Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Login
Top
New
Best
Ask
Show
Jobs
151.
▲
Show HN: Destructive_command_guard (Dcg)
(github.com/Dicklesworthstone)
3 points
eigenvalue
4 months ago
discuss
152.
▲
Show HN: Coi – A compiled-reactive language for high-performance WASM apps
3 points
io_eric
5 months ago
discuss
153.
▲
Show HN: An MPSC Queue Optimizing for Non-Uniform Bursts and Bulk Operations
(github.com/dakingffo)
3 points
dakingffo
6 months ago
discuss
154.
▲
Show HN: In-browser data exploration toolkit
(github.com/Datakitpage)
3 points
parsabg
6 months ago
discuss
155.
▲
Show HN: DeepTeam – Penetration Testing for LLMs
(github.com/confident-ai)
3 points
jeffreyip
a year ago
discuss
156.
▲
Show HN: I built a 2nd-order PyTorch optimizer for LLMs that runs on 16GB GPUs
2 points
dnosoz
a month ago
4 comments
157.
▲
Show HN: Seshions – Orchestrate multi-agent coding agents from one terminal
2 points
danhergir
3 months ago
4 comments
158.
▲
Why stop at 1M tokens when you can have 10M?
2 points
Zen_Sherbert
7 months ago
4 comments
159.
▲
Show HN: Homomorphically Encrypted Vector Database
(github.com/cloneisyou)
2 points
cloneisme
4 months ago
3 comments
160.
▲
Apple predicted the rise of local LLMs, hence the M2 Ultra
2 points
behnamoh
3 years ago
3 comments
161.
▲
Show HN: Shard – Stop watching one AI agent code for 45 min. Run four at once
(github.com/nihalgunu)
2 points
nihalgunu
3 months ago
2 comments
162.
▲
Show HN: Codebrief – Make sense of AI-generated code changes
(github.com/that-one-arab)
2 points
mo-dulaimi
3 months ago
2 comments
163.
▲
Show HN: Direct to silicon DLinear AI accelerator on the Sky130 open-source node
(github.com/Aperion-Technologies)
2 points
NotJustBinary
3 months ago
2 comments
164.
▲
Show HN: OmoiOS–190K lines of Python to stop babysitting AI agents (Apache 2.0)
(github.com/kivo360)
2 points
kanddle
3 months ago
2 comments
165.
▲
Detect Fair Queuing on an internet connection
(github.com/muxamilian)
2 points
muxamilian
3 years ago
2 comments
166.
▲
Ask HN: A fast, Rust HTML parser that works?
2 points
thatxliner
3 years ago
2 comments
167.
▲
Show HN: Efficient LLM Architectures for 32GB RAM (Ternary and Sparse Inference)
(github.com/opengraviton)
2 points
fatihturker
3 months ago
1 comment
168.
▲
Show HN: Qgate – Classical trajectory filtering for noisy quantum circuits
(github.com/ranbuch)
2 points
ranbuch
3 months ago
1 comment
169.
▲
Show HN: Feistly – Cryptographically secure ID obfuscation with Feistel cipher
(github.com/JunDev76)
2 points
jundev76
4 months ago
1 comment
170.
▲
Show HN: ClickHouse Managed Postgres
2 points
saisrirampur
4 months ago
1 comment
171.
▲
Show HN: Combo – A high-performance browser video editor SDK using WebCodecs
2 points
snapmotion
5 months ago
1 comment
172.
▲
Show HN: Fleet – Python supervisor for running coding agents in parallel
2 points
sermakarevich
12 days ago
discuss
173.
▲
Show HN: Ccmd – TUI to audit and clean developer caches
(github.com/juliensimon)
2 points
julsimon
2 months ago
discuss
174.
▲
Show HN: Batty – Run a team of AI coding agents in tmux with test gating
(github.com/battysh)
2 points
Zedmor
2 months ago
discuss
175.
▲
Show HN: Local-first agent memory loop 48hrs before the Claude Code leak
(github.com/Bitterbot-AI)
2 points
Doug_Bitterbot
2 months ago
discuss
176.
▲
Show HN: Giving HTML, Canvas Superpowers
(github.com/yeargun)
2 points
yeargun
2 months ago
discuss
177.
▲
BetterKV – A multithreaded Rust Redis alternative, 10-30x faster in benchmarks
2 points
1jmdev
3 months ago
discuss
178.
▲
Show HN: Fastify's slow startup is an AJV problem – here's a drop-in fix
2 points
greatvenerable
3 months ago
discuss
179.
▲
Show HN: AlphaEvolve inspired evolution harness for Pokemon
(github.com/papercomputeco)
2 points
brianllamar
3 months ago
discuss
180.
▲
Sumi – Open-source voice-to-text with local AI polishing
2 points
alkd
3 months ago
discuss
More