HK
Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Top
New
Best
Ask
Show
Jobs
Request
91.
▲
Show HN: I blind-tested 14 LLMs on a WP plugin task. Surprising Findings
github.com/guilamu
2 comments
2 months ago
guilamu
3 points
92.
▲
Show HN: EchoCopi Local-first, model-agnostic alternative to Google Antigravity
1 comment
7 months ago
sparksupernova
3 points
93.
▲
Show HN: Qwen3-Coder API – 480B open-source code LLM
netmind.ai
1 comment
a year ago
elricwan
3 points
94.
▲
Show HN: Claude-Bridge – Use GPT, Gemini, and Other LLMs with Claude Code
github.com/badlogic
1 comment
a year ago
badlogic
3 points
95.
▲
Show HN: Pushbullet Chrome extension for manifest v3
github.com/volkyeth
1 comment
a year ago
volky
3 points
96.
▲
Show HN: Set To-Do list as windows wallpaper (coded by AI)
github.com/casualwriter
1 comment
a year ago
casualwriter
3 points
97.
▲
Show HN: I ran every Claude agent turn through the Batch API
eran.sandler.co.il
discuss
2 months ago
erans
3 points
98.
▲
Show HN: FC-Eval – CLI to Benchmark Local or Cloud LLMs on Function Calling
github.com/gauravvij
discuss
3 months ago
gauravvij137
3 points
99.
▲
Show HN: Allos – An open-source, LLM-agnostic agentic SDK for Python
github.com/Undiluted7027
discuss
7 months ago
undiluted7027
3 points
100.
▲
Show HN: A toy MCP for AI agents to code, run, and see output of GPU code safely
github.com/mehmetoguzderin
discuss
a year ago
mehmetoguzderin
3 points
101.
▲
Show HN: CLI AI assistant that remembers and sets goals
github.com/elroy-bot
discuss
a year ago
jjfoooo4
3 points
102.
▲
RES-Q: A New Benchmark for Differentiating Frontier Model Capability
discuss
2 years ago
becklabs
3 points
103.
▲
Show HN: Dr. Headline – An Autonomous AI Agent Publishing Daily News Briefings
github.com/headlinesquare
7 comments
a year ago
Thomas-Router
2 points
104.
▲
Show HN: A simple and local project management tool made 100% by Claude
cgarduno1garduno.github.io
3 comments
a year ago
ccccrrriis
2 points
105.
▲
Show HN: Lumen – vision-first browser agent (state of the art, open source)
github.com/omxyz
1 comment
3 months ago
fearlessboi
2 points
106.
▲
Show HN: ClawAid – AI doctor that fixes OpenClaw in one command
github.com/jjj5666
1 comment
3 months ago
jjj5666
2 points
107.
▲
Show HN: Reduce LLM token use by ~30% with this MCP/CLI tool(Claude benchmarked)
1 comment
4 months ago
jahala
2 points
108.
▲
Show HN: CRTX – AI code gen that tests and fixes its own output (OSS)
github.com/CRTXAI
1 comment
4 months ago
johnnycash926
2 points
109.
▲
The Car Wash Problem: A variable isolation study on prompt architecture
1 comment
4 months ago
midmost44
2 points
110.
▲
Show HN: LLM-use – cost-effective LLM orchestrator for agents
1 comment
4 months ago
justvugg
2 points
111.
▲
Show HN: Rails engine for building production-ready LLM agents
github.com/adham90
1 comment
5 months ago
adham900
2 points
112.
▲
Show HN: A better interface to edit written text with LLMs
llm-peer-review.com
1 comment
2 years ago
jaykr_
2 points
113.
▲
Show HN: Woltspace – a lodge for your coding agents
woltspace.com
discuss
a day ago
jerpint
2 points
114.
▲
Show HN: Oy – The Yo App for Agents
oy-agent.com
discuss
3 months ago
jumploops
2 points
115.
▲
Show HN: OpenClaw Arena – Benchmark models on real tasks, rank by perf and cost
app.uniclaw.ai
discuss
3 months ago
skysniper
2 points
116.
▲
Show HN: Perstack – Containerized harness, 5 tests with full logs and API cost
github.com/perstack-ai
discuss
3 months ago
FL4TLiN3
2 points
117.
▲
Show HN: Yardstiq – Compare LLM outputs side-by-side in your terminal
yardstiq.sh
discuss
4 months ago
stanleycyang
2 points
118.
▲
Show HN: Oh-My-OpenClaw – agent orchestration for coding, from Discord/Telegram
github.com/happycastle114
discuss
4 months ago
soungmin114
2 points
119.
▲
Show HN: Design is Code – UML to TDD tests that constrain AI code generation
mossgreen.github.io
discuss
4 months ago
mossgu
2 points
120.
▲
Show HN: Murmuration – AI visualizes your state of mind
github.com/paraschopra
discuss
4 months ago
paraschopra
2 points
More