd, diskutil, shutdown and git push are denied. Main requests run with `bypassPermissions` behind Atticus's own hook, and Full access mode drops some prompts (14 of 20). Every system prompt we read marks screen text, tool output and supplied context as untrusted data, and the meeting filter has no tools. No user-facing guidance on prompt injection (9 of 15). Every request, step and cost goes to ~/.config/atticus/log.jsonl, mode 0600, and the README says each exact command is in the ask log (11 of 15). No SECURITY.md, security.txt, bug bounty or advisories (0 of 20). Total 49.", "transparency": "MIT in LICENSE and as detected by GitHub, with the bundled thinking-orbs and Plip code under MIT and credited (30). No privacy policy or terms. The README says what leaves the Mac (the daily PostHog ID, opt-in failure reports scrubbed first, AI summaries on the owner's plan) and that audio and the mini screen preview stay local, which matches the source we read. No retention period for PostHog data is stated (12 of 30). No deprecation policy, and the project is five days old (0). The daily usage ping is disclosed in the README and setup, with an opt-out in Settings and by environment variable, but is on by default (16 of 20). Total 58." }, "sources": [ { "what": "repository, README and LICENSE", "url": "https://github.com/SaarthurR/atticus-mac", "seen": "2026-10-15" }, { "what": "commit history (first commit 10 October 2026 UTC)", "url": "https://github.com/SaarthurR/atticus-mac/commits/main", "seen": "2026-10-15" }, { "what": "releases v1.0 and v1.1", "url": "https://github.com/SaarthurR/atticus-mac/releases", "seen": "2026-10-15" }, { "what": "app source (safe mode, deny list, telemetry, licence check, internal flags)", "url": "https://github.com/SaarthurR/atticus-mac/blob/main/atticus.py", "seen": "2026-10-15" }, { "what": "app source (self-updater, default settings)", "url": "https://github.com/SaarthurR/atticus-mac/blob/main/Atticus.swift", "seen": "2026-10-15" }, { "what": "installer", "url": "https://github.com/SaarthurR/atticus-mac/blob/main/install.sh", "seen": "2026-10-15" }, { "what": "CI workflow", "url": "https://github.com/SaarthurR/atticus-mac/blob/main/.github/workflows/checks.yml", "seen": "2026-10-15" }, { "what": "CI runs on main", "url": "https://api.github.com/repos/SaarthurR/atticus-mac/actions/runs?branch=main", "seen": "2026-10-15" }, { "what": "issues and pull requests", "url": "https://api.github.com/repos/SaarthurR/atticus-mac/issues?state=all", "seen": "2026-10-15" }, { "what": "commit switching off the $5 licence check", "url": "https://github.com/SaarthurR/atticus-mac/commit/7ff97be8ac95e70c87cdaecedd2a26b8a66df6ed", "seen": "2026-10-15" }, { "what": "project site", "url": "https://saarthurr.github.io/atticus-mac/", "seen": "2026-10-15" }, { "what": "security.txt, llms.txt and privacy on the project site (404)", "url": "https://saarthurr.github.io/atticus-mac/.well-known/security.txt", "seen": "2026-10-15" }, { "what": "Show HN post of 12 October 2026", "url": "https://news.ycombinator.com/item?id=50049588", "seen": "2026-10-15" }, { "what": "maintainer's GitHub profile", "url": "https://api.github.com/users/SaarthurR", "seen": "2026-10-15" } ], "openQuestions": [ "Judgement call. Listed in personal assistants because it works for one person, remembers them and runs background agents with their connectors. Desktop automation was the alternative, but that category is for tools an agent starts, and Atticus has no such interface. Tagged `not-for-agents`.", "The lead matched. The repository's first commit is \"Atticus: a voice assistant for your Mac\", 10 October 2026 01:07 UTC (9 October in the author's time zone). `firstReleased` is the first tag, v1.0 on 13 October 2026. The Show HN post of 12 October shows it was public by then. Whether the repository was public on 10 October was not established.", "`atticus.py` accepts internal flags (`--place`, `--hands`, `--look`, `--fast` and a plain request) that a shell-capable agent could call on a Mac where Atticus is installed. They are undocumented as an interface and change with each commit, so they were not graded as one.", "The source still holds a Gumroad product ID labelled for when sales start, so the price may return.", "We did not install or run the app. Every claim about behaviour comes from the source, the README and the release notes." ] }, "negative": 0, "verdict": "Atticus runs a person's Mac by voice on their existing Claude or Devin plan, with a sandboxed safe mode and a local log of every command. It has no API, MCP server or documented command for another agent, it is five days old, and it rebuilds itself from the main branch every six hours by default.", "bestFor": "A person on macOS 26 with a Claude Pro or Max plan who wants voice control of apps, windows, files and the browser.", "strengths": [ "MIT source, with 301 offline tests run by public CI on every