InnerVault

Library

85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. Hugging Face dataset by argilla

    Stale Hugging Face Hub, argilla 170 ♥mitUpdated 2 years ago

    argilla/ultrafeedback-binarized-preferences-cleaned
  2. stack-exchange-preferences

    Datasets & benchmarks

    Hugging Face dataset by HuggingFaceH4

    Stale Hugging Face Hub, HuggingFaceH4 137 ♥cc-by-sa-4.0Updated 3 years ago

    HuggingFaceH4/stack-exchange-preferences
  3. preference-lab

    Agents & frameworks

    Policy-driven preference data for content moderation, with source-linked evidence, resumable runs, budget controls and TRL/ShareGPT exports.

    Stale GitHub, dengxianghua888-ops 50 ★Apache-2.0Updated 10 days ago

    git clone https://github.com/dengxianghua888-ops/preference-lab.git
  4. SHP

    Datasets & benchmarks

    Hugging Face dataset by stanfordnlp

    Indexed Hugging Face Hub, stanfordnlp 333 ♥Updated 3 years ago

    stanfordnlp/SHP
  5. arena-human-preference-55k

    Datasets & benchmarks

    Hugging Face dataset by lmarena-ai

    Stale Hugging Face Hub, lmarena-ai 164 ♥apache-2.0Updated 2 years ago

    lmarena-ai/arena-human-preference-55k
  6. alignment-handbook

    AI repositories

    Robust recipes to align language models with human and AI preferences

    Stale GitHub, huggingface 5,695 ★Apache-2.0Updated 54 days ago

    git clone https://github.com/huggingface/alignment-handbook.git
  7. orpo-dpo-mix-40k

    Datasets & benchmarks

    Hugging Face dataset by mlabonne

    Indexed Hugging Face Hub, mlabonne 318 ♥apache-2.0Updated 2 years ago

    mlabonne/orpo-dpo-mix-40k
  8. Preferly

    MCP servers

    Free AI visibility checks for any website: AI crawler access, llms.txt, schema, business info.

    Stale Official MCP Registry, ai.preferly Updated 2 days ago 1 note

  9. LoCo-7B

    Models

    text generation model by MuyaoYuan · transformers

    Stale Hugging Face Hub, MuyaoYuan 24 ♥mitUpdated 12 days ago

    MuyaoYuan/LoCo-7B
  10. RLAIF-V-Dataset

    Datasets & benchmarks

    Hugging Face dataset by openbmb

    Stale Hugging Face Hub, openbmb 223 ♥cc-by-nc-4.0Updated 13 months ago

    openbmb/RLAIF-V-Dataset
  11. AgileRL

    Agents & frameworks

    The complete post-training stack for LLMs, plus RL for any problem. SFT, DPO and multi-turn agentic RL, with evolutionary hyperparameter optimization built in.

    Indexed GitHub, AgileRL 968 ★Apache-2.0Updated today

    git clone https://github.com/AgileRL/AgileRL.git
  12. A self-learning system for Claude Code that captures corrections, positive feedback, and preferences — then syncs them to CLAUDE.md and AGENTS.md.

    Stale GitHub, BayramAnnakov 1,801 ★MITUpdated 44 days ago

    git clone https://github.com/BayramAnnakov/claude-reflect.git
  13. 10k_prompts_ranked

    Datasets & benchmarks

    Hugging Face dataset by data-is-better-together

    Stale Hugging Face Hub, data-is-better-together 173 ♥otherUpdated 2 years ago

    data-is-better-together/10k_prompts_ranked
  14. bullframe.css

    Skills

    A semantic, lightweight CSS (PostCSS) framework for fast, accessible UIs. Class-based or classless, light or dark, agent-skills ready. Seven builds. Any stack.

    Stale GitHub, marcop135 47 ★MITUpdated 10 days ago

    git clone https://github.com/marcop135/bullframe.css.git
  15. claude-smart

    Agents & frameworks

    Turns corrections into Preferences, Project-specific skills, and Shared skills for Claude Code, Codex, and OpenCode.

    Indexed GitHub, ReflexioAI 795 ★Apache-2.0Updated today

    git clone https://github.com/ReflexioAI/claude-smart.git
  16. NPR Listening Service

    Public APIs

    Audio recommendations tailored to a user's preferences

    Indexed APIs.guru OpenAPI Directory, NPR One Enterprise Team Updated 3 years ago

  17. Local user preferences with sourced corrections, scoped recall, and Codex/Cursor host adapters. / 本地保存带来源的偏好,支持更正、限定检索与 Codex/Cursor 适配。

    Stale GitHub, KarmenLoop 21 ★Apache-2.0Updated 23 days ago

    git clone https://github.com/KarmenLoop/user-behavior-personalization.git
  18. poppy

    MCP servers

    Developer memory CLI and MCP server. Remember decisions, preferences, and lessons locally.

    Stale Official MCP Registry, ai.trags Updated 21 days ago 1 note

    poppy-memory@0.3.6
  19. Cue

    MCP servers

    Notify people through Cue: preferences, attention budgets, quiet hours and approval apply.

    Stale Official MCP Registry, io.github.murtazox04 Updated 2 days ago 2 notes

    cue-notify@0.6.1
  20. WormaCeptor

    MCP servers

    Inspect a running Android debug app: network traffic, crashes, logs, databases and preferences

    Stale Official MCP Registry, com.wormaceptor Updated 4 days ago 1 note

    wormaceptor-mcp@3.5.0
  21. memxus

    MCP servers

    Persistent memory layer that saves and recalls your project context and preferences.

    Stale Official MCP Registry, com.memxus Updated 3 months ago 1 note

  22. Agent Push Kit

    MCP servers

    Send, search, and manage notifications, accounts, and push preferences

    Stale Official MCP Registry, io.github.JustinBStrong Updated 3 months ago 3 notes

    agent-push-kit-mcp@0.1.1
  23. Behavioral science tools for commerce — personas, nudges, preferences, friction audits.

    Stale Official MCP Registry, io.phoslabs Updated 41 days ago 2 notes

  24. youtube-media

    MCP servers

    Search YouTube, read video metadata, and fetch transcripts with language preferences

    Stale Official MCP Registry, net.nexlab Updated 2 months ago 1 note

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.