imxinchengyou /
CacheVerifier
I tested whether verifying LLM cache hits in real time helps (weak yes)
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
robbyant /
lingbot-video
LingBot-Video: An open-source MoE video foundation model for embodied AI
Show HN
h0ngcha0 /
hubo
Hubo – two agents that implement and review code until they agree
Show HN
jezmn /
hanesu
Hanesu – An experimental workflow layer for AI coding agents
Show HN
thiagoperes /
storeshot
Storeshot - Apple/Google Play store screenshots built for agents
Show HN
ibreakthecloud /
kiwi
Kiwi – Run agentic dev loops in the cloud, keep keys on your laptop
gakonst /
nanocodex
Nanocodex: Headless Rust Agents SDK
Show HN
NeoZi12 /
dispatchseo
DispatchSEO – open-source SEO manager tool for Claude Code
jadeavsmith-tech /
holographic-horizon-shield-v2
V2 of Holographic Horizon Shield: LLM Defenses with Phi-3 Integration
Show HN
Cocabadger /
tick-mcp
I gave an LLM a clock and it usually won't look at it
brendenehlers /
diplomacy-ai
I made AI agents play diplomacy
humanlayer /
12-factor-agents
12 Factor Agents
Show HN
robolamp /
smol-llm-proxy
A minimalist proxy for your local LLM cluster (~1100 lines)
eouzoe /
reel
A protocol for AI agent workspace state and effect management
synthetic-sciences /
openscience
OpenScience: Workbench for scientific research using custom LLMs
Show HN
alagiz /
cc-context-telemetry
cc-context-telemetry - context and rate-limit % in Claude Code's bar
Show HN
cruxible-ai /
cruxible
Cruxible – Open-source governed truth layer for AI agents
alavicka /
pollux
Pollux – a natively vector quantized LLM with 0.76 bits per parameter