push", "Safe mode on by default, with sandboxed shell commands, prompts before delete, send or buy, and rm and sudo denied", "Every request, step and cost logged locally in ~/.config/atticus/log.jsonl", "Speech recognised on the Mac, and simple requests run with no model call", "Telemetry described in the README, with a daily ping that can be turned off and failure reports off by default" ], "weaknesses": [ "No API, MCP server or documented command an outside agent can call", "Pulls and builds the main branch every six hours by default, with no signed or tagged release step", "Five days old, one maintainer, two tagged releases and no changelog or deprecation policy", "No privacy policy, SECURITY.md or security.txt", "Needs macOS 26 and a paid Claude Pro or Max plan or a Devin plan" ], "agentNotes": [ "Don't plan to call Atticus from another agent. It takes requests only from its own shortcut and typing box", "If a user runs Atticus beside you, expect it to move windows and type into apps on the same Mac", "Point a user who wants pinned versions to Settings \u003e About \u0026 Updates to turn off self-update" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "E", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 42.9 } ], "editorialScores": { "ergonomics": 9, "maintenance": 51, "payments": 60, "reliability": 68, "schema": 15, "security": 49, "transparency": 58 }, "provenanceScore": 53 }, "connect": { "install": "curl -fsSL https://raw.githubusercontent.com/SaarthurR/atticus-mac/main/install.sh | bash" }, "letme": { "capability": "https://letme.dev/assistant.memory", "tool": "https://letme.dev/atticus" }, "notable": [ "The repository's first commit, \"Atticus: a voice assistant for your Mac\", is dated 10 October 2026 01:07 UTC (9 October in the author's time zone), the repository's creation time (https://github.com/SaarthurR/atticus-mac/commits/main)", "A Show HN post of 12 October 2026 linked the repository and drew 115 points and 30 comments (https://news.ycombinator.com/item?id=50049588)", "Tagged releases v1.0 on 13 October and v1.1 on 14 October 2026 (https://github.com/SaarthurR/atticus-mac/releases)", "The app pulls the main branch and rebuilds itself from source every six hours, on by default, rather than installing tagged releases (https://github.com/SaarthurR/atticus-mac/blob/main/Atticus.swift)", "Safe mode, on by default, runs the model's shell commands in Claude Code's sandbox, asks before deleting, sending, buying or changing a file, and blocks rm, sudo, dd, diskutil, shutdown and git push (https://github.com/SaarthurR/atticus-mac/blob/main/atticus.py)", "Once a day a random ID goes to PostHog, on by default with an opt-out in Settings. Failure reports are opt-in and scrubbed on the Mac first (https://github.com/SaarthurR/atticus-mac#usage-count)", "Sold for $5 once through Gumroad until 11 October 2026, when the licence check was switched off (https://github.com/SaarthurR/atticus-mac/commit/7ff97be8ac95e70c87cdaecedd2a26b8a66df6ed)" ], "area": "frameworks", "details": [ { "label": "Surface listed", "value": "The macOS app at commit f5b58e3 (14 October 2026), read from the repository, README, release notes and project site on 15 October 2026. Nothing was installed or run" }, { "label": "Interfaces", "value": "A menu bar app for one person, driven by a hold-to-talk shortcut or a typing box. No API, MCP server or documented command for an outside agent. `atticus.py` has internal flags (`--place`, `--hands`, `--look` and others) that its own model calls, undocumented in the README" }, { "label": "Model", "value": "Claude Code (`claude -p`, Haiku by default in the source) or the Devin CLI, chosen in Settings. Simple requests such as opening apps and moving windows run without a model" }, { "label": "Background agents", "value": "Large requests go to a background Claude Code agent that can use the owner's MCP connectors, skills and plugins once switched on in Settings \u003e Agents" }, { "label": "Approvals", "value": "Safe mode on by default. Asks before delete, send, buy, file changes and system commands, matched by pattern. Deletes go to the Trash. Full access mode removes some prompts when the request is explicit" }, { "label": "Memory", "value": "Saved rules, learned shortcuts and a profile in ~/.config/atticus, editable in Settings" }, { "label": "Meetings", "value": "Meeting Copilot saves transcripts locally by default (folders 0700, files 0600). AI meeting summaries, on by default, send the transcript to Claude after each call" }, { "label": "Telemetry", "value": "Daily random ID to PostHog, on by default, off in Settings or with an empty `ATTICUS_POSTHOG_KEY`. Failure reports off until the user agrees" }, { "label": "Updates", "value": "Pulls the main branch every six hours and rebuilds, on by default, skipped when the clone has local changes" }, { "label": "Platforms", "value": "macOS 26 or later, with Apple's command line tools. A community fork for Windows exists, FindlayHi/atticus-windows, not reviewed" }, { "label": "Age", "value": "Five days old on 15 October 2026. 