Show HN
PxyUp /
fitter
I built a scraping engine where the LLM writes configs, not code
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
nashsu /
llm_wiki
LLM Wiki Implementation
akahkhanna /
groundtruth
Groundtruth – checks your AI coding agent's claims against the Git diff
Show HN
whatadewitt /
claude-status-light
Claude Status Light
Show HN
sivaadityacoder /
asl-v6
ASL V6 – Open-source AST red-teaming engine for Python AI agents
0xroylee /
getsuperpower
GetSuperpower, an installable skill tree for coding agents
Show HN
vitalysim /
browser-bridge
Drive your real logged-in Chrome from Claude Code and Codex (MCP)
Show HN
samchon /
lint-plugin-evidence
Evidence Graph – type checking for the specs your AI agent implements
Show HN
YoniRaviv /
Relay
Relay – turn Claude Code into a visual Kanban build loop
Anode1 /
iac
Iac – local message board for agent fleets; blocking recv is the wakeup
Show HN
vagkaratzas /
token-saviour
Token-saviour – agent skill from benchmarking 9 token-saving tools
Show HN
Clear-Sights /
Makoto
Makoto – blocks AI agent claims that contradict its logged actions
Show HN
fengsi /
ufo
UFO – Open-source orchestration for running AI agents unattended
Show HN
SGSI /
claudeometer
Claudeometer – Share and pool Claude usage across a team (macOS, OSS)
Show HN
carlitose /
minnarone
Minnarone – Multimodal agents that watch, listen, and react live
Show HN
dylanneve1 /
talon
Talon: Self-hosted AI agent harness for chat, terminal, and desktop
Show HN
Dicklesworthstone /
destructive_command_guard
Block dangerous Git and shell commands from being executed by agents
igorbarshteyn /
jlens-gguf
Interactive Jacobian-Lens visualizer and live steerer for GGUF models