auto_agents
Skill0 starsChanged 6 months agoMITView on GitHub
Automatically create and manage sub-agents for complex tasks.
In this repository34 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/stack.mdcCursor rule
- api_integrationSkill
- audio_transcriptionSkill
- browserSkill
- code_analysisSkill
- code_executionSkill
- data_analystSkill
- deep_researchSkill
- docsSkill
- emailSkill
- git_integrationSkill
- gmailSkill
- google_sheetsSkill
- image_generationSkill
- messagingSkill
- notionSkill
- ocrSkill
- parsingSkill
- ragSkill
- researchSkill
- rss_newsSkill
- schedulerSkill
- self_devSkill
- slidesSkill
- social_mediaSkill
- sql_dbSkill
- templateSkill
- translationSkill
- video_processingSkill
- visionSkill
- voice_ioSkill
- web3Skill
- web_automationSkill
The file
Files
Auto Agents
Automatically create and manage sub-agents for complex tasks.
Description
Analyzes incoming tasks and spawns specialized sub-agents to handle different aspects in parallel.
Usage
from core.auto_agent_factory import AutoAgentFactory
from core.agent_store import AgentStore
store = AgentStore()
factory = AutoAgentFactory(store)
result = factory.spawn_for_task("Research AI trends and write a summary")Behavior
- LLM analyzes the task to identify sub-tasks
- Creates temporary agent configs for each sub-task
- Runs agents in parallel via ThreadPoolExecutor
- Synthesizes results into a unified response
- Cleans up temporary agents
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.