InnerVault

Library

85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.

Results

Looks like a goal we have a starting path for: I want to build an AI agent

  1. Nói với AI bằng tiếng Việt → tìm chủ đề hot, soi đối thủ, viết bài, dựng video 9:16 với 130 template (có video kể chuyện, giọng đọc tiếng Việt), duyệt rồi mới đăng; kèm bộ công cụ chạy quảng cáo Facebook cho shop. Cài làm skill cho Claude Code hoặc dùng với Antigravity. Phần lớn miễn phí, MIT.

    Stale GitHub, XuHo-IT 6 ★MITUpdated 4 days ago

    git clone https://github.com/XuHo-IT/Content-Agent-Kit.git
  2. Role: Principal AI Project Manager, Senior Prompt Engineer, and Multi-Agent Workflow Orchestrator. Context: Continue the existing project. Inspect and follow all current project rules, architecture decisions…

    Indexed prompts.chat (CC0 prompt collection), mhe931 CC0-1.0

  3. Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...

    Indexed OpenRouter model list, tencent Updated 6 months ago

    tencent/hy3-preview
  4. Mercury 3 is a diffusion-based language model from Inception, and the lab's most capable model to date. It is suited for agentic workflows and real-time applications where latency compounds, such...

    No longer listed OpenRouter model list, inception Updated 31 days ago

    inception/mercury-3
  5. skills

    Skills

    Claude Code plugin marketplace — 77 installable reference skills across vLLM/SGLang inference, Kubernetes & Harvester, GPU host bring-up, observability, security, and agent workflows.

    Stale GitHub, air-gapped 6 ★MITUpdated 6 days ago

    git clone https://github.com/air-gapped/skills.git
  6. Command A+ is Cohere's flagship model for enterprise agentic workflows. It accepts text and image inputs with a 192K context window, supports native tool calling with strict tool schemas, structured...

    Indexed OpenRouter model list, cohere Updated 55 days ago

    cohere/command-a-plus
  7. Tencent: Hy3

    Models

    Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...

    Indexed OpenRouter model list, tencent Updated 4 months ago

    tencent/hy3
  8. Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks. This is a preview of the...

    Indexed OpenRouter model list, unbiased Updated 46 days ago

    unbiased/pareto-26.10-preview
  9. Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic workflows, with strong capabilities in office productivity, document-intensive...

    Indexed OpenRouter model list, upstage Updated 3 months ago

    upstage/solar-pro4
  10. MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning,...

    No longer listed OpenRouter model list, minimax Updated 12 months ago

    minimax/minimax-m2
  11. briefback

    Skills

    A coding-agent workflow with Grill at its core: challenge assumptions and settle decisions before coding. Just describe your task and AgentFlow automatically guides the work from research to reviewable code. Lightweight spec-driven development with planning, TDD, review and handoff for Claude Code, Codex and Cursor.

    Stale GitHub, reforma-ai 10 ★MITUpdated 5 days ago

    git clone https://github.com/reforma-ai/briefback.git
  12. 241 evaluated academic Claude/agent skills across 18 research domains — bioinformatics, cheminformatics, data science, databases, clinical, social science, Turkish academia & more. Every skill ships an executable eval. Citation verifier, research→write→review pipeline, 7 multi-agent workflows. Claude Code plugins; also Cursor, Codex, Gemini CLI.

    Indexed GitHub, AlterLab-IEU 87 ★MITUpdated 5 days ago

    git clone https://github.com/AlterLab-IEU/AlterLab-Academic-Skills.git
  13. DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....

    Indexed OpenRouter model list, deepseek Updated 3 months ago

    deepseek/deepseek-v4-flash-0731
  14. LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...

    No longer listed OpenRouter model list, liquid Updated 3 months ago

    liquid/lfm-2.5-2.6b
  15. Granite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows that need multi-step reasoning. It supports full, low-effort,...

    Indexed OpenRouter model list, ibm-granite Updated 2 months ago

    ibm-granite/granite-4.2-8b
  16. LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...

    No longer listed OpenRouter model list, liquid Updated 3 months ago

    liquid/lfm-2.5-2.6b:free
  17. MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world...

    No longer listed OpenRouter model list, minimax Updated 10 months ago

    minimax/minimax-m2.1
  18. DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....

    Indexed OpenRouter model list, deepseek Updated 3 months ago

    deepseek/deepseek-v4-flash-0731:batch
  19. Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis.

    Indexed OpenRouter model list, qwen Updated 2 months ago

    qwen/qwen3.8-flash
  20. Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...

    Indexed OpenRouter model list, moonshotai Updated 4 months ago

    moonshotai/kimi-k3
  21. GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows...

    Indexed OpenRouter model list, z-ai Updated 8 months ago

    z-ai/glm-5-turbo
  22. Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...

    Indexed OpenRouter model list, moonshotai Updated 4 months ago

    moonshotai/kimi-k3:batch
  23. Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...

    Indexed OpenRouter model list, mistralai Updated 6 months ago

    mistralai/mistral-medium-3-5
  24. Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B total and 23B active parameters per token, and a...

    Indexed OpenRouter model list, reflection Updated 31 days ago

    reflection/beam-1.0-501b-a23b

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.