agent-network-protocol/anp 354
567-labs/instructor 14.0k
Instructor: Pydantic-Validated JSON Extraction from LLM Responses
0xeb/TheBigPromptLibrary 5,484 +6 today
TheBigPromptLibrary: a verbatim archive of system prompts, and what its provenance rule actually enforces
ZhuLinsen/alphasift 376
AlphaSift: auditable YAML stock screening with an optional LLM opinion
ZhangHanDong/agent-spec 458
agent-spec freezes 23 requirement subcommands and five verdicts, and its overview stops mid-word twice
xeronsh/openOii 411
openOii turns a story idea into storyboards, then pins itself to one worker
WoJiSama/skill-based-architecture 620
A meta-skill that consolidates your agent rules and refuses to become a runtime
weibocom/rill-flow 410
Rill Flow starts as a Docker Compose stack, not a binary
vorojar/ai-native-hiring-guide 480 +14 today
The AI-native hiring guide is one HTML file with a five-minute role sort
VisionForge-OU/foreman 443
foreman supervises the claude CLI you already have
VILA-Lab/FigMirror 544
One agent draws, another argues, and the loop is bounded
UNLINEARITY/CLI-WeChat-Bridge 550 +1 today
cli-wechat-bridge: two lockfiles, fourteen binaries and two of them undocumented, and the only adapter without a verified version is the one that silently degrades
Undertone0809/promptulate 511
promptulate bets the whole API on one function, pne.chat
tongjingqi/AI-Can-Learn-Scientific-Taste 434
RLCF turns citation counts into a reward model for research ideas
teng-lin/weread-omni 679 +3 today
weread-omni renamed its command away from weread, then shipped a skill still called weread
Tencent/CognitiveKernel-Pro 533