InnerVault

Library

85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

5,497 results Clear search and filters
  1. derive

    MCP servers

    Review and approval for work made by AI agents. Fair Source, self-hostable, and MCP-native.

    Indexed GitHub, derive-to 33 ★Custom licence (see repository)Updated 2 days ago

    git clone https://github.com/derive-to/derive.git
  2. AI agent skills for YouTube research. Outlier videos, niche finding & validation, competitor research, comment mining, title formulas, thumbnail concepts, script breakdowns, monetization gaps & sponsor prospecting. Powered by TubeLab. Works with Claude Code, Cursor, Codex, ChatGPT, Grok.

    Indexed GitHub, TubeLabHQ 99 ★MITUpdated 2 days ago

    git clone https://github.com/TubeLabHQ/youtube-research-skills.git
  3. kiki

    Agents & frameworks

    Open-source multi-model AI agent workbench (Desktop GUI, TUI & Web) — dispatch subagents across Claude, GPT, Gemini & Kimi, bridge WeChat/QQ, and run locally.

    Indexed GitHub, X-T-E-R 56 ★MITUpdated yesterday

    git clone https://github.com/X-T-E-R/kiki.git
  4. inno-agent

    Agents & frameworks

    An open-source personal learning agent with three-layer memory (learner profile / wiki knowledge base / cross-conversation recall), a proactive scheduler, personal IM channels, and a workspace-scoped Practice Lab — built on the Pi SDK.

    Indexed GitHub, hhyqhh 1,471 ★MITUpdated 6 days ago

    git clone https://github.com/hhyqhh/inno-agent.git
  5. 20 self-contained HTML presentation templates · 226 slides · one reusable AI skill by Lanshu.

    Stale GitHub, cclank 56 ★Custom licence (see repository)Updated 9 days ago

    git clone https://github.com/cclank/lanshu-html-ppt-templates.git
  6. Sanity

    MCP servers

    Gives AI agents direct access to your Sanity projects and guidance for working with them

    Stale Official MCP Registry, io.sanity.www 194 ★Updated 4 days ago 1 note

  7. intelligent-audit-system

    Agents & frameworks

    AuditPilot: auditable enterprise AI agents for evidence-grounded workflows, governed tools, evaluation harnesses, human review, and remediation delivery.

    Stale GitHub, Ricky-7-Yan 1,180 ★MITUpdated 12 days ago

    git clone https://github.com/Ricky-7-Yan/intelligent-audit-system.git
  8. project-cairn

    Agents & frameworks

    Turn project work into reusable knowledge — an AI-agent skill for Claude Code & Codex

    Indexed GitHub, iBlinkQ 252 ★MITUpdated 7 days ago

    git clone https://github.com/iBlinkQ/project-cairn.git
  9. nirvana-os-engine

    Agents & frameworks

    Nirvana-OS engine: ready-to-run agentic operations. One sentence in, finished work out. Source-available engine for companies, squads and mind-clones. Runtime-agnostic: Claude Code, Codex, Gemini-CLI, Antigravity, Hermes.

    Indexed GitHub, gutomec 84 ★Custom licence (see repository)Updated 4 days ago

    git clone https://github.com/gutomec/nirvana-os-engine.git
  10. Skills related to Data Engineering Work for Claude Code

    Stale GitHub, AltimateAI 130 ★MITUpdated 22 days ago

    git clone https://github.com/AltimateAI/data-engineering-skills.git
  11. bagidea-office

    Agents & frameworks

    A living AI-agent office on your desktop wallpaper — Claude Code agents that walk, work, delegate, learn & hold meetings. Per-agent swappable models (Claude/GLM/DeepSeek/Qwen/Kimi/OpenAI/Gemini/Groq/Ollama…), workflows, plugins, voice & Telegram/Discord/LINE. Open source.

    Stale GitHub, bagidea 260 ★MITUpdated 17 days ago

    git clone https://github.com/bagidea/bagidea-office.git
  12. catgo-LRG

    Agents & frameworks

    AI-driven workbench for computational materials science — interactive 3D structure viewer, natural-language CatBot assistant, visual DAG workflow engine, HPC job submission. Tauri desktop app with SvelteKit frontend and FastAPI Python backend. Drives VASP, ORCA, CP2K, QE, GPAW, DFTB+, SIESTA, LAMMPS.

