InnerVault

Library

86,671 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

10,553 results Clear search and filters

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

  1. flutter-flame-harness

    Agents & frameworks

    Idea-to-store autonomous harness for Flutter/Flame games across Claude Code, Antigravity, and Codex. Automates research, planning, design, generator-evaluator loops, AdMob, and store submission.

    Indexed GitHub, tjdrhs90 61 ★MITUpdated yesterday

    git clone https://github.com/tjdrhs90/flutter-flame-harness.git
  2. Selvedge

    MCP servers

    Persistent decision memory for AI agents: rationale, rejected approaches, and entity history.

    Stale Official MCP Registry, io.github.masondelan 26 ★Updated 16 days ago 1 note

    selvedge@0.3.18
  3. Telegram automation for coding agents — Claude Code plugin + tg-agent CLI. Read/send messages, manage channels, media, analytics, content pipelines. Multi-account, flood-safe, Telethon-powered.

    Indexed GitHub, axisrow 38 ★MITUpdated today

    git clone https://github.com/axisrow/tg_content_factory.git
  4. model-citizen

    Skills

    The control plane for your coding agents, however you run them. One checkout of rules, skills, subagents, hooks and stances, projected into Claude Code and Codex with your own primitives: hook-enforced guardrails, usage telemetry, cost postures and model tiering, under any rules library or orchestration layer.

    Stale GitHub, JakeSelby 24 ★MITUpdated 33 days ago

    git clone https://github.com/JakeSelby/model-citizen.git
  5. DroidBridge

    MCP servers

    On-device MCP server for Android. Connect ChatGPT through OpenAI's official secure tunnel, let AI agents operate your phone and run scheduled automations on it — App edition (Accessibility/Shizuku) or root edition (Magisk/KernelSU/APatch). No PC, no ADB. 卓爱桥

    Indexed GitHub, zephyr7030 23 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/zephyr7030/DroidBridge.git
  6. vigilante

    Skills

    Vigilante is a sandbox-first orchestration layer for coding agents. It isolates every task in a git worktree, enforces strict credential scoping, and gives you full audit logs — so your agents can't burn down production.

    Stale GitHub, aliengiraffe 41 ★Apache-2.0Updated 4 days ago

    git clone https://github.com/aliengiraffe/vigilante.git
  7. 16 Claude Code skills for data engineers: profile a new source, investigate a failed run, review a change, document the platform. Most end in a page you can share.

    Stale GitHub, DataWithBaraa 86 ★MITUpdated 11 days ago

    git clone https://github.com/DataWithBaraa/claude-code-data-engineering-skills.git
  8. Claude Code skills that make Claude (Fable) the conductor of AI worker fleets: many parallel OpenAI Codex workers plus Opus design agents, organized into campaigns, waves, squads, and review gates.

    Indexed GitHub, jvogan 56 ★MITUpdated 3 days ago

    git clone https://github.com/jvogan/a-fable-of-codexes.git
  9. brigade

    Skills

    Brigade Stack: run coding agents anywhere and keep one record of the work. Shared tasks, claims, verification receipts, handoffs, and MCP and skills sync for Claude Code, Codex, Cursor, OpenCode, and T3 Code.

    Indexed GitHub, escoffier-labs 83 ★MITUpdated today

    git clone https://github.com/escoffier-labs/brigade.git
  10. pi-code

    MCP servers

    Claude Code experience for the pi coding agent: reads your .claude config (rules, commands, skills, hooks, output styles, MCP, agents) and adds todo, checkpoints, memory, web search, and subagents.

    Indexed GitHub, ilovepixelart 36 ★MITUpdated 2 days ago

    git clone https://github.com/ilovepixelart/pi-code.git
  11. lighthouse-mcp-server

    MCP servers

    MCP server that enables AI agents to perform comprehensive web audits using Google Lighthouse with 13+ tools for performance, accessibility, SEO, and security analysis.

    Stale GitHub, danielsogl 74 ★MITUpdated 15 days ago

    git clone https://github.com/danielsogl/lighthouse-mcp-server.git
  12. hashtree

    Skills

    Permissionless storage and Git for humans and agents. Publish and clone with local keys—no hosting account.