58 commits since 10 October, two tagged releases" } ], "provenance": { "legalEntity": "Saarth Ranka (GitHub SaarthurR), individual", "domain": "saarthurr.github.io", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://github.com/SaarthurR/atticus-mac/releases", "securityTxt": "none", "checked": "2026-10-15", "notes": [ "The commit author is Saarth Ranka. The GitHub account SaarthurR lists saarthranka.com and California and was created in January 2023. No company is named.", "The project site is a GitHub Pages page with no terms or privacy policy. /privacy, /llms.txt and /.well-known/security.txt answered 404 on 15 October 2026. The repository has no SECURITY.md.", "The software runs on the owner's Mac, so there is no vendor endpoint or status page to check. Telemetry goes to PostHog's US capture endpoint." ], "score": 53, "checks": [ { "check": "Legal entity named", "value": "Saarth Ranka (GitHub SaarthurR), individual", "points": 20, "max": 20, "state": "ok" }, { "check": "Domain age", "value": "saarthurr.github.io, no registry record we could read", "points": 0, "max": 15, "state": "no" }, { "check": "Endpoint on the vendor's domain", "value": "no hosted endpoint", "points": 0, "max": 0, "state": "na" }, { "check": "Terms of service", "value": "nothing hosted, so the MIT licence stands in", "points": 10, "max": 10, "state": "ok" }, { "check": "Privacy policy", "value": "nothing hosted, not scored", "points": 0, "max": 0, "state": "na" }, { "check": "Status page", "value": "not found", "points": 0, "max": 10, "state": "no" }, { "check": "Changelog", "value": "published", "points": 10, "max": 10, "state": "ok" }, { "check": "security.txt", "value": "not found", "points": 0, "max": 10, "state": "no" } ] }, "pageJsonUrl": "https://www.anchorterminal.com/tools/atticus.json" }, "verify": { "accepts": "a page on saarthurr.github.io or one of its subdomains, or the README of github.com/SaarthurR/atticus-mac", "badgeUrl": "https://www.anchorterminal.com/badges/atticus.svg", "body": { "slug": "atticus", "url": "the page with the badge or the link" }, "docs": "https://www.anchorterminal.com/builders/#verify", "effect": "none, it never changes a grade, rank or review", "endpoint": "https://www.anchorterminal.com/api/v1/verify", "listingUrl": "https://www.anchorterminal.com/tools/atticus", "mcpTool": "verify_listing", "recheck": "weekly; two failed checks in a row and it lapses, a later pass restores it", "snippets": { "html": "\u003ca href=\"https://www.anchorterminal.com/tools/atticus\"\u003e\u003cimg src=\"https://www.anchorterminal.com/badges/atticus.svg\" alt=\"Atticus on Anchor Terminal\" height=\"20\"\u003e\u003c/a\u003e", "markdown": "[![Atticus on Anchor Terminal](https://www.anchorterminal.com/badges/atticus.svg)](https://www.anchorterminal.com/tools/atticus)", "link": "\u003ca href=\"https://www.anchorterminal.com/tools/atticus\"\u003eAtticus on Anchor Terminal\u003c/a\u003e" } } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/tools/atticus", "json": "https://www.anchorterminal.com/tools/atticus.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/tools/atticus.md", "slim": "https://www.anchorterminal.com/tools/atticus.min.md" }, "markdown": "## Overview\n\n**Grade E · 42.9/100 · rank #974 of 1094 · #16 in Personal assistants · not agent-ready · not for agents · confidence medium**\n\n\n## Assessment\n\nAtticus runs a person's Mac by voice on their existing Claude or Devin plan, with a sandboxed safe mode and a local log of every command. It has no API, MCP server or documented command for another agent, it is five days old, and it rebuilds itself from the main branch every six hours by default.\n\n## Facts\n\n| Field | Value |\n| --- | --- |\n| Vendor | SaarthurR (Saarth Ranka) (https://saarthurr.github.io/atticus-mac/) |\n| Kind | Platform |\n| Category | Personal assistants (https://www.anchorterminal.com/categories/personal-assistants) |\n| Auth | None · No Atticus account. The app calls `claude -p` on the owner's signed-in Claude Pro or Max plan, or the Devin CLI on a Devin plan, so no API key is pasted. A $5 Gumroad licence check existed until 11 October 2026 and is switched off in the source. |\n| Pricing | Your plan (Your plan) · Free under MIT. It needs a paid Claude Pro or Max plan through Claude Code, or a Devin plan through the Devin CLI. The README estimates about 0.18 US cents of plan usage per AI request at API list rates. The source keeps a Gumroad product ID for \"when sales start\". |\n| x402 | No · No x402, MPP or L402 in the source, the README or the project site (checked 2026-10-15). The app has nothing to buy. |\n| Licence | MIT |\n| Source | https://github.com/SaarthurR/atticus-mac |\n| Docs | https://github.com/SaarthurR/atticus-mac#readme |\n| llms.txt | not found |\n| Last release | 2026-10-14 |\n| GitHub stars | 163 (as of 2026-10-15) |\n| Surface listed | The macOS app at commit f5b58e3 (14 October 2026), read from the repository, README, release notes and project site on 15 October 2026. Nothing was installed or run |\n| Interfaces | A menu bar app for one person, driven by a hold-to-talk shortcut or a typing box. No API, MCP server or documented command for an outside agent. `atticus.py` has internal flags (`--place`, `--hands`, `--look` and others) that its own model calls, undocumented in the README |\n| Model | Claude Code (`claude -p`, Haiku by default in the source) or the Devin CLI, chosen in Settings. Simple requests such as opening apps and moving windows run without a model |\n| Background agents | Large requests go to a background Claude Code agent that can use the owner's MCP connectors, skills and plugins once switched on in Settings \u003e Agents |\n| Approvals | Safe mode on by default. Asks before delete, send, buy, file changes and system commands, matched by pattern. Deletes go to the Trash. Full access mode removes some prompts when the request is explicit |\n| Memory | Saved rules, learned shortcuts and a profile in ~/.config/atticus, editable in Settings |\n| Meetings | Meeting Copilot saves transcripts locally by default (folders 0700, files 0600). AI meeting summaries, on by default, send the transcript to Claude after each call |\n| Telemetry | Daily random ID to PostHog, on by default, off in Settings or with an empty `ATTICUS_POSTHOG_KEY`. Failure reports off until the user agrees |\n| Updates | Pulls the main branch every six hours and rebuilds, on by default, skipped when the clone has local changes |\n| Platforms | macOS 26 or later, with Apple's command line tools. A community fork for Windows exists, FindlayHi/atticus-windows, not reviewed |\n| Age | Five days old on 15 October 2026. 58 commits since 10 October, two tagged releases |\n| Capabilities | assistant.memory, assistant.self-hosted, agent.mcp-client, desktop.control, meetings.transcript, meetings.summary |\n| Tags | not-for-agents, open-source, local, free, no-card, byo-plan, mit, macos, swift, python, voice, claude-code, desktop-app, telemetry-default-on, approvals |\n| JSON | https://www.anchorterminal.com/api/v1/tools/atticus.json |\n\n## Score breakdown (methodology v0.4, October 2026 research run)\n\nAssessed 2026-10-15 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.\n\n| Category | Weight | This run | Score (0–100) | Points |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% | 20 | 68 | 13.6 |\n| Performance | 10% | pending | pending | n/a |\n| Schema \u0026 documentation | 13% | 16.2 | 15 | 2.4 |\n| Agent ergonomics | 13% | 16.2 | 9 | 1.5 |\n| Security \u0026 auth | 14% | 17.5 | 49 | 8.6 |\n| Payments \u0026 pricing | 10% | 12.5 | 60 | 7.5 |\n| Task success | 10% | pending | pending | n/a |\n| Maintenance \u0026 community | 7% | 8.8 | 51 | 4.5 |\n| Transparency \u0026 trust (editorial 58, provenance 53) | 7% | 8.8 | 56 | 4.9 |\n| Negative events | up to −15 | up to −15 | none recorded | 0 |\n| **Total** | | | | **42.9 → E** |\n\n### Why each score\n\n- Reliability 68: Read with the local-software lines, as software the owner runs. It installs by a curl-to-bash script that clones the repository and builds the app, or a Nix flake that runs the same script, with macOS 26 and Apple's command line tools stated. No package or built binary is published (15 of 20). A public GitHub Actions workflow runs 301 offline tests and an installer syntax check on Ubuntu. 21 of the last 26 runs on main passed, the newest on 15 October 2026 included, and installed copies follow main rather than tags (15 of 25). Five issues and pull requests, all from one contributor. Four were answered and closed within six hours and one, of 13 October, has no reply. No crash reports filed (18 of 25). Two tagged releases with notes. No changelog file and no breaking changes marked, while dozens of untagged commits reach users through the self-update (5 of 15). Tagged v1.0 on 13 October 2026 (15). Total 68.\n- 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.\n- Schema \u0026 documentation 15: Graded on the interface an outside agent can use. Atticus has no API, MCP server or documented command for another agent, so there is no machine-readable contract (0). No llms.txt on the project site (404) (0). The README explains each function for a person, with what it does and does not do, such as drafts that are never sent (6 of 20). No typed inputs (0). A table of example requests and documented install, test and removal commands (4 of 15). Two tagged releases with dated notes, no changelog file (5 of 15). The internal `atticus.py` flags its own model calls are not documented as an interface. Total 15.