InnerVault

Library

85,766 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

1,028 results Clear search and filters

Looks like a goal we have a starting path for: I want to build a website or app

  1. openquok-monorepo

    MCP servers

    All-in-one Content OS: social scheduling and directory launch in one workspace. Calendar, kanban, and product profiles. Extension autofill for directory listings; you approve every post and submit. Agents via CLI, MCP, and public API. Cloud or self-host.

    Indexed GitHub, Ratimon 107 ★AGPL-3.0Updated yesterday

    git clone https://github.com/Ratimon/openquok-monorepo.git
  2. Permit-verified ADU rentals, pre-approved plans and cited ADU rules for LA, San Diego, SF and NYC.

    Stale Official MCP Registry, homes.a-du Updated 20 days ago 1 note

  3. Google Flow's agent: chat that plans and makes images and videos, approvals, your own media

    Stale Official MCP Registry, net.useapi Updated 22 days ago 1 note

  4. Give your AI a budget, not your card: fund a room, set an approval line, AI hires over MCP. Sandbox.

    Stale Official MCP Registry, com.aurmada.rooms Updated 6 days ago 1 note

  5. second-shift

    Skills

    Scheduled agent tasks for your repositories, defined in Git. Approved access, sandboxed runs, a full audit trail.

    Stale GitHub, piotrekno1 7 ★Apache-2.0Updated 10 days ago

    git clone https://github.com/piotrekno1/second-shift.git
  6. aiteamkit

    Skills

    Multi-harness AI plugin for Claude Code, Cursor and Codex CLI: skills that run the delivery lifecycle of a project team - intake, estimate, design, spec, breakdown, plan, implement, fix, review, QA, verify, release, incident, retro, onboard, handover. Author and approver stay separate roles.

    Indexed GitHub, lamngockhuong 12 ★MITUpdated 3 days ago

    git clone https://github.com/lamngockhuong/aiteamkit.git
  7. agent-orchestra

    Datasets & benchmarks

    Agents can work. They cannot declare success. A governed coordination protocol for multi-agent AI work: eight contracts (task, resource, ownership, handoff, verification, evidence, approval, recovery) enforced in code, plus a reproducible conformance benchmark. Apache-2.0 code, CC BY 4.0 specification, zero dependencies, Node 18+.

    Stale GitHub, 3338902669-ops 93 ★Apache-2.0Updated 25 days ago

    git clone https://github.com/3338902669-ops/agent-orchestra.git
  8. Tellurion

    Agents & frameworks

    Mission control for AI coding agents. Watch Claude Code, Codex, Gemini and a dozen more work live in one macOS terminal: live status, an editor that follows their edits, undo for any turn, approvals from your phone and local models. 20+ built-in tools, all on the site below. Built on Ghostty.

    Stale GitHub, steventsvik 142 ★AGPL-3.0Updated 5 days ago

    git clone https://github.com/steventsvik/Tellurion.git
  9. Send a file to a user or agent as a share link with expiry, max opens, approval, revoke and logs.

    Stale Official MCP Registry, io.github.jueluddinsf Updated 19 days ago 1 note

  10. Human-in-the-loop for AI agents: ask a person and get approvals or answers by push notification.

    Stale Official MCP Registry, io.github.Pushary Updated 23 days ago 1 note

  11. cantankerous

    Prompts

    Role & Objective: Act as an objective, intellectually honest expert collaborator. Your primary goal is absolute analytical accuracy, not user approval, validation, or agreement. Behavioral Constraints: Zero Sycophancy…

    Indexed prompts.chat (CC0 prompt collection), kennynah85@gmail.com CC0-1.0

  12. droid-mcp

    MCP servers

    Let an AI use your Android phone: an app and an SDK with 160+ MCP tools (calendar, SMS, files, camera, notifications, screen control) for Claude Code, Codex, Cursor or on-device models, with approvals on the phone.

    Stale GitHub, stixez 42 ★Apache-2.0Updated 9 days ago

    git clone https://github.com/stixez/droid-mcp.git
  13. socialforge

    Skills

    An open-source social media production system that turns a content calendar into on-brand copy, images, video, and client-ready delivery - with compliance and human approval built in.

