Show HN
BraveAnn011 /
llm-author-misattribution
3,225 trials of LLMs guessing author age – confident and wrong
好代码，值得被发现。
下一个
宝藏项目.
开源项目、精巧工具，还有让人眼前一亮的点子。
从 Hacker News 社区讨论中，找到你的下一份灵感。
Y社区的眼光，你的好奇心。无付费推荐。
2,872独立仓库
4,114Show HN 帖子¹
3,330GitHub 外链¹
2026 年 7 月快照
社区发现的互联网一角
AI 与智能体✳
按 HN 分数排序，非 GitHub Star 数
Abhijeet777ui /
contextops
ContextOps, an ESLint-like static analyzer for LLM context
Show HN
ninjahawk /
Subtext
LLM Thought Visualization
Show HN
haabe /
mycelium
Mycelium – AI agent plugin guiding you from purpose to market
YoanWai /
agent-manager
Agent-Manager: A Tmux TUI for Running Claude Code, Codex and OpenCode
amruth-sn /
kong
The first agentic reverse engineer
haror1 /
answerwatch
Answerwatch – Track changes in what AI models recommend
Show HN
bruno-de-queiroz /
hoop
Hoop – A sandboxed P2P live collaboration harness for Claude Code
Show HN
SaravananJaichandar /
world-model-mcp
World Model MCP v0.10.0 – cross-runtime memory across 7 coding agents
amalshehu /
pexels-skill
Claude Code skill for searching royalty-free stock photos via the Pexels API
YogiSotho /
warden
Where do you answer"is the agent allowed to do this?"–one place,orevery adapter?
Show HN
Northwood-Systems /
foreman
Foreman, a self-hosted LLM gateway for cost aware model routing
DorShaer /
Husk
Husk – a desktop workspace for terminal AI agents
Show HN
riccardomusumeci11 /
meanwhile
Meanwhile – turn Claude Code idle time into learning
Show HN
eoinmurray /
demolab
Demolab – an opinionated agent-driven computational lab notebook
geludobre /
sovereign-agentops
Sovereign AgentOps – Self-hosted constitutional AI governance for MCP agents
Show HN
toshipepe /
tokimeter
Tokimeter – open-source usage meter for Claude, Codex, Cursor and more
Show HN
yashchimata /
statgate
Statgate, statistically calibrated ship/block CI gates for LLM evals