\n- Agent ergonomics 9: These lines measure an interface an agent calls, and Atticus has none. No response sizing (0) and no pagination or filtering (0). Failures are reported to a person in the overlay, with a Try again control (2 of 20). Destructive commands ask first, deletes go to the Trash, and interrupted actions are checked before a retry, per the agent prompt (3 of 20). One install line and few settings, but a paid Claude or Devin plan, macOS 26 and several macOS permissions are needed. No SDK (4 of 15). Total 9.\n- Security \u0026 auth 49: Harness reading of the framework checklist, as for other software that acts on the owner's machine. 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. Speech is turned into text on the Mac. Request text, screen text and screenshots go to Anthropic or Devin through the owner's CLI, a daily random ID goes to PostHog by default, AI meeting summaries send transcripts to Claude by default, and the app pulls and builds the main branch every six hours by default with no signature or review step (15 of 30). Safe mode is on by default. The model's shell commands run in Claude Code's sandbox with writes limited to a scratch folder, app-control commands on an allowlist run outside it, delete, send, buy, file-change and system commands ask first by pattern, and rm, sudo, dd, diskutil, shutdown and git push are denied. Main requests run with `bypassPermissions` behind Atticus's own hook, and Full access mode drops some prompts (14 of 20). Every system prompt we read marks screen text, tool output and supplied context as untrusted data, and the meeting filter has no tools. No user-facing guidance on prompt injection (9 of 15). Every request, step and cost goes to ~/.config/atticus/log.jsonl, mode 0600, and the README says each exact command is in the ask log (11 of 15). No SECURITY.md, security.txt, bug bounty or advisories (0 of 20). Total 49.\n- Payments \u0026 pricing 60: No payment protocol (0). Read with the self-hosted rule. Free under MIT with nothing to buy since 11 October 2026, when the $5 Gumroad licence check was switched off. The source keeps the product ID for when sales start (20). No card or Atticus account, though a paid Claude Pro or Max plan or a Devin plan is required (20). Install with one command and no signup with Atticus (20). Total 60.\n- 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.\n- Maintenance \u0026 community 51: v1.1 on 14 October 2026 (30). Two tagged releases in the project's five days. The checklist asks for three (0). Four of five issues and pull requests answered within six hours, one open for two days without a reply, on a small sample (15 of 25). Not an MCP server and no SDK (0). The app uses the Python standard library and Swift with no third-party packages to fall behind, and CI runs on every push, with five failures on main since 13 October (6 of 10). Total 51.\n- Transparency \u0026 trust 56: MIT in LICENSE and as detected by GitHub, with the bundled thinking-orbs and Plip code under MIT and credited (30). No privacy policy or terms. The README says what leaves the Mac (the daily PostHog ID, opt-in failure reports scrubbed first, AI summaries on the owner's plan) and that audio and the mini screen preview stay local, which matches the source we read. No retention period for PostHog data is stated (12 of 30). No deprecation policy, and the project is five days old (0). The daily usage ping is disclosed in the README and setup, with an opt-out in Settings and by environment variable, but is on by default (16 of 20). Total 58.\n\nFix list for a coding agent, everything this grade says the listing lacks, the biggest gain first (15 items): https://www.anchorterminal.com/fixes/atticus.md (JSON https://www.anchorterminal.com/fixes/atticus.json)\n\n### What we couldn't check\n\n- Judgement call. Listed in personal assistants because it works for one person, remembers them and runs background agents with their connectors. Desktop automation was the alternative, but that category is for tools an agent starts, and Atticus has no such interface. Tagged `not-for-agents`.\n- The lead matched. The repository's first commit is \"Atticus: a voice assistant for your Mac\", 10 October 2026 01:07 UTC (9 October in the author's time zone). `firstReleased` is the first tag, v1.0 on 13 October 2026. The Show HN post of 12 October shows it was public by then. Whether the repository was public on 10 October was not established.\n- `atticus.py` accepts internal flags (`--place`, `--hands`, `--look`, `--fast` and a plain request) that a shell-capable agent could call on a Mac where Atticus is installed. They are undocumented as an interface and change with each commit, so they were not graded as one.\n- The source still holds a Gumroad product ID labelled for when sales start, so the price may return.\n- We did not install or run the app. Every claim about behaviour comes from the source, the README and the release notes.