Library
87,606 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
workflow
Tools & appsCore package for defining and running durable workflows and activities. Supports long-running persistent workflows, retries, queues, parallel execution, workflow monitoring, dedicated storage connections, and orchestration for microservices, data pipelines, sagas, agentic workflows, and other complex business processes.
git clone https://github.com/durable-workflow/workflow.git -
SpecForge
AI repositoriesTrain speculative decoding models effortlessly and port them smoothly to SGLang serving.
git clone https://github.com/sgl-project/SpecForge.git -
prompty
AI repositoriesPrompty makes it easy to create, manage, debug, and evaluate LLM prompts for your AI applications. Prompty is an asset class and format for LLM prompts designed to enhance observability, understandability, and portability for developers.
git clone https://github.com/microsoft/prompty.git -
search2ai
MCP serversSelf-hosted search gateway for AI agents. Unified search, news and page extraction with provider fallback. REST API, MCP server and TypeScript library.
git clone https://github.com/fatwang2/search2ai.git -
Reticle
MCP serversVerify a running web app from the inside over MCP: look, act, observe, assert. No screenshots.
@reticlehq/server@3.10.7 -
text classification model by j-hartmann · transformers
j-hartmann/emotion-english-distilroberta-base -
Qwen2.5-VL-32B-Instruct
Modelsimage text to text model by Qwen · transformers
Qwen/Qwen2.5-VL-32B-Instruct -
Seed-OSS-36B-Instruct
Modelstext generation model by ByteDance-Seed · transformers
ByteDance-Seed/Seed-OSS-36B-Instruct -
Qwen3-VL-4B-Instruct
Modelsimage text to text model by Qwen · transformers
Qwen/Qwen3-VL-4B-Instruct -
Qwen3.5-27B-GGUF
Modelsimage text to text model by unsloth
unsloth/Qwen3.5-27B-GGUF -
Minimax_h3_latent_Upscaler
Modelsmodel by LBH-123-AI · minimax-h3
LBH-123-AI/Minimax_h3_latent_Upscaler -
OpenMathReasoning
Datasets & benchmarksHugging Face dataset by nvidia
nvidia/OpenMathReasoning -
kg-gen
Datasets & benchmarks[NeurIPS '25] Knowledge Graph Generation from Any Text
git clone https://github.com/stair-lab/kg-gen.git -
open-steps
SkillsPlain-language agent skills for Claude Code, Codex, Cursor and Gemini CLI: honest session reports, straight verdicts, steps you can follow. MIT.
git clone https://github.com/kharmanskyi/open-steps.git -
ongrid
Agents & frameworksAn ops AI Agent that understands your infrastructure, finds the root cause, and fixes it — right from Slack, Telegram, Lark or DingTalk.
git clone https://github.com/ongridio/ongrid.git -
gpt-neo-2.7B
Modelstext generation model by EleutherAI · transformers
EleutherAI/gpt-neo-2.7B -
text to video model by ali-vilab · open_clip
ali-vilab/modelscope-damo-text-to-video-synthesis -
zeroscope_v2_XL
Modelsvideo to video model by cerspense · diffusers
cerspense/zeroscope_v2_XL -
Qwen3-14B
Modelstext generation model by Qwen · transformers
Qwen/Qwen3-14B -
COG-second-brain
SkillsSelf-evolving second brain with 35 AI skills, 10 agents, and people CRM. Closed-loop harness: a V-model verification lifecycle where the worker never grades its own homework. Plus paired anti-slop design skills for marketing and product UI. Works with Claude Code, Cursor, Kiro, Gemini CLI, Codex.
git clone https://github.com/huytieu/COG-second-brain.git -
promptmap
Promptsa security scanner for custom LLM applications
git clone https://github.com/utkusen/promptmap.git -
ideogram-4-nf4
Modelstext to image model by ideogram-ai · diffusers
ideogram-ai/ideogram-4-nf4 -
golive-skill
SkillsTake your agent-built product live: hosting, database, domain, email, payments — on your own accounts. Open-source Agent Skill + zero-dependency Node CLI: detect → plan → approve → apply → verify. No GoLive account, backend or telemetry.
git clone https://github.com/mikehasa/golive-skill.git -
TrustRAG
AI repositoriesTrustRAG:The RAG Framework within Reliable input,Trusted output
git clone https://github.com/gomate-community/TrustRAG.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.