All-Time Top 30

The AI tools with the most community votes since we started tracking. Updated 2026-06-16.

Tracking since 2026-06-14 ยท 110 unique tools ยท 3 days of data

๐Ÿฅ‡
GitHub

ponytail

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

โ˜… 44,483 total votes
๐Ÿ“… 3/3 days
๐Ÿฅˆ
Hacker News

Claude Fable 5

System Card [pdf]: https://www-cdn.anthropic.com/d00db56fa754a1b115b6dd7cb2e3c3...

โ˜… 7,865 total votes
๐Ÿ“… 3/3 days
๐Ÿฅ‰
GitHub

omnigent

A meta-harness for all your AI agents. Omnigent provides a common layer over Claude Code, Codex, Pi, and the agents you write yourself: swap or combine harnesses without rewriting, keep them in check...

โ˜… 5,327 total votes
๐Ÿ“… 3/3 days
#4
Hacker News

Open source AI must win

Open source AI must win

โ˜… 4,733 total votes
๐Ÿ“… 3/3 days
#5
Hacker News

AI agent bankrupted their operator while trying to scan DN42

AI agent bankrupted their operator while trying to scan DN42

โ˜… 4,370 total votes
๐Ÿ“… 3/3 days
#6
GitHub

enableMacosAI

ๅ›ฝ่กŒ Mac ไธ€้”ฎๅผ€ๅฏๅฎŒๆ•ด Apple ๆ™บ่ƒฝ(็ซฏไพง + Private Cloud Compute ไบ‘็ซฏ)ยท macOS 27 / Apple Silicon

โ˜… 3,782 total votes
๐Ÿ“… 3/3 days
#7
Hacker News

If Claude Fable stops helping you, you'll never know

Related: https://simonwillison.net/2026/Jun/10/if-claude-fable-stops-helping-you/

โ˜… 3,103 total votes
๐Ÿ“… 3/3 days
#8
Hacker News

German ruling declares Google liable for false answers in AI Overviews

German ruling declares Google liable for false answers in AI Overviews

โ˜… 3,049 total votes
๐Ÿ“… 3/3 days
#9
Hacker News

CEOs who think AI replaces their employees are just bad CEOs

CEOs who think AI replaces their employees are just bad CEOs

โ˜… 2,522 total votes
๐Ÿ“… 3/3 days
#10
Hacker News

Claude Fable is relentlessly proactive

Claude Fable is relentlessly proactive

โ˜… 2,303 total votes
๐Ÿ“… 3/3 days
#11
GitHub

world-of-claudecraft

โ˜… 2,301 total votes
๐Ÿ“… 3/3 days
#12
GitHub

renwei-writing

ไบบๅ‘ณๅ„ฟๅ†™ไฝœ ยท An AI agent skill: edit people's words without erasing the person behind them

โ˜… 1,932 total votes
๐Ÿ“… 3/3 days
#13
GitHub

effective-html

Agent skill for elegant and simple html plans, architecture diagrams, or whatever else you can think of.

โ˜… 1,723 total votes
๐Ÿ“… 2/3 days
#14
GitHub

fanbox

vibe coding ็š„้ฉพ้ฉถ่ˆฑ๏ผšๅทฆ่พนๆ–‡ไปถ๏ผŒๅณ่พน/ไธ‹่พน็ปˆ็ซฏ๏ผŒไธญ้—ด็œ‹ๆธ…ๆฏไธ€ๆฌกๆ”นๅŠจใ€‚ / The cockpit for vibe coding: browse files on the left, command agents on the right, watch every change in between.

โ˜… 1,694 total votes
๐Ÿ“… 3/3 days
#15
Hacker News

Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?

Has anyone here fully swapped Claude/GPT for a local model as their main coding tool, not just for side experiments? If so, please share your setup and performance (e.g tok/s)

โ˜… 1,637 total votes
๐Ÿ“… 2/3 days
#16
Hacker News

Anthropic apologizes for invisible Claude Fable guardrails

https://web.archive.org/web/20260611122253/https://www.theve..., https://archive.ph/y4V4k

โ˜… 1,529 total votes
๐Ÿ“… 3/3 days
#17
Product Hunt

Fundraisly

Fundraisly: ultimate AI agent for fundraising. It analyzes 300K+ investors and millions of deals, identifies the relevant ones actively investing in your space, maps warm paths to them from your own n...

โ˜… 1,361 total votes
๐Ÿ“… 1/3 days
#18
GitHub

architect-loop

Claude Fable 5 as architect, GPT-5.5 Codex as builder, the repo as memory - a research-backed Claude Code skill for the cross-vendor agent loop

โ˜… 1,291 total votes
๐Ÿ“… 3/3 days
#19
GitHub

text-humanizer

Advanced open-source AI humanizer designed to make AI-generated text undetectable by Turnitin, GPTZero, and other AI detection services.

โ˜… 1,248 total votes
๐Ÿ“… 2/3 days
#20
Hacker News

Rio de Janeiro's "homegrown" LLM appears to be a merge of an existing model

Rio de Janeiro's "homegrown" LLM appears to be a merge of an existing model

โ˜… 989 total votes
๐Ÿ“… 3/3 days
#21
Product Hunt

Brew

Brew is the fastest way to design and send beautiful, on-brand emails and automations that render perfectly in every inbox. Describe a campaign or a multi-step automation in plain English, and Brew bu...

โ˜… 940 total votes
๐Ÿ“… 1/3 days
#22
GitHub

gateGPT

Full Transformer into a custom chip. microGPT in RTL, generating names on a Virtex-5 FPGA at ~56k tokens/second.

โ˜… 908 total votes
๐Ÿ“… 3/3 days
#23
GitHub

coreai-models

Model export recipes, Python primitives, and Swift runtime utilities for on-device AI

โ˜… 900 total votes
๐Ÿ“… 1/3 days
#24
Product Hunt

StoreClaw

StoreClaw is the first AI commerce platform with agents that know how to sell, so you can make more money with less effort and less stress. Connect StoreClaw to your existing store and it will study y...

โ˜… 898 total votes
๐Ÿ“… 1/3 days
#25
Hacker News

GPT-2: Too Dangerous To Release (2019)

GPT-2: Too Dangerous To Release (2019)

โ˜… 858 total votes
๐Ÿ“… 3/3 days
#26
Product Hunt

PollyReach

Most AI phone tools are built for enterprises โ€” APIs, workflows, sales automation. PollyReach is built for you. Give your AI a real phone number. Say "book me a table for 7pm" โ€” it finds the...

โ˜… 836 total votes
๐Ÿ“… 1/3 days
#27
GitHub

fusion-fable

Fuse two frontier models into one Fable-tier answer: Opus 4.8 drafts, a second model (Opus 4.8 or GPT-5.5 via codex) checks, Opus fuses. A Claude Code skill.

โ˜… 800 total votes
๐Ÿ“… 3/3 days
#28
GitHub

gpt-pp

โ˜… 791 total votes
๐Ÿ“… 2/3 days
#29
Product Hunt

Unabyss

Set it up once and never re-explain yourself to AI again. Connect the apps you use daily - Unabyss will extract, structure, and update your context automatically. Share it with any AI tool via MCP, wi...

โ˜… 777 total votes
๐Ÿ“… 1/3 days
#30
Hacker News

Apple reveals new AI architecture built around Google Gemini models

Apple reveals new AI architecture built around Google Gemini models

โ˜… 734 total votes
๐Ÿ“… 1/3 days