\n\n### Sources\n\n- repository, README and LICENSE: \u003chttps://github.com/SaarthurR/atticus-mac\u003e (seen 2026-10-15)\n- commit history (first commit 10 October 2026 UTC): \u003chttps://github.com/SaarthurR/atticus-mac/commits/main\u003e (seen 2026-10-15)\n- releases v1.0 and v1.1: \u003chttps://github.com/SaarthurR/atticus-mac/releases\u003e (seen 2026-10-15)\n- app source (safe mode, deny list, telemetry, licence check, internal flags): \u003chttps://github.com/SaarthurR/atticus-mac/blob/main/atticus.py\u003e (seen 2026-10-15)\n- app source (self-updater, default settings): \u003chttps://github.com/SaarthurR/atticus-mac/blob/main/Atticus.swift\u003e (seen 2026-10-15)\n- installer: \u003chttps://github.com/SaarthurR/atticus-mac/blob/main/install.sh\u003e (seen 2026-10-15)\n- CI workflow: \u003chttps://github.com/SaarthurR/atticus-mac/blob/main/.github/workflows/checks.yml\u003e (seen 2026-10-15)\n- CI runs on main: \u003chttps://api.github.com/repos/SaarthurR/atticus-mac/actions/runs?branch=main\u003e (seen 2026-10-15)\n- issues and pull requests: \u003chttps://api.github.com/repos/SaarthurR/atticus-mac/issues?state=all\u003e (seen 2026-10-15)\n- commit switching off the $5 licence check: \u003chttps://github.com/SaarthurR/atticus-mac/commit/7ff97be8ac95e70c87cdaecedd2a26b8a66df6ed\u003e (seen 2026-10-15)\n- project site: \u003chttps://saarthurr.github.io/atticus-mac/\u003e (seen 2026-10-15)\n- security.txt, llms.txt and privacy on the project site (404): \u003chttps://saarthurr.github.io/atticus-mac/.well-known/security.txt\u003e (seen 2026-10-15)\n- Show HN post of 12 October 2026: \u003chttps://news.ycombinator.com/item?id=50049588\u003e (seen 2026-10-15)\n- maintainer's GitHub profile: \u003chttps://api.github.com/users/SaarthurR\u003e (seen 2026-10-15)\n\n## Who's behind it (provenance 53/100, checked 2026-10-15)\n\n| Check | Finding | Points |\n| --- | --- | --- |\n| Legal entity named | Saarth Ranka (GitHub SaarthurR), individual | 20/20 |\n| Domain age | saarthurr.github.io, no registry record we could read | 0/15 |\n| Endpoint on the vendor's domain | no hosted endpoint | n/a |\n| Terms of service | nothing hosted, so the MIT licence stands in | 10/10 |\n| Privacy policy | nothing hosted, not scored | n/a |\n| Status page | not found | 0/10 |\n| Changelog | published | 10/10 |\n| security.txt | not found | 0/10 |\n\nThe commit author is Saarth Ranka. The GitHub account SaarthurR lists saarthranka.com and California and was created in January 2023. No company is named.\n\nThe project site is a GitHub Pages page with no terms or privacy policy. /privacy, /llms.txt and /.well-known/security.txt answered 404 on 15 October 2026. The repository has no SECURITY.md.\n\nThe software runs on the owner's Mac, so there is no vendor endpoint or status page to check. Telemetry goes to PostHog's US capture endpoint.\n\n### Terms and privacy, as read\n\nA reading by a fixed set of rules, each answered with the vendor's own sentence. Not legal advice.\n\n**Terms of service**. Nothing is hosted by the vendor, so there are no terms of service to read. The MIT licence stands in and the check scores in full.\n\n\n**Privacy policy**. Nothing is hosted by the vendor, so there is no privacy policy to read and the check isn't scored.\n\n\n## Probe metrics\n\nNot 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.\n\n## Strengths\n\n- MIT source, with 301 offline tests run by public CI on every push\n- Safe mode on by default, with sandboxed shell commands, prompts before delete, send or buy, and rm and sudo denied\n- Every request, step and cost logged locally in ~/.config/atticus/log.jsonl\n- Speech recognised on the Mac, and simple requests run with no model call\n- Telemetry described in the README, with a daily ping that can be turned off and failure reports off by default\n\n## Weaknesses\n\n- No API, MCP server or documented command an outside agent can call\n- Pulls and builds the main branch every six hours by default, with no signed or tagged release step\n- Five days old, one maintainer, two tagged releases and no changelog or deprecation policy\n- No privacy policy, SECURITY.md or security.txt\n- Needs macOS 26 and a paid Claude Pro or Max plan or a Devin plan\n\n\n\n## Before you call it (notes for agents)\n\n1. Don't plan to call Atticus from another agent. It takes requests only from its own shortcut and typing box\n2. If a user runs Atticus beside you, expect it to move windows and type into apps on the same Mac\n3. Point a user who wants pinned versions to Settings \u003e About \u0026 Updates to turn off self-update\n\n## Connect\n\nInstall:\n\n```bash\ncurl -fsSL https://raw.githubusercontent.com/SaarthurR/atticus-mac/main/install.sh | bash\n```\n\n## Similar tools\n\nRanked by shared capabilities, then score. Same-category tools with no shared capability key are listed last.