InnerVault

Library

86,219 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

10,536 results Clear search and filters

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

  1. captain-claw

    Agents & frameworks

    Command a fleet of AI agents, on every deck, every desk, every wrist. Self-hosted multi-agent platform with memory, a coding pipeline, Flows, a team kiosk and voice devices. Any LLM, or 100% local with Ollama.

    Indexed GitHub, kstevica 197 ★MITUpdated today

    git clone https://github.com/kstevica/captain-claw.git
  2. diorama

    Skills

    Playbook and Three.js code kit for detailed dioramas: classic pixel art, stroked toon or pixel + stroke; two intake gates for look and model sourcing; free orbit, palette snap and ink; animated toy-scale cast; per-entity frame QA.

    Indexed GitHub, sloemo01 555 ★MITUpdated yesterday

    git clone https://github.com/sloemo01/diorama.git
  3. PRD-Led Context Engineering — Memory as Infrastructure. An ontology layer for product teams building products that solve real problems — with AI agents that remember. Gated PRD, typed IDs, markdown knowledge graph, Claude Code skills & hooks.

    Stale GitHub, mattgierhart 181 ★MITUpdated 2 months ago

    git clone https://github.com/mattgierhart/PRD-driven-context-engineering.git
  4. OpenImageDebugger MCP

    MCP servers

    MCP server giving AI agents eyes on OpenImageDebugger buffers in live gdb/lldb sessions

    Stale Official MCP Registry, io.github.OpenImageDebugger 250 ★Updated 22 days ago 1 note

    oid-mcp@0.3.6
  5. cross-review

    Agents & frameworks

    Cross-model review skills for Claude Code and Codex CLI: one agent orchestrates, another model reviews plans, code and reasoning.

    Stale GitHub, lploc94 167 ★MITUpdated 6 days ago

    git clone https://github.com/lploc94/cross-review.git
  6. Awesome-Prompt-Engineering - This repository includes resources for prompt engineering. 🌟 Star if you like it!

    Stale GitHub, natnew 114 ★MITUpdated 26 days ago

    git clone https://github.com/natnew/Awesome-Prompt-Engineering.git
  7. lumina

    Skills

    A full featured, powerful, and efficient AI Agentic Harness/Desktop Agent app designed from the ground up with local inference on consumer hardware in mind. It evolves, grows, and gets smarter as you go. And it REMEMBERS...

    Indexed GitHub, Bino5150 195 ★Apache-2.0Updated today

    git clone https://github.com/Bino5150/lumina.git
  8. cortex-hub

    Agents & frameworks

    Self-hosted AI Agent Memory + Code Intelligence Platform — one MCP endpoint for persistent memory, AST-aware code search, shared knowledge, and quality enforcement across all your AI coding agents.

    Stale GitHub, lktiep 105 ★MITUpdated 18 days ago

    git clone https://github.com/lktiep/cortex-hub.git
  9. Misaka-Agent

    Agents & frameworks

    A multi-agent research system for the humanities and social sciences.

    Indexed GitHub, Luciole-Studio 256 ★Apache-2.0Updated 6 days ago

    git clone https://github.com/Luciole-Studio/Misaka-Agent.git
  10. memtrace-public

    MCP servers

    Structural memory for AI coding agents. Bi-temporal graph, MCP-native, zero LLM calls. Cursor · Claude Code · Codex · DeepSeek Harness · Hermes · VS Code · Windsurf.

    Stale GitHub, syncable-dev 510 ★Custom licence (see repository)Updated 13 days ago

    git clone https://github.com/syncable-dev/memtrace-public.git
  11. awesome-agent-memory

    MCP servers

    A curated list of memory systems, frameworks, benchmarks, and research for AI agents.

    Stale GitHub, mnemoverse 66 ★CC0-1.0Updated 7 days ago

    git clone https://github.com/mnemoverse/awesome-agent-memory.git
  12. heimdall

    Agents & frameworks

    A lightweight CPU only memory approach with ranked retrieval. Simple, yet effective.

    Stale GitHub, ArihantDeva 137 ★MITUpdated 15 days ago

    git clone https://github.com/ArihantDeva/heimdall.git
  13. Hatchdoor

    MCP servers

    Self-host your Obsidian vaults: a web UI for you, MCP for your AI agents. No Obsidian, no plugins required.

