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. all-agentic-architectures

    Agents & frameworks

    35 production-grade agentic AI architectures (Reflexion, LATS, GraphRAG, MemGPT, Voyager, BrowserAgent, ...) — a Python library and runnable textbook with multi-provider LLM support and a 17-task benchmark leaderboard.

    Indexed GitHub, FareedKhan-dev 4,756 ★MITUpdated today

    git clone https://github.com/FareedKhan-dev/all-agentic-architectures.git
  2. The Architecture Review Agent is an open-source AI agent sample that reviews software architectures and generates interactive diagrams automatically.

    Stale GitHub, Azure-Samples 109 ★MITUpdated 26 days ago

    git clone https://github.com/Azure-Samples/agent-architecture-review-sample.git
  3. agent-design-patterns

    Agents & frameworks

    A 7×6 framework for agent architecture. 28 patterns, each placed at a coordinate, runnable Python code with verified engineering slices from Claude Code, Aider, OpenHands, DeerFlow. Companion to Designing AI Agents (Manning) by Jia Huang.

    Stale GitHub, huangjia2019 306 ★MITUpdated 36 days ago

    git clone https://github.com/huangjia2019/agent-design-patterns.git
  4. archify

    Skills

    Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more.

    Indexed GitHub, tt-a1i 96.9k ★Apache-2.0Updated today

    git clone https://github.com/tt-a1i/archify.git
  5. Build LLM systems you actually control. A free, open engineering book + course — from tokenization to serving your own models. Mechanisms, trade-offs, and numbers, not prompt tips

    Stale GitHub, Drobiazkin 57 ★CC-BY-SA-4.0Updated 15 days ago

    git clone https://github.com/Drobiazkin/ai-agent-architecture.git
  6. Build AI agents from first principles using a local LLM - no frameworks, no cloud APIs, no hidden reasoning.

    Stale GitHub, pguso 1,047 ★MITUpdated 3 months ago

    git clone https://github.com/pguso/agents-from-scratch.git
  7. SeeCode

    Skills

    Animated, explorable diagrams for Claude and other coding agents, from a short JSON spec.

    Stale GitHub, Aryanutkarsh 846 ★MITUpdated 14 days ago

    git clone https://github.com/Aryanutkarsh/SeeCode.git
  8. Reference architecture and working case study for Codex × Antigravity agent-runtime collaboration.

    Stale GitHub, a275618631 11 ★MITUpdated 14 days ago

    git clone https://github.com/a275618631/codex-antigravity-collaboration.git
  9. A portable project-planning skill for Codex, Claude Code, pi, Hermes, and Agent Skills-compatible harnesses. Evidence before build advice.

    Stale GitHub, AaravKashyap12 320 ★MITUpdated 2 months ago

    git clone https://github.com/AaravKashyap12/advise-project-approach.git
  10. reposwarm

    Tools & apps

    Open-source multi-repo architecture discovery for AI coding agents. Analyze repositories, generate standardized .arch.md files, and keep them in a central results hub for agent context, onboarding and architecture reviews. GitHub, GitLab, CodeCommit, Azure DevOps and Bitbucket. Apache-2.0.

    Stale GitHub, reposwarm 279 ★Apache-2.0Updated 7 days ago

    git clone https://github.com/reposwarm/reposwarm.git
  11. Gridline

    Skills

    Portable AI agent skills, subagents, and plugins for architecture/AEC workflows across Codex, Claude Code, Gemini CLI, and other compatible agents.

    Stale GitHub, MakeItEzzz555 25 ★MITUpdated 21 days ago

    git clone https://github.com/MakeItEzzz555/Gridline.git
  12. 28 installable agent skills for construction: estimating, architecture, rendering, engineering, scheduling, site, safety, commercial and BD. Claude Code plugin, plain SKILL.md, CC BY 4.0.

    Stale GitHub, constructelligence-lab 10 ★Custom licence (see repository)Updated 7 days ago

    git clone https://github.com/constructelligence-lab/construction-agent-skills.git
  13. openflowkit

    Tools & apps

    Free, open-source diagram canvas. Draw it, write it as code (Mermaid, D2, Structurizr in), ask any AI model or a local one, let Claude Code edit it live over MCP, or map a GitHub repo with every arrow cited to a file and line. MIT, local-first, no account.