\n\n| Tool | Grade | Score | Rank | Shared capabilities | x402 | Markdown |\n| --- | --- | --- | --- | --- | --- | --- |\n| ZeroClaw | BB | 70.2 | 167 | assistant.memory, assistant.self-hosted, agent.mcp-client | no | https://www.anchorterminal.com/tools/zeroclaw.md |\n| NanoClaw | B | 68.3 | 237 | assistant.memory, assistant.self-hosted, agent.mcp-client | no | https://www.anchorterminal.com/tools/nanoclaw.md |\n| Hermes Agent | B | 67.9 | 254 | assistant.memory, assistant.self-hosted, agent.mcp-client | no | https://www.anchorterminal.com/tools/hermes-agent.md |\n| OpenClaw | B | 67.1 | 280 | assistant.memory, assistant.self-hosted, agent.mcp-client | no | https://www.anchorterminal.com/tools/openclaw.md |\n| IronClaw | B | 66.7 | 299 | assistant.memory, assistant.self-hosted, agent.mcp-client | no | https://www.anchorterminal.com/tools/ironclaw.md |\n| nanobot | B | 62.4 | 466 | assistant.memory, assistant.self-hosted, agent.mcp-client | no | https://www.anchorterminal.com/tools/nanobot.md |\n\n## Panel reviews (0)\n\nReviewed by the Anchor panel (https://www.anchorterminal.com/reviewers/index.md): .\n\nDesk 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\n\n## Notable\n\n- The repository's first commit, \"Atticus: a voice assistant for your Mac\", is dated 10 October 2026 01:07 UTC (9 October in the author's time zone), the repository's creation time (source: \u003chttps://github.com/SaarthurR/atticus-mac/commits/main\u003e)\n- A Show HN post of 12 October 2026 linked the repository and drew 115 points and 30 comments (source: \u003chttps://news.ycombinator.com/item?id=50049588\u003e)\n- Tagged releases v1.0 on 13 October and v1.1 on 14 October 2026 (source: \u003chttps://github.com/SaarthurR/atticus-mac/releases\u003e)\n- The app pulls the main branch and rebuilds itself from source every six hours, on by default, rather than installing tagged releases (source: \u003chttps://github.com/SaarthurR/atticus-mac/blob/main/Atticus.swift\u003e)\n- Safe mode, on by default, runs the model's shell commands in Claude Code's sandbox, asks before deleting, sending, buying or changing a file, and blocks rm, sudo, dd, diskutil, shutdown and git push (source: \u003chttps://github.com/SaarthurR/atticus-mac/blob/main/atticus.py\u003e)\n- Once a day a random ID goes to PostHog, on by default with an opt-out in Settings. Failure reports are opt-in and scrubbed on the Mac first (source: \u003chttps://github.com/SaarthurR/atticus-mac#usage-count\u003e)\n- Sold for $5 once through Gumroad until 11 October 2026, when the licence check was switched off (source: \u003chttps://github.com/SaarthurR/atticus-mac/commit/7ff97be8ac95e70c87cdaecedd2a26b8a66df6ed\u003e)\n\n- #16 of 43 in Best AI personal assistants that act for one person: https://www.anchorterminal.com/best/personal-assistants/index.md\n- All 875 assistants comparisons: https://www.anchorterminal.com/compare/personal-assistants/index.md\n\n## Compare\n\n- [asaply vs Atticus](https://www.anchorterminal.com/compare/asaply-vs-atticus.md): F 7.6 vs E 42.9\n- [Asmi vs Atticus](https://www.anchorterminal.com/compare/asmi-vs-atticus.md): F 33.3 vs E 42.9\n- [Atticus vs Boba](https://www.anchorterminal.com/compare/atticus-vs-boba.md): E 42.9 vs F 10.3\n- [Atticus vs Boski](https://www.anchorterminal.com/compare/atticus-vs-boski.md): E 42.9 vs F 26.2\n- [Atticus vs Brea](https://www.anchorterminal.com/compare/atticus-vs-brea.md): E 42.9 vs F 12.9\n- [Atticus vs Caddy](https://www.anchorterminal.com/compare/atticus-vs-caddy-app.md): E 42.9 vs F 16.7\n- [Atticus vs CowAgent](https://www.anchorterminal.com/compare/atticus-vs-cowagent.md): E 42.9 vs C 58.5\n- [Atticus vs Del](https://www.anchorterminal.com/compare/atticus-vs-del.md): E 42.9 vs F 20.6\n- [Atticus vs folk](https://www.anchorterminal.com/compare/atticus-vs-folk-nozomio.md): E 42.9 vs F 19.8\n- [Atticus vs GAIA](https://www.anchorterminal.com/compare/atticus-vs-gaia.md): E 42.9 vs D 49.5\n- [Atticus vs Gemini Spark](https://www.anchorterminal.com/compare/atticus-vs-gemini-spark.md): E 42.9 vs F 24.5\n- [Atticus vs Grok Bot](https://www.anchorterminal.com/compare/atticus-vs-grok-bot.md): E 42.9 vs F 24.4\n- [Atticus vs Haven](https://www.anchorterminal.com/compare/atticus-vs-haven.md): E 42.9 vs F 22.2\n- [Atticus vs Hermes Agent](https://www.anchorterminal.com/compare/atticus-vs-hermes-agent.md): E 42.9 vs B 67.9\n- [Atticus vs HireAlpha](https://www.anchorterminal.com/compare/atticus-vs-hirealpha.md): E 42.9 vs F 8.4\n- [Atticus vs Instinct](https://www.anchorterminal.com/compare/atticus-vs-instinct.md): E 42.9 vs F 7.3\n- [Atticus vs IronClaw](https://www.anchorterminal.com/compare/atticus-vs-ironclaw.md): E 42.9 vs B 66.7\n- [Atticus vs Leon](https://www.anchorterminal.com/compare/atticus-vs-leon.md): E 42.9 vs E 41\n- [Atticus vs Lindy](https://www.anchorterminal.com/compare/atticus-vs-lindy.md): E 42.9 vs F 32.3\n- [Atticus vs nanobot](https://www.anchorterminal.com/compare/atticus-vs-nanobot.md): E 42.9 vs B 62.4\n- [Atticus vs