Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Nubase
AI repositories🔥🔥🔥 Turn AI-written code into real apps. Nubase is an open-source, AI-native backend platform for AI Coding, agentic applications, and modern product teams: Memory, Database, Storage, and Auth in one self-hostable service.
git clone https://github.com/OtterMind/Nubase.git -
openclip
AI repositoriesAn open-source, macOS text action popup for running custom scripts, AI actions, and extensible workflows on selected text.
git clone https://github.com/ganeshmshetty/openclip.git -
Hermes-3-Dataset
Datasets & benchmarksHugging Face dataset by NousResearch
NousResearch/Hermes-3-Dataset -
mmlu
Datasets & benchmarksHugging Face dataset by cais
cais/mmlu -
portal-tunnel
SkillsPublishes localhost services to the agentic web through self-hostable, trustless relays.
git clone https://github.com/gosuda/portal-tunnel.git -
3d-collection
Datasets & benchmarksHugging Face dataset by scenario-labs
scenario-labs/3d-collection -
ppt-agent-skills
Agents & frameworksA code-driven presentation generation framework. 像构建软件工程一样生成演示文稿。
git clone https://github.com/sunbigfly/ppt-agent-skills.git -
open-computer-use
AI repositoriesAI computer use powered by open source LLMs and E2B Desktop Sandbox
git clone https://github.com/e2b-dev/open-computer-use.git -
tiktok-5.6B-videos
Datasets & benchmarksHugging Face dataset by datasocial
datasocial/tiktok-5.6B-videos -
AgileRL
Agents & frameworksThe complete post-training stack for LLMs, plus RL for any problem. SFT, DPO and multi-turn agentic RL, with evolutionary hyperparameter optimization built in.
git clone https://github.com/AgileRL/AgileRL.git -
squad
Datasets & benchmarksHugging Face dataset by rajpurkar
rajpurkar/squad -
research-plan-gen
Datasets & benchmarksHugging Face dataset by facebook
facebook/research-plan-gen -
docetl
AI repositoriesA system for agentic LLM-powered data processing and ETL
git clone https://github.com/ucbepic/docetl.git -
fauxnix
MCP serversRun Linux-style commands on Windows via deterministic bash→PowerShell translation. No VM, no WSL. MCP server + CLI built for AI agents (Claude Code, Codex, OpenCode...). GNU-style output, bash-style errors, UTF-8/GBK handled.
git clone https://github.com/20000419/fauxnix.git -
WildChat-1M
Datasets & benchmarksHugging Face dataset by allenai
allenai/WildChat-1M -
OpenMathReasoning
Datasets & benchmarksHugging Face dataset by nvidia
nvidia/OpenMathReasoning -
llama-gpt
AI repositoriesA self-hosted, offline, ChatGPT-like chatbot. Powered by Llama 2. 100% private, with no data leaving your device. New: Code Llama support!
git clone https://github.com/getumbrel/llama-gpt.git -
Opus-4.6-Reasoning-3300x
Datasets & benchmarksHugging Face dataset by Crownelius
Crownelius/Opus-4.6-Reasoning-3300x -
open-web-math
Datasets & benchmarksHugging Face dataset by open-web-math
open-web-math/open-web-math -
FineTome-100k
Datasets & benchmarksHugging Face dataset by mlabonne
mlabonne/FineTome-100k -
Stable-Diffusion-Prompts
Datasets & benchmarksHugging Face dataset by Gustavosta
Gustavosta/Stable-Diffusion-Prompts -
reasoning-0.01
Datasets & benchmarksHugging Face dataset by SkunkworksAI
SkunkworksAI/reasoning-0.01 -
quark_drive_skills
SkillsQuark Drive Skills: Pokemon Champions Agent Skills for dex and metagame facts, exact battle calculations, and audited team building. Companion interface: Quark Drive Web.
git clone https://github.com/pmwl0128/quark_drive_skills.git -
Bespoke-Stratos-17k
Datasets & benchmarksHugging Face dataset by bespokelabs
bespokelabs/Bespoke-Stratos-17k
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.