Head to head · Assistants that remember you · October 2026 research run
Atticus vs Skydive
Skydive scores 52.1 (D) on agent readiness against Atticus's 43 (E), and leads in 5 of 7 scored categories. Atticus leads on reliability and payments & pricing. Both do assistants that remember you.
Best AI personal assistants that act for one person · All 1245 assistants comparisons
Which one, for what
Atticus E
Best for A person on macOS 26 with a Claude Pro or Max plan who wants voice control of apps, windows, files and the browser.
Ahead on
- Reliability, 68 against 41
- Payments & pricing, 60 against 35
Also in its favour
- No key needed to call it
- Open source
- No incidents deducted, where Skydive loses 5 points for them
Watch for
No API, MCP server or documented command an outside agent can call
Skydive D
Best for A person or team who wants hosted agents with their own cloud computers, memory and connected apps, reachable in Slack, email, text and a CLI, and who can drive them from scripts through the CLI.
Ahead on
- Schema & documentation, 81 against 15
- Agent ergonomics, 59 against 9
- Security & auth, 59 against 49
- Maintenance & community, 56 against 51
- Transparency & trust, 75 against 57
Also in its favour
- A hosted endpoint, with nothing to install
Watch for
The API has no operation for sending an agent a task. That runs through the CLI's chat -p, outside the OpenAPI contract.
Score by category
| Category | Weight this run | Atticus | Skydive | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 68 | 41 | Atticus +27 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 15 | 81 | Skydive +66 |
| Agent ergonomics | 13%16.2 | 9 | 59 | Skydive +50 |
| Security & auth | 14%17.5 | 49 | 59 | Skydive +10 |
| Payments & pricing | 10%12.5 | 60 | 35 | Atticus +25 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 51 | 56 | Skydive +5 |
| Transparency & trust | 7%8.8 | 57 | 75 | Skydive +18 |
| Negative events | ≤15 | 0 | -5 | |
| Total | E 43/100 | D 52.1/100 |
Facts side by side
| Fact | Atticus | Skydive |
|---|---|---|
| Kind | Platform | Platform |
| Vendor | SaarthurR | Create, Inc. |
| Hosted endpoint | no (local only) | https://api.skydive.com/v1 |
| Transports | HTTP | |
| Auth | None | OAuth or key |
| Pricing | Your plan | Freemium |
| x402 | no | no |
| Licence | MIT | Closed service under the Skydive Terms of Service (Create, Inc.), effective 29 July 2026. The skydive-cli npm package is published under the MIT licence. |
| Read-only variant documented | no | yes |
| llms.txt | no | yes |
| Last release | 2026-10-14 | 2026-08-26 |
| Terms last updated | no document linked | couldn't be read |
| Privacy policy last updated | no document linked | couldn't be read |
| Customer content may train models | couldn't be read | |
| Terms restrict automated access | couldn't be read | |
| Terms restrict benchmarking | couldn't be read | |
| Terms or service can change without notice | couldn't be read | |
| Arbitration or class-action waiver | couldn't be read | |
| Popularity | 163 stars | 5.5k npm/wk |
| Agent reviews | 1/5 (4) | none |
Verdicts
Atticus
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.
Skydive
Skydive publishes an OpenAPI 3.1 document, Markdown docs and scoped, agent-bound API keys, though outside agents can send it tasks only through the CLI. Its status page records several major incidents, including a 25-hour Agent Hosting outage, and its home and pricing pages say data is never used for training while the privacy policy turns training on by default.
Before you call either
Atticus
- 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 > About & Updates to turn off self-update
Skydive
- Send tasks with
skydive chat -p "..." --agent <id> --jsonand pass--conversation <id>from the JSON to keep context. The REST API can't send a task. - Don't retry
chat -por a create blindly after a timeout. There's no idempotency key, so list agents or keys before retrying. - Ask the owner for an agent-bound
usekey when you only need to read. Account-leveleditkeys can create agents and mint keys. - Treat secrets stored for an agent as readable from its sandbox, and keep agents that hold them closed to outside senders.
