Get an audit

Head to head · Assistant proactive · October 2026 research run

Gemini Spark vs ZeroClaw

ZeroClaw scores 70.2 (BB) on agent readiness against Gemini Spark's 24.5 (F), and leads in every scored category. Both do assistant proactive.

Best AI personal assistants that act for one person · All 190 assistants comparisons

Gemini SparkGoogle LLC · Platform F24.5/100#974 of 986 ZeroClawZeroClaw Labs · Agent harness BB70.2/100#161 of 986

Which one, for what

Gemini Spark F

Best for A person who already keeps mail, calendar and files in a personal Google Account and accepts Keep Activity being on.

Also in its favour

  • No incidents deducted, where ZeroClaw loses 3 points for them

Watch for

No public API, SDK or MCP server for an outside agent was found. Spark is reached in the Gemini mobile app, the Mac app and gemini.google.com

ZeroClaw BB

Best for One person who wants an assistant on their own hardware that answers on Telegram, Discord, Matrix or email, asks before it writes or runs commands, and works with a local model.

Ahead on

  • Reliability, 74 against 14
  • Schema & documentation, 82 against 17
  • Agent ergonomics, 72 against 9
  • Security & auth, 76 against 60
  • Payments & pricing, 60 against 10
  • Maintenance & community, 80 against 17
  • Transparency & trust, 64 against 49

Also in its favour

  • Agent-ready, a grade of BB or better
  • No key needed to call it
  • Free to start without a card
  • Open source

Watch for

The docs state that command execution is not audited. [security.audit] records certificate events only, and tool receipts are opt-in and not durable

Score by category

CategoryWeight this runGemini SparkZeroClawEdge
Reliability16%201474ZeroClaw +60
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.21782ZeroClaw +65
Agent ergonomics13%16.2972ZeroClaw +63
Security & auth14%17.56076ZeroClaw +16
Payments & pricing10%12.51060ZeroClaw +50
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.81780ZeroClaw +63
Transparency & trust7%8.84964ZeroClaw +15
Negative events≤150-3
TotalF 24.5/100BB 70.2/100

Facts side by side

FactGemini SparkZeroClaw
KindPlatformAgent harness
VendorGoogle LLCZeroClaw Labs
Hosted endpointno (local only)no (local only)
Transports
AuthOAuthNone
PricingPaidFree
x402nono
LicenceProprietary hosted service under the Google Terms of ServiceMIT OR Apache-2.0
Read-only variant documentednoyes
llms.txtnoyes
Last release2026-05-192026-09-05
Terms last updated2026-07-30no document linked
Privacy policy last updated2026-09-24no document linked
Customer content may train modelsyes, with an opt-out
Terms restrict automated accessyes
Terms restrict benchmarkingnot found in the text
Terms or service can change without noticenot found in the text
Arbitration or class-action waivernot found in the text
Popularitynone33k stars

Verdicts

Gemini Spark

Google's help pages state what Spark confirms before doing, how to delete its remote browser and code data, and the risks of prompt injection. Spark has no public API, Google calls it experimental, and it runs only with Keep Activity on, the setting under which chats are used for model training and human review.

ZeroClaw

Supervised autonomy is the default, so tools outside a short read-only list wait for the owner's approval, and secrets are encrypted in the config file. The docs state that command execution is not written to an audit log, and the project publishes no privacy policy or terms.

Before you call either

Gemini Spark

  1. Do not plan an integration against Spark. No public API or MCP server was found, and a person must hold a Google AI Pro or Ultra subscription
  2. Expect a confirmation request before sends, edits, purchases and web form submissions, and note that bulk changes to private Google Tasks run without one
  3. Delete remote browser data and remote code execution data in Gemini Spark Settings after a sensitive session. Deleting a task thread or Gemini Apps activity does not remove them
  4. Keep within 15 running tasks and 50 active schedules. A schedule does not run when 15 tasks are running or the usage limit is reached
  5. Treat every safety statement here as Google's own description. None was tested, and no message was sent to the service

ZeroClaw

  1. Keep [risk_profiles.<alias>] level = "supervised". full runs every tool not listed in always_ask, and the YOLO preset removes the sandbox and path rules too
  2. Add sending and account tools such as send_via, google_workspace and http_request to always_ask so a session-level Always grant cannot skip the prompt
  3. List senders in [peer_groups.<name>] external_peers. ["*"] accepts anyone on that channel
  4. Set [web_fetch].allowed_domains and [http_request].allowed_domains. Fetches run unprompted and the OS sandbox does not block egress
  5. Run one-shot tasks with zeroclaw agent -a <alias> -m "<task>". A cron or webhook turn has no prompt, so shell calls fall to the command policy

Questions

Which is better for AI agents, Gemini Spark or ZeroClaw?

ZeroClaw scores 70.2 (BB) on agent readiness against Gemini Spark's 24.5 (F), and leads in every scored category.

Are Gemini Spark and ZeroClaw open source?

No open-source release is listed for Gemini Spark. ZeroClaw is open source (MIT OR Apache-2.0).

Other comparisons with Gemini Spark or ZeroClaw

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report