Top AI Tools ยท 2026-06-15

Daily snapshot from 2026-06-15T21:07:14.531Z. Top 30 of 65 tools tracked.

โ† 2026-06-14 ยท All Past Rankings ยท 2026-06-16 โ†’

๐Ÿ† Top 30

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˜… 15,477 votes
๐Ÿ’ฌ 8
๐Ÿฅˆ
Hacker News

Claude Fable 5

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

โ˜… 2,621 votes
๐Ÿ’ฌ 2152
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˜… 1,791 votes
๐Ÿ’ฌ 96
#4
Hacker News

Open source AI must win

Open source AI must win

โ˜… 1,585 votes
๐Ÿ’ฌ 477
#5
Hacker News

AI agent bankrupted their operator while trying to scan DN42

AI agent bankrupted their operator while trying to scan DN42

โ˜… 1,460 votes
๐Ÿ’ฌ 531
#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˜… 1,281 votes
๐Ÿ’ฌ 20
#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˜… 1,035 votes
๐Ÿ’ฌ 500
#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˜… 1,017 votes
๐Ÿ’ฌ 549
#9
GitHub

effective-html

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

โ˜… 909 votes
๐Ÿ’ฌ 2
#10
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˜… 842 votes
๐Ÿ’ฌ 308
#11
GitHub

world-of-claudecraft

โ˜… 777 votes
๐Ÿ’ฌ 120
#12
Hacker News

Claude Fable is relentlessly proactive

Claude Fable is relentlessly proactive

โ˜… 769 votes
๐Ÿ’ฌ 656
#13
GitHub

text-humanizer

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

โ˜… 671 votes
๐Ÿ’ฌ 0
#14
GitHub

renwei-writing

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

โ˜… 666 votes
๐Ÿ’ฌ 0
#15
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˜… 572 votes
๐Ÿ’ฌ 6
#16
Hacker News

Microsoft's open source tools were hacked to steal passwords of AI developers

Microsoft's open source tools were hacked to steal passwords of AI developers

โ˜… 561 votes
๐Ÿ’ฌ 194
#17
Hacker News

Anthropic apologizes for invisible Claude Fable guardrails

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

โ˜… 510 votes
๐Ÿ’ฌ 443
#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˜… 443 votes
๐Ÿ’ฌ 1
#19
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˜… 438 votes
๐Ÿ’ฌ 235
#20
GitHub

gpt-pp

โ˜… 396 votes
๐Ÿ’ฌ 1
#21
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˜… 392 votes
๐Ÿ’ฌ 212
#22
GitHub

gateGPT

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

โ˜… 299 votes
๐Ÿ’ฌ 0
#23
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˜… 294 votes
๐Ÿ’ฌ 0
#24
Hacker News

GPT-2: Too Dangerous To Release (2019)

GPT-2: Too Dangerous To Release (2019)

โ˜… 286 votes
๐Ÿ’ฌ 129
#25
GitHub

loop-engineering

Practical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (inspired by Addy Osmani and Boris Cherny). Includes loop-aud...

โ˜… 256 votes
๐Ÿ’ฌ 9
#26
GitHub

bingo

Bingo - AI-powered Red Team Terminal (DeepSeek/Claude/GPT/GLM)

โ˜… 158 votes
๐Ÿ’ฌ 1
#27
GitHub

Ironsmith

Create personal Mac apps instantly with a prompt. Supports on-device and cloud LLMs

โ˜… 142 votes
๐Ÿ’ฌ 1
#28
GitHub

worldcup2026-prediction-skill

2026 ไธ–็•Œๆฏ AI ้ข„ๆต‹ๅผ•ๆ“Žใ€Œ็ปฟ่Œต็ฅž็ฎ—ใ€ โ€” ็ปๅฎžๆˆ˜้ชŒ่ฏ็š„ๅคงๆจกๅž‹ system prompt,ๆŠŠ 48 ้˜Ÿ่ต„ๆ–™ๅบ“ + ่ฏ„ไผฐๆ–นๆณ•่ฎบ + ไธฅๆ ผ JSON ่พ“ๅ‡บๅฅ‘็บฆๅ†™ๆญปๅœจๅ•ๆ–‡ไปถ,ไปปไฝ• OpenAI ๅ…ผๅฎนๆŽฅๅฃๅณ่ดดๅณ็”จใ€‚

โ˜… 136 votes
๐Ÿ’ฌ 3
#29
GitHub

coreai-model-zoo

Community model zoo + knowledge base for Apple Core AI (iOS/macOS 27): Qwen3.5 & Gemma 4 converted end-to-end, verified on-device (iPhone 17 Pro GPU/ANE), conversion gotchas, custom Metal kernels,...

โ˜… 134 votes
๐Ÿ’ฌ 1
#30
GitHub

ghostwork

Your personal AI worker. Watches your screen, learns your workflows, automates the repetitive parts. Built on Screenpipe. All local, no cloud, no setup. It gets better every day without you doing anyt...

โ˜… 123 votes
๐Ÿ’ฌ 12