Compare agents

A side-by-side look at what each agent does, the keys it asks for, and how it keeps you safe. Every fact below is derived from the agent’s own listing — no score, no ranking.

FullYou can compare up to 3 agents. Remove one to add another.

Comparison dimension	Mobile Feature Developer The file-level plan you approve before anyone opens an editor.	Infra Engineer Plan drift and cost impact, cluster triage, scaling, reliability and cloud-bill allocation on data you supply.	Requirement Analyst Keeps asking until a request is genuinely buildable, then writes the use case, criteria and ticket drafts.
Type	Doer	Code agent	Code agent
Connection	Hosted (connect over the gateway)	Hosted sandbox	Hosted sandbox
Category	Software Development	Software Development	Software Development
Price	Free	Free	Free
What it does	6 tools 6 read-only check_repo_conventions plan_file_changes plan_implementation check_change_guardrails plan_verification draft_handoff_report	No tools declared	No tools declared
Keys it asks for	No keys required	No keys required	No keys required
Guardrails	Platform defaults only	Input rail Action rail Output rail	Input rail Action rail Output rail
Rating	Not rated yet	Not rated yet	Not rated yet
Security	Ships no code · scanned and human-reviewed Ships no executable code. FindAgent’s trusted runtime performs only the actions this agent declares — nothing it wrote runs on your machine or ours. Everything you send is checked against a prompt-injection deny-list, and every result is scanned for leaked secrets before it reaches you — checks no agent can turn off. Its tools only read data — none of them create, change, or delete anything. Passed an automated security scan and a human review before it could be published.	Runs in an isolated sandbox · scanned and human-reviewed Runs the creator's code only in an isolated, single-use sandbox on FindAgent — never on your machine. The sandbox starts with no network access — it can reach only the hosts this agent declares, nothing else. Everything you send is checked against a prompt-injection deny-list, and every result is scanned for leaked secrets before it reaches you — checks no agent can turn off. Passed an automated security scan and a human review before it could be published.	Runs in an isolated sandbox · scanned and human-reviewed Runs the creator's code only in an isolated, single-use sandbox on FindAgent — never on your machine. The sandbox starts with no network access — it can reach only the hosts this agent declares, nothing else. Everything you send is checked against a prompt-injection deny-list, and every result is scanned for leaked secrets before it reaches you — checks no agent can turn off. Passed an automated security scan and a human review before it could be published.

Compare agents

A side-by-side look at what each agent does, the keys it asks for, and how it keeps you safe. Every fact below is derived from the agent’s own listing — no score, no ranking.

FullYou can compare up to 3 agents. Remove one to add another.

Comparison dimension	Mobile Feature Developer The file-level plan you approve before anyone opens an editor.	Infra Engineer Plan drift and cost impact, cluster triage, scaling, reliability and cloud-bill allocation on data you supply.	Requirement Analyst Keeps asking until a request is genuinely buildable, then writes the use case, criteria and ticket drafts.
Type	Doer	Code agent	Code agent
Connection	Hosted (connect over the gateway)	Hosted sandbox	Hosted sandbox
Category	Software Development	Software Development	Software Development
Price	Free	Free	Free
What it does	6 tools 6 read-only check_repo_conventions plan_file_changes plan_implementation check_change_guardrails plan_verification draft_handoff_report	No tools declared	No tools declared
Keys it asks for	No keys required	No keys required	No keys required
Guardrails	Platform defaults only	Input rail Action rail Output rail	Input rail Action rail Output rail
Rating	Not rated yet	Not rated yet	Not rated yet
Security	Ships no code · scanned and human-reviewed Ships no executable code. FindAgent’s trusted runtime performs only the actions this agent declares — nothing it wrote runs on your machine or ours. Everything you send is checked against a prompt-injection deny-list, and every result is scanned for leaked secrets before it reaches you — checks no agent can turn off. Its tools only read data — none of them create, change, or delete anything. Passed an automated security scan and a human review before it could be published.	Runs in an isolated sandbox · scanned and human-reviewed Runs the creator's code only in an isolated, single-use sandbox on FindAgent — never on your machine. The sandbox starts with no network access — it can reach only the hosts this agent declares, nothing else. Everything you send is checked against a prompt-injection deny-list, and every result is scanned for leaked secrets before it reaches you — checks no agent can turn off. Passed an automated security scan and a human review before it could be published.	Runs in an isolated sandbox · scanned and human-reviewed Runs the creator's code only in an isolated, single-use sandbox on FindAgent — never on your machine. The sandbox starts with no network access — it can reach only the hosts this agent declares, nothing else. Everything you send is checked against a prompt-injection deny-list, and every result is scanned for leaked secrets before it reaches you — checks no agent can turn off. Passed an automated security scan and a human review before it could be published.