    Stale GitHub, Hello-QM 208 ★AGPL-3.0Updated 26 days ago

    git clone https://github.com/Hello-QM/catgo-LRG.git
  13. c9watch

    Agents & frameworks

    Mac app and JSON CLI to monitor every Claude Code, Codex, Cursor Agent and Pi session on your machine. See which agent needs permission, which is working, and which is idle. Works with any terminal or IDE. Free, open source (MIT).

    Stale GitHub, minchenlee 136 ★MITUpdated 11 days ago

    git clone https://github.com/minchenlee/c9watch.git
  14. Agent skill for Verilog-2001 RTL generation and FPGA design workflows.

    Stale GitHub, Eriemon 316 ★Apache-2.0Updated 2 months ago

    git clone https://github.com/Eriemon/verilog-generator.git
  15. chief

    Tools & apps

    Build big projects with Claude. Chief breaks your work into tasks and runs Claude Code in a loop until they're done.

    Stale GitHub, MiniCodeMonkey 473 ★MITUpdated 50 days ago

    git clone https://github.com/MiniCodeMonkey/chief.git
  16. AI-Skills

    Prompts

    A portable library of reusable AI skills, prompts, workflows, schemas, and automation patterns designed for ChatGPT, Claude, Copilot, and local LLM workflows.

    Stale GitHub, mickpletcher 20 ★MITUpdated 13 days ago

    git clone https://github.com/mickpletcher/AI-Skills.git
  17. ginno

    Skills

    Local-first personal AI agent desktop app — Claude Code's shape with a visual workflow studio, local knowledge base, and zero cloud. Tauri + Next.js + Python.

    Indexed GitHub, robscc 15 ★MITUpdated yesterday

    git clone https://github.com/robscc/ginno.git
  18. altk-evolve

    MCP servers

    Self improving agents through iterations

    Stale GitHub, AgentToolkit 134 ★Apache-2.0Updated 21 days ago

    git clone https://github.com/AgentToolkit/altk-evolve.git
  19. build-an-agentic-llm-assistant

    Agents & frameworks

    Labs for the "Build an agentic LLM assistant on AWS" workshop. A step by step agentic llm assistant development workshop using serverless three-tier architecture.

    Stale GitHub, aws-samples 80 ★MIT-0Updated 13 months ago

    git clone https://github.com/aws-samples/build-an-agentic-llm-assistant.git
  20. modsearch

    Skills

    🥇 The strongest free web search plugin for DeepSeek Harness, and the search bridge for every model without native web access. Free, no signup, no API key. Ask the web or X, get structured JSON evidence. | 🥇 全网最强的 DeepSeek Harness 免费联网搜索插件,免费免注册免 API key。为不能联网的模型补上搜索,问网页或 X,拿回结构化 JSON 证据(搜索、抓取、引用)。

    Indexed GitHub, liustack 990 ★MITUpdated 2 days ago

    git clone https://github.com/liustack/modsearch.git
  21. 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 23 days ago

    git clone https://github.com/UditAkhourii/adhd.git
  22. actonos

    Agents & frameworks

    ActonOS is a single-purpose appliance operating system engineered as a customizable, self-governing AI agent kernel running 24/7.

    Stale GitHub, actonos 77 ★Apache-2.0Updated 16 days ago

    git clone https://github.com/actonos/actonos.git
  23. Stop That Shit(别再造史了)|面向 Codex/GPT 场景的多平台 Hook + Skill Guard:拦截 AI coding agent 无需求的哈希、校验和与任务范围膨胀。 A multi-platform Hook + Skill Guard for AI coding agents in Codex/GPT workflows: stop unrequested hashes, checksums, and task-scope creep.

    Stale GitHub, lennney 3,636 ★MITUpdated 12 days ago

    git clone https://github.com/lennney/stop-that-shit.git
  24. dsh-industry-research

    Tools & apps

    Industry and company research domain pack for DeepSeek Harness: methodology skills, industry chain mapping, public-source policy/news tracking, company research cards, and auditable research reports. Research only - not investment advice.

    Indexed GitHub, PerryLink 219 ★Apache-2.0Updated 4 days ago

    git clone https://github.com/PerryLink/dsh-industry-research.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.