Marrow AI: Control Layer for AI Agents alternatives

1

agent-device

by callstack

A

Open source device layer for AI agents: control mobile, web, TV, and desktop apps over MCP

2

HOL Guard

by hashgraph-online

A

Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.

3

Agent-Native Chat

by BuilderIO

A

Minimal chat-first app with durable threads, actions, and the app-agent loop

4

Emilia Protocol

by emiliaprotocol

B

Exact-action approval for consequential agent actions: request, track, and verify signed receipts.

Correction-first agent memory. Precision KPI tracks if agents heed warnings. 5 layers, local-only.

6

three.ws Provenance

by nirholas

B

Append-only, signed, on-chain-verifiable agent action log — record and audit what agents did.

7

agent-device

by callstackincubator

A

Let AI agents inspect, control, and debug real iOS, Android, desktop, and TV apps

8

Basic Memory

by basicmachines-co

B

Local-first knowledge management with bi-directional LLM sync via Markdown files.

9

Decionis

by decionis.com

A

Authorize consequential AI agent actions before execution

10

DCC-MCP Core

by dcc-mcp

A

Agent control plane for DCC and engine hosts: one MCP endpoint, one tool contract.

11

Godot MCP

by satelliteoflove

A

Agent-driven Godot playtesting: editor control, input injection, game-time stepping, live state.

12

Roast My Design System

by pencilrebel

A

Audit your Design System and serve your Agent the rules that keep AI-written UI on-system.

13

Decionis Commerce Gate MCP

by decionis.com

A

Commerce preflights, D365 authorization; opt-in agent writes require authorized backend connectors.

14

CHAP Coordinator

by BrightbeamAI

A

Auditable records of human decisions over AI agent work. Approvals, edits, overrides, escalations.

15

Kiln

by codeofaxel

B

Spawn an object into existence: describe it, and your agent designs it, checks it, and 3D prints it.

16

Roast My Design System

by gregkozakiewicz

A

Audit your Design System and serve your Agent the rules that keep AI-written UI on-system.

17

three.ws Autopilot

by nirholas

B

Set autopilot scopes and a daily SOL spend cap, then propose, execute, and undo agent actions.

18

Vibe Check

by PV-Bhat

B

Metacognitive AI agent oversight: adaptive CPI interrupts for alignment, reflection and safety

Security layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities.

20

Claude Prompts

by minipuft

A

Reusable prompt templates, multi-step workflow chains, and quality gates for any MCP client.

21

paper-preflight

by amos689

A

Checks every LaTeX reference against Crossref, dblp, arXiv, DataCite, PubMed and OpenAlex. No LLM.