Library
87,151 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
ruby_llm
Agents & frameworksThe Ruby AI framework.
git clone https://github.com/crmne/ruby_llm.git -
m_flow
AI repositoriesA bio-inspired cognitive memory engine — a new paradigm for Graph RAG.
git clone https://github.com/FlowElement-xinliuyuansu/m_flow.git -
image text to text model by google
google/gemma-3n-E4B-it-litert-preview -
bert-base-chinese
Modelsfill mask model by google-bert · transformers
google-bert/bert-base-chinese -
nono
Agents & frameworksagent runtime security - zero trust, zero setup, zero latency agent sandbox
git clone https://github.com/nolabs-ai/nono.git -
VLMEvalKit
AI repositoriesOpen-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks
git clone https://github.com/open-compass/VLMEvalKit.git -
oracle-ai-developer-hub
AI repositoriesTechnical resources for AI developers to build applications, agents, and systems using Oracle AI Database and OCI services
git clone https://github.com/oracle-devrel/oracle-ai-developer-hub.git -
gptme
Agents & frameworksYour agent in your terminal, equipped with local tools: writes code, uses the terminal, browses the web. Make your own persistent autonomous agent on top!
git clone https://github.com/gptme/gptme.git -
ragent
AI repositories企业级 Agentic RAG 智能体 - 全链路覆盖文档解析、多路检索、意图识别、问题重写、会话记忆、MCP 工具调用与深度思考。面向真实业务场景,从 0 到 1 完整工程实现。
git clone https://github.com/nageoffer/ragent.git -
LMOps
AI repositoriesGeneral technology for enabling AI capabilities w/ LLMs and MLLMs
git clone https://github.com/microsoft/LMOps.git -
pstack-claude
SkillsAntigravity, Claude Code, Codex, Copilot, Gemini, Muse, OpenCode, Pi, and Prime Agent versions of Poteto's pstack. Rigorous agent workflows with Cursor primitives translated for other harnesses.
git clone https://github.com/michael-denyer/pstack-claude.git -
adhd
PromptsADHD — a skill for coding agents. Tree-of-thought with pruning, built on the Claude & Codex Agent SDK. Fans out parallel divergent thoughts under different cognitive frames, scores, prunes traps, deepens the survivors. The no-brainer skill for creative and interdisciplinary work.
git clone https://github.com/UditAkhourii/adhd.git -
judge0
Agents & frameworksRobust, fast, scalable, and sandboxed open-source online code execution system for humans and AI.
git clone https://github.com/judge0/judge0.git -
ChatGPT-On-CS
AI repositories拼多多、千牛、抖店 AI 客服机器人:自动回复客户咨询、商品答疑、售后申诉处理,支持微信、小红书、京东、抖音、B站、微博等多平台统一接待;可接入 DeepSeek / 通义千问 等大模型,支持自有知识库定制。
git clone https://github.com/cs-lazy-tools/ChatGPT-On-CS.git -
Phi-3-mini-4k-instruct
Modelstext generation model by microsoft · transformers
microsoft/Phi-3-mini-4k-instruct -
pstack
SkillsUse pstack with claude, codex, pi - Skills and principles for rigorous AI-assisted engineering
git clone https://github.com/backnotprop/pstack.git -
ChatGPT4
Tools & appsHugging Face space by ysharma
ysharma/ChatGPT4 -
distilbert-base-uncased
Modelsfill mask model by distilbert · transformers
distilbert/distilbert-base-uncased -
llm-foundry
AI repositoriesLLM training code for Databricks foundation models
git clone https://github.com/mosaicml/llm-foundry.git -
MiniMax-H3-Image
Modelstext to image model by MiniMaxAI · minimax-h3
MiniMaxAI/MiniMax-H3-Image -
memory-lancedb-pro
AI repositoriesEnhanced LanceDB memory plugin for OpenClaw — Hybrid Retrieval (Vector + BM25), Cross-Encoder Rerank, Multi-Scope Isolation, Management CLI
git clone https://github.com/CortexReach/memory-lancedb-pro.git -
claude-octopus
Agents & frameworksRun multiple AI models against the same research, design, or coding task. Surface disagreements before you ship.
git clone https://github.com/nyldn/claude-octopus.git -
archestra
MCP serversEnterprise AI Platform with guardrails, MCP registry, gateway & orchestrator
git clone https://github.com/archestra-ai/archestra.git -
ragapp
AI repositoriesThe easiest way to use Agentic RAG in any enterprise
git clone https://github.com/ragapp/ragapp.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.