HK
Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Top
New
Best
Ask
Show
Jobs
Request
91.
▲
Show HN: SwiftAI – open-source library to easily build LLM features on iOS/macOS
github.com/mi12labs
24 comments
10 months ago
mi12-root
74 points
92.
▲
Show HN: TensorZero – open-source data and learning flywheel for LLMs
github.com/tensorzero
2 comments
2 years ago
GabrielBianconi
49 points
93.
▲
Show HN: Watch LLMs play 21,000 hands of Poker
pokerbench.adfontes.io
19 comments
5 months ago
jazarwil
36 points
94.
▲
Show HN: TrustGraph – Do More with AI with Less (Open Source AI Infrastructure)
github.com/trustgraph-ai
5 comments
2 years ago
cybermaggedon
22 points
95.
▲
Show HN: Open-source study to measure end user satisfaction levels with LLMs
open-llm-initiative.com
2 comments
2 years ago
sparacha
12 points
96.
▲
Show HN: How I built Timeframe, our family e-paper dashboard
hawksley.org
2 comments
4 months ago
hawksley
8 points
97.
▲
Show HN: Dealing with Claude 3 XML function calling so you don't have to
3 comments
2 years ago
willbakst
7 points
98.
▲
Show HN: Prompt-injection firewall for OpenClaw agents
github.com/ContextFort-AI
3 comments
5 months ago
ashwinr2002
6 points
99.
▲
Show HN: Sub-microsecond (890 ns) trading execution research system
submicro.krishnabajpai.me
9 comments
6 months ago
krish678
5 points
100.
▲
Show HN: Turn OpenClaw in a high performing development team with DevClaw
github.com/laurentenhoor
6 comments
4 months ago
laurentenhoor
5 points
101.
▲
Ask HN: Internships in High School?
4 comments
6 years ago
etherio
4 points
102.
▲
Show HN: Tilth v0.5.0 –> ~40% cheaper AI code navigation (160 runs, 3 models)
2 comments
4 months ago
jahala
4 points
103.
▲
Show HN: Claude-ts – Translation proxy to fix non-English token waste in Claude
github.com/kimi230
discuss
4 months ago
kiimdonglin
4 points
104.
▲
Show HN: ANMA, boundary contracts for cheaper AI coding agents
github.com/anma-labs
2 comments
a day ago
nxy
3 points
105.
▲
Show HN: I built a LLM human rights evaluator for HN (content vs. site behavior)
observatory.unratified.org
2 comments
4 months ago
9wzYQbTYsAIc
3 points
106.
▲
Show HN: Omni-Glass – Rust app that turns screen pixels into MCP tool calls
github.com/goshtasb
1 comment
4 months ago
goshtasb
3 points
107.
▲
Show HN: I ran every Claude agent turn through the Batch API
eran.sandler.co.il
discuss
2 months ago
erans
3 points
108.
▲
Show HN: Auto-generated titles and colors for parallel Claude Code sessions
github.com/jbarbier
discuss
2 months ago
julien421
3 points
109.
▲
We Replaced Every Tool Claude Code Ships With
discuss
3 months ago
neilbb
3 points
110.
▲
Show HN: ClaudeTerminal – A tabbed terminal manager for Claude Code
github.com/Mr8BitHK
discuss
4 months ago
mr8bit
3 points
111.
▲
Show HN: HN Showcase – I rebuilt my 2011 Show HN gallery with AI curation
hnshowcase.com
discuss
4 months ago
ssong
3 points
112.
▲
Show HN: Tilth v0.3 – 17% cheaper AI code navigation (279 runs, 3 Claude models)
discuss
4 months ago
jahala
3 points
113.
▲
How I got 300+ HN points posting a 5yo+ link that made the front page for 20hrs
3 comments
14 years ago
Hawkee
2 points
114.
▲
Show HN: AgentShield – Stop AI agents from spending money unsupervised
agentshieldv2-dashboard-production.up.railway.app
1 comment
a month ago
lucarizzo1010
2 points
115.
▲
Show HN: Reduce LLM token use by ~30% with this MCP/CLI tool(Claude benchmarked)
1 comment
4 months ago
jahala
2 points
116.
▲
Show HN: Escape the Room, bounded AI stats game
github.com/AymanJabr
discuss
3 months ago
AymanJabr
2 points
117.
▲
Show HN: Tested 12 LLMs with few-shot examples
discuss
3 months ago
shuntaro-okuma
2 points
118.
▲
Show HN: HDC-based function caller ranks #2 on BFCL V4 – $2.08 vs. Opus at $87
github.com/glyphh-ai
discuss
3 months ago
timmetime
2 points
119.
▲
Show HN: Claude Skill for temporary cost tracking
github.com/jbdamask
discuss
4 months ago
jbdamask
2 points
120.
▲
Show HN: OmniGlass – Executable AI screen snips with kernel-level sandboxing
github.com/goshtasb
discuss
4 months ago
goshtasb
2 points
More