evoagentx
par nantes
AI & LLMsRésumé
EvoAgentX - Self-evolving AI agents framework integration.
Description
Ce que fait ce skill
EvoAgentX is a framework for building AI agents that auto-construct workflows from a stated goal and improve themselves based on feedback. It supports multiple LLM backends and includes short-term and long-term memory. The skill provides install, status check, docs, and workflow execution commands via PowerShell.
Auto-constructing workflows from a goal description removes the need to manually wire together agent steps that most frameworks require you to define upfront.
Quand l'utiliser
- Running a multi-step research task by describing a goal in plain text
- Automating a repetitive workflow that requires iterative refinement
- Testing how different LLM backends handle the same agent goal
- Building a prototype agent pipeline without writing orchestration code manually
- Checking which API keys and dependencies are configured before running a job
Exemple de workflow
User asks: run an EvoAgentX workflow with the goal 'summarize top AI papers from last week'
- 1
Sets OPENAI_API_KEY environment variable
- 2
Runs evoagentx.ps1 -Action status to confirm installation and key presence
- 3
Runs evoagentx.ps1 -Action run -Goal 'summarize top AI papers from last week'
- 4
EvoAgentX auto-constructs a workflow, executes agent steps, and applies self-evolution based on intermediate feedback
A summary of recent AI papers produced by the self-constructed agent workflow
Prérequis
- OPENAI_API_KEY environment variable (or equivalent for Claude, DeepSeek, or Qwen)
Installation
clawhub install nantes/evoagentxExécute la commande CLI, ou colle l'instruction dans Claude Code, Cursor, Codex ou l'agent de code que tu utilises.