HK
Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Top
New
Best
Ask
Show
Jobs
Request
421.
▲
A prompt convention that preserves epistemic hygiene across multi-agent chains
discuss
4 months ago
mdiskint37
1 points
422.
▲
Show HN: RepoCrunch – Analyze any GitHub repo's health in seconds
discuss
4 months ago
chillkim
1 points
423.
▲
Show HN: SciCraft – generate scientific Claude Code skills on demand (176 built)
github.com/jaechang-hits
discuss
4 months ago
jaechang
1 points
424.
▲
Show HN: Kremis – Deterministic memory graph for AI agents (Rust)
github.com/M2Dr3g0n
discuss
4 months ago
M2Dr3g0n
1 points
425.
▲
Show HN: Fixing AI's Core Flaws, A protocol cuts LLM token waste by 40–70%
discuss
4 months ago
WujieGuGavin
1 points
426.
▲
Show HN: A text-only reasoning core for LLMs (MIT, system prompt and self-test)
github.com/onestardao
discuss
4 months ago
wfgy-github
1 points
427.
▲
MiRAGE: Open-source framework for multimodal RAG evaluation
discuss
4 months ago
mmhetric
1 points
428.
▲
Show HN: Sales Agent Benchmark – SWE-Bench for sales AI agents (open source)
sales-agent-benchmarks.fly.dev
discuss
4 months ago
a1j9o94
1 points
429.
▲
Show HN: Parametric Hubris – Beating GPT-5 on SimpleQA with forced retrieval
dev.thelastrag.de
discuss
4 months ago
LutumVeritas
1 points
430.
▲
AI skill for generating linter configs and repairing code
discuss
5 months ago
zzzzjhello
1 points
431.
▲
I Built a Claude Code Plugin That Detects and Blocks It Before Changes Happen
discuss
5 months ago
andreahlert
1 points
432.
▲
Show HN: Nono – Kernel-enforced sandboxing for AI agents
github.com/lukehinds
discuss
5 months ago
decodebytes
1 points
433.
▲
Show HN: Context9 – A private-first Knowledge MCP for real-time local doc sync
github.com/Prism-Shadow
discuss
5 months ago
PrismShadow
1 points
434.
▲
Show HN: CPU-based Neural Net. Zero floats. Returns "I don't know"
github.com/probabilistic-minds-consortium
discuss
5 months ago
kwojno
1 points
435.
▲
Show HN: Hackmenot – Security scanner for AI-generated code
github.com/b0rd3aux
discuss
5 months ago
b0rd3aux
1 points
436.
▲
Show HN: Measuring runtime strain in autonomous AI systems
github.com/willshacklett
discuss
5 months ago
PapaShack45
1 points
437.
▲
Show HN: Intent-Driven Development with NTNT
github.com/ntntlang
discuss
5 months ago
joshcramer
1 points
438.
▲
Show HN: Loclean – Local semantic data cleaning with LLMs and Pydantic
github.com/nxank4
discuss
5 months ago
nxank4
1 points
439.
▲
Show HN: SONA – An AI-native serialization format to reduce "Syntax Tax"
github.com/fabiosleal
discuss
5 months ago
fabio2620
1 points
440.
▲
Show HN: BlueMouse – AI Code Generator with 17-Layer Validation
github.com/peijun1700
discuss
5 months ago
bluemouse_ai
1 points
441.
▲
Show HN: VAAK (Voice-Activated Autonomous-Knowledge-System)
github.com/ayushmaanbhav
discuss
5 months ago
ayushmaanbhav
1 points
442.
▲
Hermit-AI – An offline, privacy-first RAG chatbot for ZIM files
discuss
5 months ago
ImDelivered
1 points
443.
▲
Show HN: Context Protocol, a sovereign-first workflow for thinking with LLMs
discuss
6 months ago
zpusmani
1 points
444.
▲
Show HN: Open-source, citations-first RAG search for Epstein Files
github.com/benbaessler
discuss
6 months ago
benbaessler
1 points
445.
▲
Show HN: Leash – Security guardrails for AI coding agents
github.com/melihmucuk
discuss
6 months ago
melihmucuk
1 points
446.
▲
Show HN: SiteIQ–Automated security tests for LLM APIs(prompt inj,jailbreaks,DoS)
github.com/sastrophy
discuss
6 months ago
sastrophy
1 points
447.
▲
Show HN: Interlock – Circuit breaker for AI infrastructure with signed audits
discuss
6 months ago
CULPRITCHAOS
1 points
448.
▲
Show HN: Ghost – Local-first agent that runs and auto-fixes Python tests
github.com/tripathiji1312
discuss
6 months ago
swarnim1312
1 points
449.
▲
Show HN: Agenteract – Drive mobile apps with LLMs using UI trees (no vision)
discuss
6 months ago
mribbons
1 points
450.
▲
StillMe – an open-source "transparent RAG" framework
discuss
6 months ago
Anh_Nguyen_vn
1 points
More