InnerVault

Library

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

Results

  1. HallusionBench

    Datasets & benchmarks

    [CVPR'24] HallusionBench: You See What You Think? Or You Think What You See? An Image-Context Reasoning Benchmark Challenging for GPT-4V(ision), LLaVA-1.5, and Other Multi-modality Models

    Stale GitHub, tianyi-lab 344 ★BSD-3-ClauseUpdated 13 months ago

    git clone https://github.com/tianyi-lab/HallusionBench.git
  2. obsidian-copilot

    AI repositories

    🤖 A prototype assistant for writing and thinking

    Stale GitHub, eugeneyan 561 ★Apache-2.0Updated 2 years ago

    git clone https://github.com/eugeneyan/obsidian-copilot.git
  3. image text to text model by huihui-ai · transformers

    Indexed Hugging Face Hub, huihui-ai 260 ♥otherUpdated 7 days ago

    huihui-ai/Huihui-Qwen3.8-Flash-Next-abliterated-v2-GGUF
  4. workflows for compound thinking with AI

    Stale GitHub, lsnackerman 44 ★Custom licence (see repository)Updated 22 days ago

    git clone https://github.com/lsnackerman/raw-clauding-skills.git
  5. nuwa-skill

    Skills

    你想蒸馏的下一个员工,何必是同事。蒸馏任何人的思维方式——心智模型、决策启发式、表达DNA。Distill how anyone thinks.

    Indexed GitHub, alchaincyf 38.4k ★MITUpdated yesterday

    git clone https://github.com/alchaincyf/nuwa-skill.git
  6. UltraData-SFT-2605

    Datasets & benchmarks

    Hugging Face dataset by openbmb

    Indexed Hugging Face Hub, openbmb 419 ♥apache-2.0Updated 5 months ago 1 note

    openbmb/UltraData-SFT-2605
  7. 669 work prompts, prompt and answer checks, a job planner, a prompt linter and AI prices.

    Stale Official MCP Registry, si.thinkhard Updated 12 days ago 1 note

  8. thinkrun

    MCP servers

    Browser control + session recording MCP for AI coding agents (Claude Code, Cursor) — real Chrome.

    Stale Official MCP Registry, io.github.dundas Updated 13 days ago 1 note

    @thinkrun/mcp@0.3.14
  9. model by peculiar-ragdoll · mlx

    Stale Hugging Face Hub, peculiar-ragdoll 22 ♥otherUpdated 33 days ago

    peculiar-ragdoll/Sharp-LFM2.5-Chat-Templates
  10. Learning-Prompt

    Prompts

    Free prompt engineering online course. ChatGPT and Midjourney tutorials are now included!

    Stale GitHub, thinkingjimmy 5,299 ★Custom licence (see repository)Updated 3 years ago

    git clone https://github.com/thinkingjimmy/Learning-Prompt.git
  11. THX-02

    Models

    zero shot classification model by HAL-X-AI · thx02

    Indexed Hugging Face Hub, HAL-X-AI 71 ♥apache-2.0Updated 3 days ago

    HAL-X-AI/THX-02
  12. text generation model by DavidAU

    Stale Hugging Face Hub, DavidAU 434 ♥mitUpdated 5 months ago

    DavidAU/GLM-4.7-Flash-Uncensored-Heretic-NEO-CODE-Imatrix-MAX-GGUF
  13. image text to text model by huihui-ai · transformers

    Stale Hugging Face Hub, huihui-ai 179 ♥otherUpdated 36 days ago

    huihui-ai/Huihui-Qwen3.8-Flash-Next-abliterated-GGUF
  14. Reviewed decision matrices and buying guides: ranked options and weighted criteria in 6 languages

    Stale Official MCP Registry, com.octothinks Updated 26 days ago 1 note

  15. Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels...

    No longer listed OpenRouter model list, qwen Updated 13 months ago

    qwen/qwen3-vl-30b-a3b-thinking
  16. agent-flow

    Agents & frameworks

    Real-time visualization of Claude Code agent orchestration — see your agents think, branch, and coordinate as they work.

    Stale GitHub, patoles 1,702 ★Apache-2.0Updated 37 days ago

    git clone https://github.com/patoles/agent-flow.git
  17. skills

    Skills

    Skills to augment LLM thinking process, integrated with InfraNodus insight generation tool

    Indexed GitHub, infranodus 127 ★Custom licence (see repository)Updated 4 days ago

    git clone https://github.com/infranodus/skills.git
  18. Pay-per-call x402 tools for agents: invoice, quote, vendor and claim checks, research, mindset.

    Stale Official MCP Registry, io.github.Tgwedwin Updated 3 days ago 1 note

  19. Act as a comprehensive decision-making system for deep thinking and development. ## System Structure - **Opus**: You are the central decision-maker, orchestrating all processes and ensuring alignment with strategic…

    Indexed prompts.chat (CC0 prompt collection), yigitgurler CC0-1.0

  20. adhd

    Prompts

    ADHD — 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.

    Stale GitHub, UditAkhourii 4,477 ★MITUpdated 22 days ago

    git clone https://github.com/UditAkhourii/adhd.git
  21. ROLE: OMEGA-LEVEL SYSTEM "DEEPTHINKER-CA" & METACOGNITIVE ANALYST # CORE IDENTITY You are "DeepThinker-CA" - a highly advanced cognitive engine designed for **Deep Recursive Thinking**. You do not provide surface-level…

    Indexed prompts.chat (CC0 prompt collection), mathanhcong1992@gmail.com CC0-1.0

  22. thinking.town

    MCP servers

    A public message board built for AI agents. Read threads, reply, or start one; poll for new posts.

    Stale Official MCP Registry, io.github.Tsadoq Updated 39 days ago 1 note

  23. **Adaptive Thinking Framework (Integrated Version)** This framework has the user’s “Standard—Borrow Wisdom—Review” three-tier quality control method embedded within it and must not be executed by skipping any steps…

    Indexed prompts.chat (CC0 prompt collection), arimerzhu1@gmail.com CC0-1.0

  24. Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...

    Indexed OpenRouter model list, moonshotai Updated 12 months ago

    moonshotai/kimi-k2-thinking

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.