    Stale GitHub, indranilbanerjee 43 ★MITUpdated 10 days ago

    git clone https://github.com/indranilbanerjee/socialforge.git
  14. skills

    Skills

    Spec Driven — orchestrator-first Agent Skills for spec-driven development. The orchestrator skill turns a PRD or idea into approved SPECs, tracked GitHub Issues, TDD-implemented slices, QA gates, and reviewed PRs across Claude Code, Codex, Cursor, OpenCode, and Devin.

    Stale GitHub, afonsoft 13 ★MITUpdated 21 days ago

    git clone https://github.com/afonsoft/skills.git
  15. OGAD

    AI repositories

    Your private, on-device personal AI assistant for macOS, Windows and Linux. Chat, create, search files, and connect tools with local models. Includes an OpenAI-compatible API. Opt-in Pro sees, remembers, reflects, and acts with your approval, for one payment. No cloud or account.

    Indexed GitHub, off-grid-ai 147 ★AGPL-3.0Updated 2 days ago

    git clone https://github.com/off-grid-ai/OGAD.git
  16. Act as a senior functional analyst: work in phases, state all assumptions, preserve existing behaviour, no UML/Gherkin/specs without explicit approval, be direct and analytical.

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

  17. Based on the approved concept, build the [Homepage/About/etc.] page. Constraints: - Single-file React component with Tailwind - Mobile-first, responsive - Performance budget: no library over 50kb unless justified -…

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

  18. agent-leash

    Skills

    LEASH-8: an 8-domain control model for AI agents with delegated authority. Scorecard, approval-design checklist, plan-vs-authorize pattern. Patterns from a live production agent operation, sanitized. Free, MIT.

    Indexed GitHub, tonydzi 5 ★MITUpdated 3 days ago

    git clone https://github.com/tonydzi/agent-leash.git
  19. duct

    Skills

    Open-source AI marketing agent: a growth analyst with every login. Reads Google Ads, GA4, Search Console, Stripe & more together, tells you why a number moved, and fixes it when you approve.

    Stale GitHub, 5hirish 9 ★MITUpdated 6 days ago

    git clone https://github.com/5hirish/duct.git
  20. bridge

    MCP servers

    ComplyEaze Bridge is an open-source (Apache-2.0) TallyPrime MCP server for Claude Desktop, for CA firms and accountants. Reads the books on your own computer; prepares vouchers from bank statements as an import file. Posting is off by default; when on, you approve each voucher.

    Stale GitHub, ComplyEaze 35 ★Apache-2.0Updated 6 days ago

    git clone https://github.com/ComplyEaze/bridge.git
  21. pgwarden

    MCP servers

    Governed Postgres access for AI assistants: an MCP gateway with OAuth 2.1 and OIDC login, one Postgres role per person, database-enforced read-only queries, PII masking, human-approved writes, a tamper-evident audit log, a red-team suite and Terraform for Cloud Run.

    Stale GitHub, B0yko 23 ★Apache-2.0Updated 11 days ago

    git clone https://github.com/B0yko/pgwarden.git
  22. { "role": "Approval Processor", "context": "You are responsible for processing annual leave requests.", "task": "Calculate and adjust annual leave balance when form_id is 1.", "constraints": [ "Oly apply to form_nid…

    Indexed prompts.chat (CC0 prompt collection), muhtesemozgur9 CC0-1.0

  23. Agent skill to clean up AI-generated code: audit, refactor and guard vibe-coded codebases with Claude Code, Cursor or Codex. A human approves every decision.

    Indexed GitHub, fictormarcel2 5 ★MITUpdated 6 days ago

    git clone https://github.com/fictormarcel2/untangle-everything.git
  24. graph

    Skills

    Turns any idea into a checked plan your AI must follow: reads you first, finds and safety-checks the best skills, one-tap approval, rules enforced in code, full logs. Claude Code, Codex, Cursor, OpenCode, OpenClaw.

    Stale GitHub, gwaghmar 15 ★MITUpdated 6 days ago

    git clone https://github.com/gwaghmar/graph.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.