Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Login
Top
New
Best
Ask
Show
Jobs
121.
▲
Show HN: A CLI to query the unsealed court files with local LLMs
(github.com/simulationship)
2 points
simulationship
3 months ago
discuss
122.
▲
Show HN: ESP32-S3 probe – a UART "flight recorder" with auto frame decoder
(github.com/choihimchan)
2 points
octablock
4 months ago
discuss
123.
▲
Show HN: ChatProjects Open-source WordPress plugin for document RAG and chat
(github.com/chatprojects-com)
2 points
morog
4 months ago
discuss
124.
▲
Show HN: Parquetastic – a browser-based Parquet metadata inspector
(parquetastic.dev)
2 points
cgfloat
4 months ago
discuss
125.
▲
Show HN: Distill – Remove redundant RAG context in 12ms, no LLM calls
2 points
sidk24
5 months ago
discuss
126.
▲
Show HN: Gcommit – clustering code changes semantically
(github.com/yp583)
2 points
yp583
5 months ago
discuss
127.
▲
Show HN: Veriduct Prime – Format destruction framework for binary evasion
(github.com/Bombadil-Systems)
2 points
float_val
6 months ago
discuss
128.
▲
Show HN: RAG-TUI – Visual chunking debugger for RAG pipelines in the terminal
(pypi.org)
2 points
rasinmuhammed
6 months ago
discuss
129.
▲
Show HN: A simple app to collect people's info at events (bluetooth)
2 points
fcpguru
7 months ago
discuss
130.
▲
Show HN: DeepContext MCP – Large Codebase Search for Codex and Claude Code
(github.com/Wildcard-Official)
2 points
kaushikmahorker
9 months ago
discuss
131.
▲
Show HN: Runtime – skills-based browser automation that uses fewer tokens
(github.com/runtime-org)
2 points
tito777
10 months ago
discuss
132.
▲
Show HN: Manifold is a platform for workflow automation using AI assistants
(github.com/intelligencedev)
2 points
Art9681
a year ago
discuss
133.
▲
Show HN: Contextual AI Document Parser – Infer hierarchy for long, complex docs
2 points
ishan_sinha
a year ago
discuss
134.
▲
Show HN: TaskVenture–Break Tasks Down into RPG-Like Quests for ADHD Programmers
(taskventure.vercel.app)
2 points
its_down_again
a year ago
discuss
135.
▲
Show HN: Code retrieval findings from a real-world benchmark
(github.com/Storia-AI)
2 points
CuriousJ
2 years ago
discuss
136.
▲
Show HN: I just made my $48k profit AI chat bubble open-sourced
(github.com/szguoxz)
2 points
luanxr2000
2 years ago
discuss
137.
▲
Show HN: RepoGPT – question answering over repos using contextual chunking
(github.com/alexminnaar)
2 points
iknownothing12
3 years ago
discuss
138.
▲
Show HN: Go DDOS Yourself (serverless-artillery)
2 points
erikerikson
9 years ago
discuss
139.
▲
Show HN: Picunic – convert image to Unicode art using ML
(mnur.me)
1 point
mntalateyya
5 months ago
5 comments
140.
▲
Show HN: RAG Firewall – retrieval-time guardrails for LangChain/LlamaIndex
(github.com/taladari)
1 point
talbuilds
9 months ago
3 comments
141.
▲
Show HN: RAG Architecture for optimizing retrieval volume/relevancy tradeoff
(github.com/darwinapps)
1 point
Gregoryy
5 months ago
2 comments
142.
▲
Show HN: Repair-JSON-stream – Fix broken JSON from LLM streaming (1.7x faster)
(github.com/prxtenses)
1 point
prxtenses
5 months ago
2 comments
143.
▲
Show HN: Simple API to Compress Large Audio/Video Files for AI Transcriptions
(github.com/vfssantos)
1 point
vfssantos
2 years ago
2 comments
144.
▲
Ask HN: Anybody Know of an AI / LLM Based JavaScript Unminifier?
1 point
mfbx9da4
3 years ago
2 comments
145.
▲
Can application layer improve local model output quality?
1 point
acro-v
6 months ago
1 comment
146.
▲
Obsidian-native memory for your Claude Code sessions
1 point
Alendronat
a month ago
discuss
147.
▲
Show HN: Build queryable packs for AI agents from videos, podcasts, and files
(github.com/buralog)
1 point
buralog
2 months ago
discuss
148.
▲
Show HN: Portable offline LLM knowledge system that runs in browser
1 point
muthuishere
2 months ago
discuss
149.
▲
Show HN: VectorLens – See why your RAG hallucinates, no config
1 point
gustav-proxi
3 months ago
discuss
150.
▲
Show HN: RustyRAG lowest-latency open-source RAG on GitHub
(github.com/AlphaCorp-AI)
1 point
zer0tokens
3 months ago
discuss
More