    Stale GitHub, mmalmi 12 ★Updated 12 days ago

    git clone https://github.com/mmalmi/hashtree.git
  13. Claude Code plugin marketplace & agent skills for RudderStack — instrument events, design tracking plans & data graphs, write transformations, build Profiles, and drive the CLI, MCP server, and Terraform provider from Claude Code, Cursor, and 40+ AI agents.

    Indexed GitHub, rudderlabs 19 ★MITUpdated 4 days ago

    git clone https://github.com/rudderlabs/rudder-agent-skills.git
  14. tyran

    Agents & frameworks

    A task conductor for Claude Code that gets better the more you use it. Multi-agent orchestration with an evidence contract that BLOCKS instead of asking, gates written as hooks rather than prompts, and a retrospective that learns your repo's rules and tunes its own playbook.

    Indexed GitHub, jjanczur 79 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/jjanczur/tyran.git
  15. Agent Skill for GitHub repository setup and platform-specific features | Claude Code compatible

    Stale GitHub, netresearch 10 ★Custom licence (see repository)Updated 18 days ago

    git clone https://github.com/netresearch/github-project-skill.git
  16. outlook-assistant

    MCP servers

    MCP server for Outlook email, calendar, and contacts — let your AI assistant manage your inbox directly from the conversation.

    Indexed GitHub, littlebearapps 40 ★MITUpdated today

    git clone https://github.com/littlebearapps/outlook-assistant.git
  17. skills

    Skills

    Open-source marketing skills that turn Claude Code, Codex and other AI agents into an AI CMO.

    Indexed GitHub, Ekos-Labs 10 ★MITUpdated 3 days ago

    git clone https://github.com/Ekos-Labs/skills.git
  18. AI Research Radar — Evidence-Grounded Trend Ledger for AI Systems

    Indexed GitHub, Neetx 5 ★Updated today

    git clone https://github.com/Neetx/ai-research-radar.git
  19. warden-mcp

    MCP servers

    🔐 Vaultwarden / Bitwarden MCP server for credential-aware AI agents

    Indexed GitHub, icoretech 29 ★MITUpdated yesterday

    git clone https://github.com/icoretech/warden-mcp.git
  20. crux

    Skills

    A scientific-method lab notebook your AI agent drives — research as a tree of questions and falsifiable hypotheses in plain markdown, with an LLM literature wiki, a task manager, and a local browser GUI cockpit.

    Stale GitHub, mehdiforoozandeh 18 ★MITUpdated 17 days ago

    git clone https://github.com/mehdiforoozandeh/crux.git
  21. Agentic, long-horizon visual generation: a fuzzy story → a cross-model-audited image-based movie. Brings ARIS's research-wiki + multi-agent debate to multimodal generation (intelligence lives in the agent; the diffusion model just renders). Image-based today, video next.

    Stale GitHub, wanshuiyin 75 ★MITUpdated 11 days ago

    git clone https://github.com/wanshuiyin/ARIS-Movie-Director.git
  22. A portable AI work protocol: reuse proven solutions, limit redundant retrieval, deliver results. 让 AI 先复用、少重复、重交付。

    Indexed GitHub, RenatusPang 16 ★MITUpdated 3 days ago

    git clone https://github.com/RenatusPang/network-reuse-protocol.git
  23. quil

    MCP servers

    Reboot-proof terminal multiplexer for AI-native devs — a tmux alternative that persists your whole workspace across reboots and auto-resumes Claude Code & OpenCode sessions. Ships an MCP server so AI agents can drive your panes. Go, cross-platform (Linux/macOS/Windows). Apache-2.0.

    Stale GitHub, artyomsv 27 ★Apache-2.0Updated 12 days ago

    git clone https://github.com/artyomsv/quil.git
  24. Agent Skill for systematically upgrading TYPO3 extensions to newer LTS versions | Claude Code compatible

    Stale GitHub, netresearch 11 ★Custom licence (see repository)Updated 18 days ago

    git clone https://github.com/netresearch/typo3-extension-upgrade-skill.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.