HK
Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Top
New
Best
Ask
Show
Jobs
Request
841.
▲
llcat: /usr/bin/cat for LLMs
github.com/day50-dev
discuss
5 months ago
lioeters
2 points
842.
▲
Show HN: Sigma Runtime – model-agnostic identity control for LLMs
github.com/sigmastratum
discuss
5 months ago
teugent
2 points
843.
▲
Show HN: Fast (0.5 GB/SEC) dedup utility for the era of LLMs written in C23
github.com/ThirdLetterC
discuss
6 months ago
yehors
2 points
844.
▲
Show HN: MirrorMate – A self-hosted AI smart mirror with local LLMs
github.com/orangekame3
discuss
6 months ago
orangekame3
2 points
845.
▲
Show HN: A CLI That Compiles React, Next.js, TS and Vue for LLMs
github.com/LogicStamp
discuss
6 months ago
AmiteK
2 points
846.
▲
Stop benchmarking LLMs. Make them fight
github.com/AGI-Eval-Official
discuss
6 months ago
jinqueeny
2 points
847.
▲
Show HN: CommerceTXT – llms.txt for e-commerce (95% token reduction)
discuss
6 months ago
tsazan
2 points
848.
▲
Llmwalk: Explore the answer-space of open LLMs
github.com/samwho
discuss
6 months ago
simonpure
2 points
849.
▲
Benchmarking LLMs on whether they can play FizzBuzz
github.com/venkatasg
discuss
6 months ago
_venkatasg
2 points
850.
▲
Hark: Voice prompts for LLMs, meeting minutes, quick voice journaling
github.com/FPurchess
discuss
7 months ago
FPurchess
2 points
851.
▲
Code Evolution: Self-Improving Software with LLMs and Python
github.com/camilochs
discuss
7 months ago
camilochs
2 points
852.
▲
Chess LLM Benchmark: Evaluating LLMs' ability to play chess
github.com/lightnesscaster
discuss
7 months ago
dwohnitmok
2 points
853.
▲
Show HN: Turn Any Website into Clean Markdown for LLMs/RAG with SiteOne Crawler
github.com/janreges
discuss
7 months ago
janreges
2 points
854.
▲
TOON is a compact serialization format for passing structured data to LLMs
github.com/toon-format
discuss
7 months ago
rekl
2 points
855.
▲
Show HN: Painless structured data from LLMs in Rust: rstructor
github.com/clifton
discuss
8 months ago
cliftonk
2 points
856.
▲
Show HN: Ldbg: a Python library to ask LLMs while debugging
github.com/arthursw
discuss
8 months ago
arthursw
2 points
857.
▲
Show HN: ChatGPT clone using open-source LLMs
github.com/kdeps
discuss
8 months ago
jjuliano
2 points
858.
▲
Show HN: LLM-use – Routing, caching and A/B testing for LLMs
github.com/llm-use
discuss
9 months ago
justvugg
2 points
859.
▲
Yzma – local Vision Language Models/LLMs in Go using llama.cpp without CGo
github.com/hybridgroup
discuss
9 months ago
deadprogram
2 points
860.
▲
Show HN: Give LLMs TypeScript tools without writing MCP servers
github.com/jx-codes
discuss
9 months ago
jmcodes
2 points
861.
▲
Show HN: Model-literals, model-aliases, and preference-aligned routing for LLMs
docs.archgw.com
discuss
9 months ago
honorable_coder
2 points
862.
▲
Codegen Scorer – evaluate the quality of code generated by LLMs
github.com/angular
discuss
9 months ago
martypitt
2 points
863.
▲
Introducing BackendBench: how well LLMs and humans can write PyTorch backends
github.com/meta-pytorch
discuss
10 months ago
matt_d
2 points
864.
▲
CLI-based multi-agent trading system using LLMs
github.com/TauricResearch
discuss
10 months ago
mustaphah
2 points
865.
▲
Show HN: LLM‑Simple‑Eval – Easily Benchmark LLMs for Your Use Case
github.com/grigio
discuss
10 months ago
grigio
2 points
866.
▲
LLMs Love Elixir
github.com/Tencent-Hunyuan
discuss
10 months ago
taatparya
2 points
867.
▲
Skynet: Control robots and drones with LLMs via MCP using Bash
github.com/hybridgroup
discuss
10 months ago
deadprogram
2 points
868.
▲
Fine-tuning LLM Agents without Fine-tuning LLMs
github.com/Agent-on-the-Fly
discuss
10 months ago
JnBrymn
2 points
869.
▲
Show HN: prompttest – pytest for LLMs
github.com/decodingchris
discuss
10 months ago
decodingchris
2 points
870.
▲
MemOS: Treating "memory" as a first-class resource for LLMs
github.com/MemTensor
discuss
10 months ago
mustaphah
2 points
More