Show HN
hyperlogue /
r3
R3 – A Local Code Review Tool for You and Your AI Agent
GOOD CODE. GREAT DISCOVERIES.
Your next
rabbit hole.
Open-source projects. Clever little tools. Big ideas.
Unearthed from the Hacker News community.
YCommunity signal. Human curiosity.No paid placements.
2,872unique repositories
4,114Show HN stories¹
3,330GitHub links¹
July 2026 snapshot
THE COMMUNITY’S CORNER OF THE INTERNET
AI & agents✳
Ranked by HN points, not GitHub stars
christopherkarani /
ContextCore
GPU-accelerated context memory for on-device AI agents on Apple Silicon
gni /
maquis
The fastest coding agent for offline usage?
tonypls /
agentic-product-launch
A launch playbook your coding agent can run – it launched itself
ananfauh7 /
MRVPlatform
Resilience testing for AI models against radiation-induced bit flips
piyushkhemka /
sip
Built a tracker to estimate water wastage when talking to Claude
Show HN
baristaGeek /
minions-army-harness
Minions Army Harness – Small Version of Claude Tag
breschio /
drawbridge
Drawbridge – Design Editor for Claude Code and Cursor
Show HN
skyphusion-labs /
postern
Postern, an email system for both humans and agents
Tania-coder /
SEISMOGRAPH
Seismograph – open-source early warning for silent LLM API drift
Show HN
Michael-Ax64 /
K4-AlgebraicSwarm
A self-correcting algebraic agent swarm
TommyTranX /
traceburn
Traceburn, a local profiler that found 69% avoidable agent spend
Show HN
MaorBril /
agentic
Agentic – Run Claude Code on different models with routing and budgets
Show HN
Clear-Sights /
Lever
Lever – replace agent token transport with deterministic hooks
capitalone /
VulnHunter
VulnHunter: Agentic AI Security Tool
Show HN
scouttyg /
writekin
Writekin – fine-tune a local LLM on your own writing, on your Mac
kiycoh /
silica-agent
Silica, a notes/codebase agent that reverts its edits if they break coherence
Show HN
amitkumardubey /
praana
Praana – a terminal coding agent that curates its own context