Hacker ApprovedDepartments

TinyFish Web Agent

Ranked 5 of 5 browser agents by recommenders

An AI web agent that runs multi-step browser tasks, with benchmark results people find promising and public failure traces. Critics question whether its benchmarks reflect real multi-step workflows.

An AI web agent that runs multi-step browser tasks, with benchmark results people find promising and public failure traces. Critics question whether its benchmarks reflect real multi-step workflows.

7 people gave an opinion

recommend it
6
criticize it
1
approval share
86%
Each figure is one person. RecommendsCriticizes

Recommended in 2 of 13 months

  1. November 2025: not recommended
  2. December 2025: not recommended
  3. January 2026: not recommended
  4. February 2026: recommended
  5. March 2026: not recommended
  6. April 2026: recommended
  7. May 2026: not recommended
  8. June 2026: not recommended
  9. July 2026: not recommended
  10. August 2026: not recommended
  11. September 2026: not recommended
  12. October 2026: not recommended
  13. November 2026: not recommended (month in progress)

Why it doesn’t carry the badge

  • 6 people recommend itNeeds 10 or more, not met.
  • 6 recommenders for every criticNeeds 2 to 1 or better, met.
  • Recommended in 2 of 13 monthsNeeds 4 or more, not met.

The same three rules apply to every product, and the badge can’t be bought. How the badge works

Other browser agents people recommend

The four most recommended other browser agents, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.

TinyFish Web Agent compared with 4 alternatives
ProductRecommendCriticizeApprovalMonthsOwnedBadge
Browser Use522568%11—Approved
Smooth CLI10759%2——
PageAgent9756%1——
Rover by rtrvr.ai7188%6——
TinyFish Web AgentThis page6186%2——
See all 5 browser agents, ranked

What people said

6 of the 7 comments that mention it, newest first. Each links to the original comment.

“because status 200 with 14 characters of text isn't actually a successful fetch.”

RecommendsComment from 14 Apr 2026 on Hacker News

“I assume you used your own product to hype up this post?”

CriticizesComment from 12 Feb 2026 in “Show HN: TinyFish Web Agent (82% on hard tasks vs. Operator's 43%)”

“Promising numbers, especially if Online-Mind2Web better reflects real multi-step workflows than WebVoyager.”

MixedComment from 12 Feb 2026 in “Show HN: TinyFish Web Agent (82% on hard tasks vs. Operator's 43%)”

“The failure traces being public is a nice touch.”

RecommendsComment from 12 Feb 2026 in “Show HN: TinyFish Web Agent (82% on hard tasks vs. Operator's 43%)”

“I didn't expect to be able to verify every result in the spreadsheet myself.”

RecommendsComment from 12 Feb 2026 in “Show HN: TinyFish Web Agent (82% on hard tasks vs. Operator's 43%)”

“structured browser primitives that agents can actually reason about”

RecommendsComment from 10 Feb 2026 in “Ask HN: What Are You Working On? (February 2026)”

Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.