Orchestrate Swarms of Agents From Any Framework Like OpenAI, Langchain, and Etc for Real World Workflow Automation. Join our Community: https://discord.gg/DbjBMJTSWD
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
Go to file
Occupying-Mars b62bdf27b6
doc update
4 months ago
.github Bump actions/setup-python from 3 to 5 8 months ago
docs doc update 4 months ago
images [5.4.8] 8 months ago
scripts [SWARM MODELS MIGRATION] 7 months ago
swarms swarmrouter output file types 5 months ago
tests doc update 4 months ago
.env.example [FEAT][SpreadSheetSwarm] [FEAT][TaskQueueSwarm] 8 months ago
.gitignore [DOCS FIX] 6 months ago
.pre-commit-config.yaml [5.4.8] 8 months ago
6_0_0.md [CLEANUP] 6 months ago
CODE_OF_CONDUCT.md [5.4.8] 8 months ago
CONTRIBUTING.md [CONTRIBUTING] 7 months ago
Dockerfile [[CLEANUP][hashicorp_vault], [FEATS][Swarm DFS] [Swarm MonteCarlo] [Swarm Tree] [FIXES][Schema fixes] [Logging][Fixed a bug where logs and errors would be sent into root, now an agent workspace dir] [DEMOS][Marketing Campaign] [HiearchicalSwarm] 8 months ago
LICENSE Rename LICENSE.md to LICENSE 6 months ago
README.md doc update 4 months ago
SECURITY.md [5.4.8] 8 months ago
agent_with_rag.py [CLEANUP][Models] 7 months ago
agent_with_rag_and_tools.py [CLEANUP] 7 months ago
auto_flow.py [CLEANUP] 6 months ago
auto_swarm_builder.py [FEATS][ run_agents_concurrently, 6 months ago
auto_swarm_router.py [CLEANUP] 6 months ago
example.py [FEAT][Output file types] 6 months ago
outputs.txt [CLEANUP] 6 months ago
pyproject.toml [FEAT][Output file types] 6 months ago
requirements.txt [CLEANUP] 6 months ago
swarm_arange_demo.py [NEW UPDATE DOC FIXES] 6 months ago
tool_builder.py [CLEANUP] 6 months ago

README.md

The Enterprise-Grade Production-Ready Multi-Agent Orchestration Framework

Python Version

🐦 Twitter   •   📢 Discord   •   Swarms Platform   •   📙 Documentation

[Previous content remains unchanged until the new section...]

AsyncWorkflow

The AsyncWorkflow class enables asynchronous execution of multiple agents in parallel, allowing for efficient task processing and improved performance. This workflow is particularly useful when dealing with multiple independent tasks that can be executed concurrently.

Methods

Method Description Parameters Return Value
__init__ Initialize the AsyncWorkflow agents: List of Agent objects
max_workers: Maximum number of concurrent workers
None
run Execute tasks asynchronously tasks: List of tasks to be processed List of results from all tasks

Inputs

Input Type Description
agents List[Agent] List of Agent objects to process tasks
max_workers int Maximum number of concurrent worker threads
tasks List[str] List of tasks to be processed

Output

The run method returns a list containing the results from all processed tasks.

Example Usage