Show HN
ecrasevvv /
c-fm
C-Flow Matching Inference
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
Show HN
agileAlligator /
mcploitable
Mcploitable – Vulnerable MCP Servers for the OWASP Agentic Top
Show HN
overflowy /
herdr-claude-gpt-adversarial-review-skill
Adversarial code review setup with herdr, Claude and GPT-5.6-sol
Show HN
PJHkorea /
pim-hbm-bypass
HW/SW co-design blueprint for fault recovery in LLM training
langchain-ai /
deepagents
Deepagents
Show HN
tarunlnmiit /
autopilot-jobhunt
Agent scans 130 careers pages nightly, scores jobs vs. your resume
kmeinke /
ssh-cast
SSH-cast – record / watch agents SSH sessions
drwolfgangstegemann-sudo /
ali-reference-implementation
ALI: A Python agent architecture where the normative evaluator is
Show HN
sin-ack /
agent-run
Agent-run – Run a coding agent in a sandboxed environment
OyaAIProd /
oya
Oya – Keep tool outputs away from the LLM to cut tokens and stop injection
Show HN
ndom91 /
open-plan-annotator
Open-plan-annotator – local annotation UI for working with agent plans
devr-tools /
szr
Szr: A safer command output reduction for coding agents
robert-auger /
safer-dependencies
Safer-dependencies claudecode skillpack to secure dependencies during developmnt
Show HN
BrunkenClaas /
lx
LX Coreutils – 72 Unix tools that pipe together, each backed by an LLM
Show HN
kdeps /
turo
Turo – An Aggressive Token-Saving Proxy for CLI AI Agents
Show HN
e35zhang /
property-testing-skill
A prompt to make LLMs write property-based tests
Show HN
Kentucky-ai /
opentakeoff
OpenTakeoff – open-source construction takeoff your AI agent can drive
kubernetes-sigs /
agent-sandbox
Agent Sandbox: A Kubernetes CRD and controller for AI agent runtimes