HK
Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Top
New
Best
Ask
Show
Jobs
Request
31.
▲
Badonkatrunc, a jQuery plugin for dynamic text layout and truncation
github.com/plexipixel
discuss
14 years ago
joelday
2 points
32.
▲
Stretch-Hash-and-Truncate, a novel algorithm for extreme DNS privacy
github.com/jedisct1
discuss
7 years ago
jedisct1
2 points
33.
▲
Show HN: Suture – a reverse proxy that repairs truncated JSON in LLM streams
github.com/tensorhq
discuss
19 days ago
nabucodonosor
1 points
34.
▲
Go-panikint: Go compiler that panics on arithmetic and truncation issues
github.com/trailofbits
discuss
6 months ago
ingve
1 points
35.
▲
Shave: JavaScript plugin for truncating text to fit within an element with a max-height
github.com/dollarshaveclub
discuss
10 years ago
briangonzalez
1 points
36.
▲
Show HN: Wordllama – Things you can do with the token embeddings of an LLM
github.com/dleemiller
36 comments
2 years ago
deepsquirrelnet
370 points
37.
▲
Launch HN: Serra (YC S23) – Open-core, Python-based dbt alternative
84 comments
3 years ago
Alanhlwang
139 points
38.
▲
Show HN: Async – Claude code and Linear and GitHub PRs in one opinionated tool
github.com/bkdevs
46 comments
10 months ago
wjsekfghks
107 points
39.
▲
Show HN: Agent-desktop – Native desktop automation CLI for AI agents
github.com/lahfir
44 comments
2 months ago
lahfir
99 points
40.
▲
Show HN: I built a fast RSS reader in Zig
github.com/superstarryeyes
32 comments
6 months ago
superstarryeyes
90 points
41.
▲
Show HN: Continue.dev releases local, open-source tab-autocomplete
continue.dev
3 comments
2 years ago
sestinj
53 points
42.
▲
Show HN: Logchef – Schema-agnostic log viewer for ClickHouse
github.com/mr-karan
3 comments
a year ago
mr-karan
41 points
43.
▲
Show HN: Keep large tool output out of LLM context: 3x accuracy 95% fewer tokens
github.com/lourencomaciel
1 comment
4 months ago
loumaciel
10 points
44.
▲
Show HN: Wosp – advanced full-text search on the command line
github.com/atrettel
2 comments
8 months ago
atrettel
8 points
45.
▲
Show HN: Llmbuffer – Python library for cache-optimized LLM conversation history
github.com/scottpurdy
1 comment
12 days ago
scottmp10
7 points
46.
▲
Show HN: Quorum-free replicated state machine built atop S3
github.com/io-s2c
discuss
5 months ago
mzazaipsc
6 points
47.
▲
Show HN: Brainfuck to RISC-V JIT compiler written in Zig
github.com/evelance
3 comments
a year ago
0x000xca0xfe
5 points
48.
▲
Show HN: xmllm – Structured LLM streaming output using lenient XML parsing
github.com/padolsey
discuss
2 years ago
padolsey
5 points
49.
▲
Show HN: Decision Guardian – Enforce ADRs on PRs
8 comments
4 months ago
iamalizaidi
4 points
50.
▲
Show HN: PlanckClaw an AI agent in 6832 bytes of x86-64 assembly
github.com/frntn
4 comments
3 months ago
frntn
4 points
51.
▲
Ask HN: Best practice for posting links to large Mastodon threads?
1 comment
2 years ago
WhyUVoteGarbage
4 points
52.
▲
Show HN: AriaType v0.3 Has Come – Fast and Private Voice to Text Input Client
github.com/joe223
discuss
2 months ago
Joe_Harris
4 points
53.
▲
Show HN: I built proxy that keeps RAG working while hiding PII
discuss
3 months ago
rohansx
4 points
54.
▲
Show HN: A Fast JSON Formatter
github.com/usebruno
discuss
8 months ago
helloanoop
3 points
55.
▲
Show HN: Evolutionary (binary) JSON DBS keeping an immutable revision history
discuss
3 years ago
lichtenberger
3 points
56.
▲
Show HN: How simple (but clever) algorithms can find label issues in datasets
playground.cleanlab.ai
discuss
4 years ago
calebchiam
3 points
57.
▲
Show HN: Circe – Deterministic, offline-verifiable receipts for AI agent actions
github.com/wv26296-ux
5 comments
5 months ago
W_rey45
2 points
58.
▲
Show HN: I built a 2nd-order PyTorch optimizer for LLMs that runs on 16GB GPUs
4 comments
2 months ago
dnosoz
2 points
59.
▲
We built the fastest data replication tool in the world using Go
1 comment
9 months ago
Cappybara12
2 points
60.
▲
Show HN: Decision Guardian – Auto-surface architectural context on PRs and CLI
discuss
4 months ago
iamalizaidi
2 points
More