HK
Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Top
New
Best
Ask
Show
Jobs
Request
181.
▲
Show HN: ElasticMM – 4.2× Faster Multimodal LLM Serving (NeurIPS 2025 Oral)
1 comment
6 months ago
PaperWeekly
1 points
182.
▲
Show HN: Finite element simulation library built in JavaScript
github.com/FEAScript
1 comment
10 months ago
nikoscham
1 points
183.
▲
Ask HN: Ideas for small projects
1 comment
10 years ago
zuzuleinen
1 points
184.
▲
Show HN: Stochastc Unit Commmitment Using Genetic Algorithm
github.com/bellpesce
discuss
13 days ago
guarana
1 points
185.
▲
Show HN: AI agents who prevent context drift through gossip
wuphf.team
discuss
a month ago
najmuzzaman
1 points
186.
▲
Show HN: The Trawl CLI, trudge through agent harness logs for shit and giggles
the-daily-claude.github.io
discuss
2 months ago
ElFitz
1 points
187.
▲
Show HN: Volresample – 3D volume resampling up to 13× faster than PyTorch on CPU
github.com/JoHof
discuss
4 months ago
hojijoji
1 points
188.
▲
Show HN: AgentDX – Open-source linter and LLM benchmark for MCP servers
github.com/agentdx
discuss
4 months ago
yamarldfst
1 points
189.
▲
PgDog: Connection pooler, load balancer and sharder for PostgreSQL
discuss
4 months ago
levkk
1 points
190.
▲
Show HN: Pcons: new software build tool in Python, inspired by SCons and CMake
github.com/DarkStarSystems
discuss
4 months ago
darkstarsys
1 points
191.
▲
Show HN: NanoSLG – Hack Your Own Multi-GPU LLM Server (5x Faster, Educational)
github.com/Guney-olu
discuss
4 months ago
geniusyan
1 points
192.
▲
Show HN: Sofia Core – Open-source AI infrastructure with biological computing
github.com/emeraldorbit
discuss
4 months ago
emeraldorbit
1 points
193.
▲
Show HN: Source code graphRAG for Java/Kotlin development based on jQAssistant
github.com/2015xli
discuss
5 months ago
artigent
1 points
194.
▲
Show HN: ARIA – P2P distributed inference protocol for 1-bit LLMs on CPU
github.com/spmfrance-cloud
discuss
5 months ago
anthonymu
1 points
195.
▲
Show HN: Doom rendered in OpenSCAD geometry, now playable in browser
doom.mikeayles.com
discuss
5 months ago
mikeayles
1 points
196.
▲
"A public origin record for a phase‑resonance hybrid computing architecture"
discuss
5 months ago
LUMENPIXEL
1 points
197.
▲
Show HN: Infinate –O(k)constant-time spatial attention for unlimited LLM context
github.com/ch1pu
discuss
5 months ago
ch1pu
1 points
198.
▲
Show HN: ZXC – Asymmetric, +40% decode vs. LZ4 on ARM (C, BSD-3, Fuzzed)
github.com/hellobertrand
discuss
6 months ago
pollop_
1 points
199.
▲
Show HN: LLM Inference Performance Analytic Tool for Moe Models (DeepSeek/etc.)
github.com/kevinyuan
discuss
7 months ago
kevin-2025
1 points
200.
▲
Show HN: Splintr – Rust BPE tokenizer, 12x faster than tiktoken for batches
github.com/farhan-syah
discuss
7 months ago
fs90
1 points
201.
▲
Show HN: FromGtoG 8 – Cross-platform desktop tool to batch backup ALL Git repos
github.com/goto-eof
discuss
8 months ago
cbrx31
1 points
202.
▲
Show HN: Gradle-less APK builds on Android
github.com/Junaid-Ibrahim
discuss
9 months ago
mujeeeb
1 points
203.
▲
Show HN: Floaty – Multithreaded Fluid and Soft Body Simulation for Browsers
floaty-fluid.netlify.app
discuss
10 months ago
matsuoka-601
1 points
204.
▲
Show HN: Benchmax, a new open-source RL environment framework for LLM finetuning
github.com/cgftinc
discuss
a year ago
kumama
1 points
205.
▲
Show HN: UIT – Library for performant, modular, low-memory file processing
github.com/janwilmake
discuss
a year ago
janwilmake
1 points
206.
▲
Ask HN: What language do you use for performant web jobs and services?
discuss
a year ago
rahil627
1 points
207.
▲
Show HN: tparagen -A tool to make Go test code parallel-ready in bulk
github.com/sho-hata
discuss
2 years ago
sho-hata
1 points
208.
▲
Show HN: milo c++ constexpr crypto library
github.com/milosob
discuss
3 years ago
milosob
1 points
209.
▲
Show HN: Auto-scaling worker pool library, using Go 1.18 generics
github.com/cmitsakis
discuss
4 years ago
cmitsakis
1 points
210.
▲
Concurrency for JavaScript
discuss
15 years ago
sheremetyev
1 points
More