Verified:GitHub

autonomy

Orchestrate autonomous research loops for Synapse projects with Claude Code.

29|3|Updated Mar 20, 2026

Search Tags:#MCP tools #project synthesis #autonomous research #experiment orchestration #sub-agent dispatch #compute scheduling

Ready to run

npx skills add https://github.com/Vincentwei1021/Synapse --skill autonomy-vincentwei1021

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: autonomy
Source: https://github.com/Vincentwei1021/Synapse/tree/main/public/synapse-plugin/skills/autonomy
Command: npx skills add https://github.com/Vincentwei1021/Synapse --skill autonomy-vincentwei1021

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps orchestrate autonomous research execution for Synapse projects by continuously proposing experiments, dispatching sub-agents to run them, and iterating based on observed results and project context.

Core Features & Use Cases

Autonomous CC-client research loop: drives the in-session iteration cycle that plans the next experiment, monitors in-flight work, and continues until stop conditions are met.
Sub-agent dispatch and monitoring: automatically schedules heartbeat monitoring for long-running experiments and spawns Task-tool sub-agents for pending experiments.
Project synthesis maintenance: updates the platform’s project synthesis so the main loop keeps a rolling, tool-based understanding of what has been learned.

Quick Start

Ask your Claude Code agent to run a Synapse project autonomously by turning on the autonomous loop for the target research project UUID.

Frequently Asked Questions about autonomy

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I run autonomous research loops for a Synapse project using Claude Code?▼

To run autonomous research loops, ask your Claude Code agent to turn on the autonomous loop for the target Synapse project UUID. The skill drives in-session iteration by proposing experiments, dispatching sub-agents, monitoring progress, and updating project synthesis until stop conditions are met.

What is sub-agent dispatch and monitoring for autonomous experimentation?▼

Sub-agent dispatch and monitoring automatically schedules heartbeat monitoring for long-running experiments and spawns Task-tool sub-agents for pending experiments. This mechanism ensures continuous progress tracking and execution coordination within the autonomous research loop.

Can I use autonomous research orchestration with existing server-side autonomous loops?▼

No, autonomous research orchestration requires mutual exclusion against server-side autonomous loops. The in-session control flow manages compute availability, experiment status queues, and synthesis updates independently to prevent conflicts with server-side processes.

How does project synthesis maintenance work during autonomous experimentation?▼

Project synthesis maintenance updates the platform's project synthesis continuously during experimentation. This ensures the main orchestration loop maintains a rolling, tool-based understanding of observed results and what has been learned throughout the research cycle.

Do I need MCP tools to orchestrate autonomous research execution?▼

Yes, MCP tool calls are required for project context, experiment proposal, dispatch, and checkpointing. The autonomous research loop relies on in-session control flow and MCP tools to coordinate compute scheduling and stop-condition handling.