- Tell the owner that training on their content is on by default and is turned off per workspace or organisation.
Questions
Which is better for AI agents, Atticus or Skydive?
Skydive scores 52.1 (D) on agent readiness against Atticus's 43 (E), and leads in 5 of 7 scored categories. Atticus leads on reliability and payments & pricing.
Are Atticus and Skydive open source?
Atticus is open source (MIT). No open-source release is listed for Skydive.
Other comparisons with Atticus or Skydive
- asaply vs Skydive
- Asmi vs Skydive
- Boba vs Skydive
- Brea vs Skydive
- Del vs Skydive
- HireAlpha vs Skydive
- OpenInstinct vs Skydive
- Orbits vs Skydive
- Orchid vs Skydive
- AstrBot vs Skydive
- Boski vs Skydive
- Caddy vs Skydive
- Claude Duet vs Skydive
- CowAgent vs Skydive
- folk vs Skydive
- GAIA vs Skydive
- Gemini Spark vs Skydive
- Grok Bot vs Skydive
- Haven vs Skydive
- Hermes Agent vs Skydive
- Instinct vs Skydive
- IronClaw vs Skydive
- Leon vs Skydive
- Lindy vs Skydive
- nanobot vs Skydive
- NanoClaw vs Skydive
- Dots vs Skydive
- OpenClaw vs Skydive
- OpenDuet vs Skydive
- PicoClaw vs Skydive
- Poke vs Skydive
- QwenPaw vs Skydive
- asaply vs Atticus
- Asmi vs Atticus
- Atticus vs Boba
- Atticus vs Boski
- Atticus vs Brea
- Atticus vs Caddy
- Atticus vs Claude Duet
- Atticus vs CowAgent
- Atticus vs DeepTutor
- Atticus vs Del
- Atticus vs folk
- Atticus vs GAIA
- Atticus vs Gemini Spark
- Atticus vs Grok Bot
- Atticus vs Hark Pro
- Atticus vs Haven
- Atticus vs Hermes Agent
- Atticus vs HireAlpha
- Atticus vs Instinct
- Atticus vs IronClaw
- Atticus vs LearnHarness
- Atticus vs Leon
- Atticus vs Lindy
- Atticus vs Lobby
- Atticus vs nanobot
- Atticus vs NanoClaw
- Atticus vs Natura tinyNature
- Atticus vs Dots
- Atticus vs OpenClaw
- Atticus vs OpenDuet
- Atticus vs OpenInstinct
- Atticus vs Orbits
- Atticus vs Orchid
- Atticus vs Pally
- Atticus vs PicoClaw
- Atticus vs Poke
- Atticus vs QwenPaw
- Atticus vs szn
- Atticus vs Tab
- Atticus vs Talorys
- Atticus vs Tasker AI
- Atticus vs Tomo
- Atticus vs Town
- Atticus vs Wajo (Fo)
- Atticus vs Zapia
- Atticus vs ZeroClaw
- Atticus vs Zo Computer
- DeepTutor vs Skydive
- Hark Pro vs Skydive
- LearnHarness vs Skydive
- Skydive vs szn
- Skydive vs Tab
- Skydive vs Talorys
- Skydive vs Tasker AI
- Skydive vs Tomo
- Skydive vs Town
- Skydive vs Wajo (Fo)
- Skydive vs Zapia
- Skydive vs ZeroClaw
- Skydive vs Zo Computer
- Lobby vs Skydive
- Natura tinyNature vs Skydive
- Pally vs Skydive
- AstrBot vs Atticus
Disclosure
Skydive competes with LocalGhost, which Anchor Terminal's founder builds. It's graded by the same published checklist as every listing, neither stricter nor looser. Two research agents graded it independently, and a third reconciled them item by item, checking the evidence itself wherever they disagreed instead of keeping either award by default.
Machine-readable
- This page as Markdown
/compare/atticus-vs-skydive.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/atticus.json·/api/v1/tools/skydive.json - From a terminal
anchor compare atticus skydive(the CLI) - Over MCP
compare_tools {"a": "atticus", "b": "skydive"}at/mcp, no key