Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Login
Top
New
Best
Ask
Show
Jobs
331.
▲
Show HN: OS Megakernel that match M5 Max Tok/w at 2x the Throughput on RTX 3090
(github.com/Luce-Org)
6 points
GreenGames
2 months ago
1 comment
332.
▲
Tell HN: Llamacpp now supports unified system RAM offloading on Linux
6 points
dabockster
2 months ago
discuss
333.
▲
Show HN: Less Slow C++
(github.com/ashvardanian)
6 points
ashvardanian
a year ago
discuss
334.
▲
Show HN: LLGTRT: TensorRT-LLM+Rust server w/ OpenAI-compat and Structured Output
(github.com/guidance-ai)
6 points
mmoskal
2 years ago
discuss
335.
▲
Show HN: Costanza – an autonomous AI agent that can't be turned off
(ahrussell.com)
5 points
aruss
a month ago
3 comments
336.
▲
Show HN: Audio AI had a wild day – 5 major open-source / real-time TTS drops
(github.com/FlashLabs-AI-Corp)
5 points
pratik227
4 months ago
2 comments
337.
▲
Show HN: Paseo – Open-source coding agent interface (desktop, mobile, CLI)
5 points
boudra
2 months ago
1 comment
338.
▲
Show HN: I built an open-source AI system for drones
(github.com/stephansturges)
5 points
stephanst
3 years ago
1 comment
339.
▲
The Oats Protocol – Open Agent Tools for Local Coding Agents
5 points
dsdevjay
18 days ago
discuss
340.
▲
Show HN: LLMKube – Kubernetes for Local LLMs with GPU Acceleration
(github.com/defilantech)
5 points
defilan
7 months ago
discuss
341.
▲
Show HN: WebGPU FTW with Splat-Transform
(github.com/playcanvas)
5 points
slimbuck
8 months ago
discuss
342.
▲
Show HN: LLMOne – Deploy LLMs from bare metal to production in hours
(github.com/EM-GeekLab)
5 points
pescn
a year ago
discuss
343.
▲
Show HN: Arch-Function: 3B parameter LLM that beats GPT-4o on function calling
(huggingface.co)
5 points
sparacha
2 years ago
discuss
344.
▲
Vectorless: open-source PDF chatbot without RAG
4 points
richardmeng
10 months ago
4 comments
345.
▲
Show HN: FP32 matmul of large matrices up to 24% faster than cuBLAS on a 4090
(github.com/arekpaterek)
4 points
ap4
2 years ago
4 comments
346.
▲
Show HN: A navigable map and recommender for 17M music entities
(toposonico.com)
4 points
deppep
a month ago
2 comments
347.
▲
Show HN: Turkish Sieve Engine – GPU-Accelerated Prime Number Generator
(github.com/bilgisofttr)
4 points
bilgisoft
5 months ago
1 comment
348.
▲
Show HN: WattSeal – PC power consumption monitor
(github.com/Daminoup88)
4 points
Daminoup
3 months ago
discuss
349.
▲
Show HN: Vocalinux // 100% offline voice typing for Linux
(vocalinux.com)
4 points
jatinkrmalik
4 months ago
discuss
350.
▲
Show HN: ReFrame – Linux remote desktop that supports Login on Wayland/TTY
(github.com/AlynxZhou)
4 points
AlynxZhou
4 months ago
discuss
351.
▲
Show HN: modal-cuda – CLI to run CUDA .cu programs on Modal GPUs
(github.com/ExpressGradient)
4 points
Sai_Praneeth
7 months ago
discuss
352.
▲
Run 35B LLMs on Dual Pascal GPUs with QLoRA
4 points
rickesh_tn
8 months ago
discuss
353.
▲
ExpidusOS, the mobile and desktop operating system
4 points
TheComputerGuy
6 years ago
discuss
354.
▲
Show HN: Tabby – AI Coding Assistant Runs on Apple M1/M2 GPU
(github.com/TabbyML)
3 points
wsxiaoys
3 years ago
2 comments
355.
▲
Show HN: Research-Backed Multi-Agent System for Autonomous Development
(github.com/asklokesh)
3 points
slogansand
5 months ago
1 comment
356.
▲
Show HN: Velda – Run any command directly on cloud compute
(velda.io)
3 points
eagleonhill
9 months ago
1 comment
357.
▲
Show HN: Collider – the platform for local LLM debug and inference at warp speed
(github.com/gotzmann)
3 points
Ambix
3 years ago
1 comment
358.
▲
Show HN: Thaw – Git branch for a running LLM (fork agents, skip prefill)
(github.com/thaw-ai)
3 points
nilsmatteson
6 days ago
discuss
359.
▲
Show HN: Local video search with Qwen3-VL: no API, runs on Apple Silicon, GPUs
(github.com/ssrajadh)
3 points
sohamrj
2 months ago
discuss
360.
▲
Show HN: AluminatiAi – Per-job GPU energy cost tracking (open source)
3 points
AluminatiAi
3 months ago
discuss
More