Zot coding agent
Shares rank 6 of 11 coding agent harnesses by recommenders
Fast single-binary terminal coding agent with modest memory use and no gateway overhead, used daily by several people. Critics say it spoofs Claude Code requests to the Anthropic API.
Fast single-binary terminal coding agent with modest memory use and no gateway overhead, used daily by several people. Critics say it spoofs Claude Code requests to the Anthropic API.
15 people gave an opinion
- recommend it
- 9
- criticize it
- 6
- approval share
- 60%
Recommended in 4 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: not recommended
- March 2026: recommended
- April 2026: recommended
- May 2026: recommended
- June 2026: recommended
- July 2026: not recommended
- August 2026: not recommended
- September 2026: not recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 9 people recommend itNeeds 10 or more, not met.
- 1.5 recommenders for every criticNeeds 2 to 1 or better, not met.
- Recommended in 4 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Reliable daily use
“It works and does what it's supposed to.”
Comment from 29 May 2026 in “Zot now supports Claude Opus 4.8” “zot has become my daily driver”
Comment from 29 May 2026 in “Zot now supports Claude Opus 4.8” Well-tested, reusable terminal UI
“Judging from the animation, you actually cared to test the TUI quite a lot.”
Comment from 29 May 2026 in “Zot now supports Claude Opus 4.8” “you can totally use zot's packages for your own TUI too”
Comment from 29 May 2026 in “Zot now supports Claude Opus 4.8”
What people warn about
Each mark is one comment
Spoofs Claude Code API requests
“it does try to impersonate Claude when talking to the Anthropic API”
Comment from 30 May 2026 in “Zot now supports Claude Opus 4.8” “It's not allowed, it spoofs claude code's requests.”
Comment from 29 May 2026 in “Zot now supports Claude Opus 4.8”
Other coding agent harnesses people recommend
The four most recommended other coding agent harnesses, 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.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| Pi coding agent | 892 | 198 | 82% | 12 | 3 mo51 owners | Approved |
| omp (oh-my-pi) | 80 | 21 | 79% | 6 | — | Approved |
| ForgeCode | 39 | 12 | 76% | 10 | — | Approved |
| Reasonix | 26 | 19 | 58% | 6 | — | — |
| Zot coding agentThis page | 9 | 6 | 60% | 4 | — | — |
What people said
14 of the 16 comments that mention it, newest first. Each links to the original comment.
“Being a single binary with modest memory requirements, I wonder if it can be used as a voice assistant”
“it does try to impersonate Claude when talking to the Anthropic API”
“Looks like they do include a disclaimer in the GitHub README, but not on zot.sh.”
“isn't trying to grow into an agent business or cloud service”
“you can totally use zot's packages for your own TUI too”
“Judging from the animation, you actually cared to test the TUI quite a lot.”
“zot is more limited there”
“It works and does what it's supposed to.”
“zot has become my daily driver”
“Written (vibe-slopped) in Go. In beta forever.”
“this will eventually stop working once Anthropic cuts off access”
“It's not allowed, it spoofs claude code's requests.”
“it is fast, there is no fucking gateway fuckaround or any other similar issues”
“It hits ~95% accuracy in synthetic lab tests with near-zero false positives.”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.