Skip to main content

Multi-agent SDK with Bedrock, ReAct, parallel sub-agents

Project description

AgentSDK

A Python SDK for building multi-agent systems with Bedrock-backed LLMs, ReAct tool-use, and parallel sub-agent orchestration.

Install

pip install agentsdk

Quickstart

from agentsdk import (
  BedrockClient, SessionManager, ToolRegistry, Agent,
  OrchestratorAgent, load_sub_agents_from_dir,
  FileSystemTool, ShellTool, WebFetchTool,
)

bedrock = BedrockClient(model_id="openai.gpt-oss-120b-1:0", region_name="us-west-2")
sessions = SessionManager()
registry = ToolRegistry()
registry.register(FileSystemTool(root="."))
registry.register(ShellTool(root="."))
registry.register(WebFetchTool())

def on_thought(agent, kind, text):
    print(f"[{agent}][{kind}] {text[:160]}")

default = Agent(
  name="default", bedrock=bedrock, registry=registry,
  sessions=sessions, system_prompt="You are a helpful coding assistant.",
  on_thought=on_thought,
)
subs = load_sub_agents_from_dir(".agents", base_agent=default)

orch = OrchestratorAgent(
  planner=default, sub_agents=subs, sessions=sessions,
)

print(orch.run(session_id="sess1", query="Audit repo for secrets and summarize."))

CLI

agentsdk run --agents-dir .agents --show-thoughts --query "Your task"

License

Apache-2.0

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

agentsdk_ayush2-0.1.4.tar.gz (14.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

agentsdk_ayush2-0.1.4-py3-none-any.whl (17.2 kB view details)

Uploaded Python 3

File details

Details for the file agentsdk_ayush2-0.1.4.tar.gz.

File metadata

  • Download URL: agentsdk_ayush2-0.1.4.tar.gz
  • Upload date:
  • Size: 14.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.4

File hashes

Hashes for agentsdk_ayush2-0.1.4.tar.gz
Algorithm Hash digest
SHA256 2b12db24cb47acf356fe7f3e6a92787901dd4488c340c082d59f47bb157be23a
MD5 add7735db6cac89e93128b45678d22ca
BLAKE2b-256 073a09b92f0145e7260b188bd430b6ebb3b3fa3cc059e09338182130ec1f7d92

See more details on using hashes here.

File details

Details for the file agentsdk_ayush2-0.1.4-py3-none-any.whl.

File metadata

File hashes

Hashes for agentsdk_ayush2-0.1.4-py3-none-any.whl
Algorithm Hash digest
SHA256 f05de979f32faa81d4c2b2a95d1c43a1efbee1d43c184a4e799e9748b15c1af8
MD5 64946ab28800319c56cf963ea6ee439d
BLAKE2b-256 5677ff8acb05f8f3ccfab5d27f20e00f7cb6da68e795137f95f489726b62b251

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page