Skip to content

About

GenPark AI Agent Skill - Safe micro-action delegation with user guardrails and token budget gating inspired by Instinct.

Topics

Resources

Stars

8 stars

Watchers

0 watching

Forks

Latest commit

 

History

3 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 

Repository files navigation

GenPark Autonomous Personal Delegator Skill

GenPark Certified Protocol Category License

GenPark AI Agent Skill - Autonomous micro-action delegation with user guardrails, confidence thresholding, dry-run previews, and token budget gating.
Inspired by architectural paradigms from Instinct (instinct.is).


🌟 Overview & Architecture

Modern personal agents must evolve past static prompt-response turn-taking into continuous ambient cognitive companions.
The genpark-autonomous-personal-delegator-skill brings production-grade primitives for Model Context Protocol (MCP) clients, autonomous agent swarms, and personal assistants operating within the GenPark ecosystem.

+-------------------------------------------------------------+
|                GenPark Personal Agent Swarm                 |
+-------------------------------------------------------------+
       |                                              |
       v                                              v
+-----------------------------+        +------------------------------+
|   Zero-Prompt Anticipator   |        |   Hierarchical Memory Stream |
| (Activity & Context Sensing)|        |   (Temporal Decay & Vectors) |
+-----------------------------+        +------------------------------+
       |                                              |
       +----------------------+-----------------------+
                              |
                              v
       +----------------------------------------------+
       |     Autonomous Guardrailed Micro-Delegator    |
       |  (Sandboxed Dispatch & Token Budget Gating)  |
       +----------------------------------------------+

🛠️ Exposed Tools & Capabilities

evaluate_delegation_safety

Scores proposed autonomous actions against user risk boundaries, reversible impact levels, and required permissions.

stage_micro_action

Stages non-destructive micro-actions in a dry-run state awaiting automatic or single-click confirmation.

execute_sandboxed_dispatch

Executes verified micro-actions across connected agent tools within strict token and latency budgets.


🚀 Quickstart & MCP Configuration

Add this skill to your genpark.config.json or Claude / Cursor desktop MCP configurations:

{
  "mcpServers": {
    "genpark-autonomous-personal-delegator-skill": {
      "command": "npx",
      "args": ["-y", "@alphapark/genpark-autonomous-personal-delegator-skill"],
      "env": {
        "GENPARK_API_KEY": "your_genpark_api_key"
      }
    }
  }
}

📄 License

Apache-2.0 © 2026 GenPark AI Inc. (alphaparkinc)

About

GenPark AI Agent Skill - Safe micro-action delegation with user guardrails and token budget gating inspired by Instinct.

Topics

Resources

Stars

8 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors