HK
Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Top
New
Best
Ask
Show
Jobs
Request
61.
▲
Sharing learnings from evaluating Million+ LLM responses
discuss
3 years ago
sourabh03agr
3 points
62.
▲
Show HN: Graphmind – Persistent Memory and Graph for Claude Code (MCP, CLI, GUI)
github.com/aouicher
2 comments
a month ago
aouicher
2 points
63.
▲
Show HN: OpenGranola – meeting copilot that searches your notes in real time
2 comments
3 months ago
yazinsai
2 points
64.
▲
Show HN: Shared team context for AI coding sessions with ambient intelligence
github.com/norrietaylor
discuss
3 months ago
torrienaylor
2 points
65.
▲
Show HN: Agent Memory DB – Episodic memory for agents (97.5% vs. 85% recall)
github.com/sathvikkurap
discuss
4 months ago
andy9829
2 points
66.
▲
Show HN: Signal Engine – filter the noise from static analysis results
github.com/armoredcode
discuss
5 months ago
thesp0nge
2 points
67.
▲
Show HN: Multimodal Benchmarks
github.com/mixpeek
discuss
7 months ago
Beefin
2 points
68.
▲
Show HN: Dream – An LLM memory architecture using adaptive TTL to control cost
discuss
7 months ago
matheusdevmp
2 points
69.
▲
Show HN: AikiPedia – An Open-Source AI-Enhanced Interface for Wikipedia
aikipedia.vercel.app
discuss
8 months ago
grenishrai
2 points
70.
▲
Show HN: HyperMind – Experimental human-like memory layer for AI apps (OS)
github.com/vashuteotia123
discuss
8 months ago
vishalteotia
2 points
71.
▲
Show HN: RIHU – Beyond RAG: Retrieval as Geometry, Not Vectors
github.com/shinmaruko1997
discuss
8 months ago
shinmaruko1997
2 points
72.
▲
Show HN: Chapter – Real-time lead-gen from public activity (open source)
github.com/chapter-gtm
discuss
2 years ago
robinyapockets
2 points
73.
▲
Show HN: Roampal – a local memory layer that learns from outcomes
github.com/roampal-ai
4 comments
7 months ago
roampal
1 points
74.
▲
Show HN: Swik – catalog of asset-specific sentiment inversions for financial NLP
2 comments
3 months ago
multidude
1 points
75.
▲
HMP: A Cognitive Application Protocol for Agent Networks
2 comments
5 months ago
kagvi13
1 points
76.
▲
Principally new search
2 comments
7 years ago
21xhipster
1 points
77.
▲
Why codex /goal fails on complex workflows: compaction amnesia and context rot
discuss
a month ago
shaurya-sethi
1 points
78.
▲
Show HN: AI agents who prevent context drift through gossip
wuphf.team
discuss
a month ago
najmuzzaman
1 points
79.
▲
Show HN: Iris – first MCP-native eval and observability tool for AI agents
github.com/iris-eval
discuss
3 months ago
iparent
1 points
80.
▲
Show HN: arxiv-digest: Daily robotics paper scouting for OpenClaw and Zotero
github.com/tb5z035i
discuss
3 months ago
tb5z035i
1 points
81.
▲
Show HN: Sift – Score your feed locally with EmbeddingGemma
github.com/shreyaskarnik
discuss
4 months ago
shreyask
1 points
82.
▲
Show HN: I built an open-source X/Twitter filter that uses X's own AI against it
github.com/DaveyLovesCode
discuss
5 months ago
DaveyLovesCode
1 points
83.
▲
Show HN: I built a tool to help freelancers find better Upwork jobs with AI
github.com/daniloedu
discuss
8 months ago
daniloedu
1 points
84.
▲
Show HN: Syneva – A Chatbot under 3kb that fits in a QR code
github.com/Kuberwastaken
discuss
a year ago
kuberwastaken
1 points
85.
▲
Guide to Adding Custom Attributes in Medusa.js
discuss
2 years ago
GregTomaka
1 points
86.
▲
Relevancy.js - sorting and weighting strings by relevancy with javascript
github.com/padolsey
discuss
14 years ago
mars
2 points
87.
▲
Show HN: RAG Architecture for optimizing retrieval volume/relevancy tradeoff
github.com/darwinapps
2 comments
5 months ago
Gregoryy
1 points
88.
▲
Launch HN: Traceloop (YC W23) – Detecting LLM Hallucinations with OpenTelemetry
72 comments
2 years ago
GalKlm
101 points
89.
▲
Show HN: UpTrain (YC W23) – open-source tool to evaluate LLM response quality
demo.uptrain.ai
discuss
3 years ago
sourabh03agr
12 points
90.
▲
RAG Without a Vector DB, PostgreSQL and Faiss for AI-Powered Docs
2 comments
a year ago
rahmansahinler1
4 points
More