    Stale GitHub, openflowkit 960 ★MITUpdated 9 days ago

    git clone https://github.com/openflowkit/openflowkit.git
  14. neat

    MCP servers

    Live code graph that fuses static analysis (tree-sitter) with OpenTelemetry runtime traces, queried over MCP so AI coding agents get real full-stack context.

    Indexed GitHub, neat-technologies 34 ★Apache-2.0Updated today

    git clone https://github.com/neat-technologies/neat.git
  15. grok-bot-architecture

    Agents & frameworks

    MCP-native multi-agent architecture with desktop agents and human-in-the-loop gates

    Stale GitHub, tiagovilasboas 61 ★MITUpdated 6 days ago

    git clone https://github.com/tiagovilasboas/grok-bot-architecture.git
  16. skills

    Skills

    Agent skills for software delivery, from requirements gap analysis to reviewed, shipped code. Supports Claude Code, Codex, Cursor, Copilot, and OpenCode.

    Indexed GitHub, kevinlin 5 ★MITUpdated 2 days ago

    git clone https://github.com/kevinlin/skills.git
  17. claude-skills

    Prompts

    200+ production-ready Claude Code skills for sales, marketing, design, engineering, and AI agent architecture. Built and maintained by OneWave AI.

    Stale GitHub, OneWave-AI 367 ★MITUpdated 27 days ago

    git clone https://github.com/OneWave-AI/claude-skills.git
  18. 23 Claude Code plugins: TDD enforcement hooks, git/PR workflows, spec-driven development, code review, project lifecycle, fix-from-error, maintenance automation, context optimization, research, and multi-LLM delegation. 186 skills, 128 commands, 54 agents.

    Indexed GitHub, athola 350 ★MITUpdated 3 days ago

    git clone https://github.com/athola/claude-night-market.git
  19. CyberClaw

    Agents & frameworks

    👾 下一代透明智能体架构 | Next-Gen Transparent Agent Architecture 🔍 全行为审计 | 🛡️ 两段式安全调用 | 🧠 双水位记忆 | ⏰ 心跳任务 📊 P0 级事故率降低 80% | 兼容 OpenClaw + Claude Code 技能生态

    Stale GitHub, ttguy0707 336 ★MITUpdated 2 months ago

    git clone https://github.com/ttguy0707/CyberClaw.git
  20. Aegis

    Skills

    Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks.

    Indexed GitHub, GanyuanRan 1,442 ★MITUpdated 2 days ago

    git clone https://github.com/GanyuanRan/Aegis.git
  21. Build production-ready AI agents in Claude Code from natural language. Analyzes your problem, researches best practices, and generates subagents, skills, hooks, commands & MCP configs.

    Stale GitHub, keysersoose 45 ★MITUpdated 8 months ago

    git clone https://github.com/keysersoose/claude-agent-builder.git
  22. archlang

    MCP servers

    【Every star you give feeds a hungry developer's motivation! ⭐️】Floor plans as code. Your AI writes ArchLang; the compiler draws a precise, dimensioned plan (SVG, DXF, PDF) and tells it what's wrong. Open source, MIT.

    Indexed GitHub, ChanMeng666 72 ★MITUpdated today

    git clone https://github.com/ChanMeng666/archlang.git
  23. archboard

    Skills

    Plan the next change with your agent on a map of the system, before it writes a line. Then follow any feature into the code, and see every place where the map and the code disagree.

    Indexed GitHub, miklschmidt 11 ★Custom licence (see repository)Updated yesterday

    git clone https://github.com/miklschmidt/archboard.git
  24. A curated list of AI Agent evolution, memory systems, multi-agent architectures, and self-improvement projects. | evomap.ai

    Indexed GitHub, EvoMap 241 ★Custom licence (see repository)Updated today

    git clone https://github.com/EvoMap/awesome-agent-evolution.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.