NanoClaw](https://www.anchorterminal.com/compare/atticus-vs-nanoclaw.md): E 42.9 vs B 68.3\n- [Atticus vs Natura tinyNature](https://www.anchorterminal.com/compare/atticus-vs-natura.md): E 42.9 vs F 15.1\n- [Atticus vs Dots](https://www.anchorterminal.com/compare/atticus-vs-openai-dots.md): E 42.9 vs F 28.3\n- [Atticus vs OpenClaw](https://www.anchorterminal.com/compare/atticus-vs-openclaw.md): E 42.9 vs B 67.1\n- [Atticus vs OpenInstinct](https://www.anchorterminal.com/compare/atticus-vs-openinstinct.md): E 42.9 vs F 21.8\n- [Atticus vs Orbits](https://www.anchorterminal.com/compare/atticus-vs-orbits.md): E 42.9 vs F 15.6\n- [Atticus vs Orchid](https://www.anchorterminal.com/compare/atticus-vs-orchid-ai.md): E 42.9 vs F 20.2\n- [Atticus vs Pally](https://www.anchorterminal.com/compare/atticus-vs-pally.md): E 42.9 vs F 37.8\n- [Atticus vs PicoClaw](https://www.anchorterminal.com/compare/atticus-vs-picoclaw.md): E 42.9 vs D 46.1\n- [Atticus vs Poke](https://www.anchorterminal.com/compare/atticus-vs-poke.md): E 42.9 vs F 37.6\n- [Atticus vs QwenPaw](https://www.anchorterminal.com/compare/atticus-vs-qwenpaw.md): E 42.9 vs B 62.2\n- [Atticus vs szn](https://www.anchorterminal.com/compare/atticus-vs-szn.md): E 42.9 vs F 7.3\n- [Atticus vs Tab](https://www.anchorterminal.com/compare/atticus-vs-tab-bot.md): E 42.9 vs F 10.7\n- [Atticus vs Talorys](https://www.anchorterminal.com/compare/atticus-vs-talorys.md): E 42.9 vs F 28.9\n- [Atticus vs Tomo](https://www.anchorterminal.com/compare/atticus-vs-tomo.md): E 42.9 vs F 13.1\n- [Atticus vs Town](https://www.anchorterminal.com/compare/atticus-vs-town.md): E 42.9 vs D 48.7\n- [Atticus vs Wajo (Fo)](https://www.anchorterminal.com/compare/atticus-vs-wajo.md): E 42.9 vs E 43.9\n- [Atticus vs Zapia](https://www.anchorterminal.com/compare/atticus-vs-zapia.md): E 42.9 vs F 17.3\n- [Atticus vs ZeroClaw](https://www.anchorterminal.com/compare/atticus-vs-zeroclaw.md): E 42.9 vs BB 70.2\n- [Atticus vs Zo Computer](https://www.anchorterminal.com/compare/atticus-vs-zo-computer.md): E 42.9 vs E 43.1\n- [AstrBot vs Atticus](https://www.anchorterminal.com/compare/astrbot-vs-atticus.md): C 58.8 vs E 42.9\n\n## Verify this listing\n\nFor the vendor. The badge or a plain link to this page verifies the listing, from a page on saarthurr.github.io or one of its subdomains, or the README of github.com/SaarthurR/atticus-mac. 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\": \"atticus\", \"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\n\nHTML badge:\n\n```html\n\u003ca href=\"https://www.anchorterminal.com/tools/atticus\"\u003e\u003cimg src=\"https://www.anchorterminal.com/badges/atticus.svg\" alt=\"Atticus on Anchor Terminal\" height=\"20\"\u003e\u003c/a\u003e\n```\n\nMarkdown badge, for a README:\n\n```markdown\n[![Atticus on Anchor Terminal](https://www.anchorterminal.com/badges/atticus.svg)](https://www.anchorterminal.com/tools/atticus)\n```\n\nPlain link:\n\n```html\n\u003ca href=\"https://www.anchorterminal.com/tools/atticus\"\u003eAtticus on Anchor Terminal\u003c/a\u003e\n```\n\n## Share this listing\n\nFor the vendor. Sharing assets for social media, two PNGs of 1200 × 630 that say Atticus is listed on Anchor Terminal, with the vendor's logo and this page's address and no grade or score.\n\n- Dark: https://www.anchorterminal.com/assets/share/atticus-dark.png\n- Light: https://www.anchorterminal.com/assets/share/atticus-light.png\n- Create a video and download its frames: https://www.anchorterminal.com/assets/listing-video/index.html?listing=atticus\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit required: when you show, quote or pass on anything from here (to a user in an answer, in a product, a report or a dataset), say it's from Anchor Terminal (anchorterminal.com) and link the page or API address you took it from. Reviews also credit their author.", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-15", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "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" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Terminal", "url": "https://www.anchorterminal.com/tools/" }, { "name": "Personal assistants", "url": "https://www.anchorterminal.com/categories/personal-assistants" }, { "name": "Atticus", "url": "" } ], "description": "Atticus is an open-source macOS menu bar assistant that takes spoken or typed requests and operates apps, windows, files and the web, using the owner's Claude Code or Devin CLI plan as its model.", "facts": [ "rank #974 of 1094", "None auth", "0 desk reviews" ], "h1": "Atticus", "image": "https://www.anchorterminal.com/assets/og/tools-atticus.png", "path": "/tools/atticus", "published": "2026-10-01", "section": "tools", "title": "Atticus review (2026): pricing, alternatives and grade E", "toc": null, "updated": "2026-10-15", "url": "https://www.anchorterminal.com/tools/atticus" }, "tokens": { "markdown": 6650, "slim": 1480 }, "version": 1 }