    Stale GitHub, BatterWorks 73 ★AGPL-3.0Updated 13 days ago

    git clone https://github.com/BatterWorks/Hatchdoor.git
  14. evolving-agents

    Agents & frameworks

    A director agent that learns how your team works: it plans by walking your CLAUDE.md and memory as linked statements, delegates to Claude Code or local models, and keeps each lesson as a gated, versioned patch. Measured: 0.929 vs 0.589.

    Stale GitHub, EvolvingAgentsLabs 456 ★Apache-2.0Updated 28 days ago

    git clone https://github.com/EvolvingAgentsLabs/evolving-agents.git
  15. 孙学,零成本安装。孙宇晨两期访谈(邵艾伦、金明)的带时间戳全文,能动手的观点每个配一篇 AI 教程,工具都有国内能用的版本

    Stale GitHub, wousp112 205 ★Custom licence (see repository)Updated 17 days ago

    git clone https://github.com/wousp112/awesome-justin-sun-ideas-to-ai-howto.git
  16. ccmux

    Agents & frameworks

    🔮 Run all your AI coding agents in tmux: jump to the one that needs you, spawn them into worktrees, and hand work between them

    Indexed GitHub, epilande 243 ★MITUpdated today

    git clone https://github.com/epilande/ccmux.git
  17. apra-fleet

    MCP servers

    AI agents that write code, review each other's work, and coordinate across your machines

    Indexed GitHub, Apra-Labs 107 ★Custom licence (see repository)Updated today

    git clone https://github.com/Apra-Labs/apra-fleet.git
  18. safari-mcp

    MCP servers

    Native Safari browser automation for AI agents — 98 tools, zero Chrome overhead.

    Indexed Official MCP Registry, io.github.achiya-automation 228 ★Updated 2 days ago 1 note

    safari-mcp@2.24.1
  19. mavsdk_drone_show

    Agents & frameworks

    Open-source MAVLink fleet operations for PX4: SITL, drone shows, search and rescue, cooperative autonomy, and field validation

    Stale GitHub, alireza787b 334 ★Custom licence (see repository)Updated 20 days ago

    git clone https://github.com/alireza787b/mavsdk_drone_show.git
  20. ThinkTerm

    Agents & frameworks

    A modern terminal with a built-in multiplexer: close it and your sessions keep running. Run shells and tons of AI agents across your machines, then pick them up from desktop, browser, TUI and more. Written in Rust with no UI framework: interface drawn straight on the GPU. No Electron, GPUI or webview.

    Stale GitHub, RoversX 236 ★GPL-3.0Updated 9 days ago

    git clone https://github.com/RoversX/ThinkTerm.git
  21. sagent

    Agents & frameworks

    A coding-agent CLI and strongly-typed Python library -- self-mutating, hot-swapping, multi-provider, with async tool calls and bidirectional recursive spawn.

    Indexed GitHub, rekursiv-ai 84 ★Apache-2.0Updated today

    git clone https://github.com/rekursiv-ai/sagent.git
  22. 面向 Codex、Claude Code 等 AI Agent 的医学绘图 Skill,基于可信证据制作医学插画、科普漫画与科研示意图,提供可编辑成果与审核记录。 · Evidence-backed medical illustration, comics and research figures for Codex, Claude Code and other AI agents, with editable output and review records.

    Indexed GitHub, wilbert-MD-PhD 175 ★Custom licence (see repository)Updated 3 days ago

    git clone https://github.com/wilbert-MD-PhD/medical-illustration.git
  23. Verovo

    Agents & frameworks

    AI financial audit and task economics: connect usage, supplier charges and business outcomes to calculate task costs, cost per verified success and ROI.

    Indexed GitHub, roy-tong 219 ★MITUpdated 2 days ago

    git clone https://github.com/roy-tong/Verovo.git
  24. dsh-codex-effort-slider

    Agents & frameworks

    Codex 风格的推理等级滑条(DeepSeek Harness 插件):可拖动连续滑条 + 高档位渐变星尘特效

    Stale GitHub, Microqian2th 153 ★MITUpdated 30 days ago

    git clone https://github.com/Microqian2th/dsh-codex-effort-slider.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.