Skip to main content

Antikythera Agent SDK

General-purpose agent runtime with multi-agent orchestration, MCP tool integration, and WebAssembly support.

Installation

pip install antikythera-agent

For WASM execution support:

pip install antikythera-agent[wasm]

Quick Start

Create an Agent

from antikythera_agent import Agent, PromptManager, PromptConfig

prompts = PromptManager()
prompts.register(PromptConfig(
    id="assistant",
    name="Assistant",
    content="You are a helpful assistant.",
))

agent = Agent(
    provider="openai",
    model="gpt-4o",
    system_prompt=prompts.get_content("assistant")
)

result = agent.run("Hello, how can you help me?")
print(result.output)

Multi-Agent Orchestration

from antikythera_agent import Orchestrator, PromptManager, PromptConfig

prompts = PromptManager()
prompts.register(PromptConfig(
    id="coder",
    name="Coder",
    content="You are a software engineer.",
    tags=["engineering"]
))
prompts.register(PromptConfig(
    id="reviewer",
    name="Reviewer",
    content="You are a code reviewer.",
    tags=["quality"]
))

orchestrator = Orchestrator(execution_mode="auto", max_concurrent_tasks=4)

orchestrator.register_agent(AgentProfileConfig(
    id="coder",
    name="Coder",
    role="developer",
    system_prompt=prompts.get_content("coder")
))

orchestrator.register_agent(AgentProfileConfig(
    id="reviewer",
    name="Reviewer",
    role="reviewer",
    system_prompt=prompts.get_content("reviewer")
))

result = orchestrator.dispatch("Write and review code")

WASM Runtime (Server-Side)

from antikythera_agent import WasmRuntime

runtime = WasmRuntime()
result = runtime.call_checked("init", '{"max_steps": 10}')
print(result)

Load Prompts from JSON

from antikythera_agent import PromptManager

# Load from file
prompts = PromptManager.from_file("prompts.json")

# Or load from string
prompts = PromptManager.from_json('[{"id":"agent","name":"Agent","content":"You are helpful."}]')

Requirements

  • Python 3
  • wasmtime (optional, for WASM execution; the supported minimum is pinned in pyproject.toml)

License

MIT

Download files

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

Source Distribution

antikythera_agent-1.8.4.tar.gz (298.2 kB view details)

Uploaded Source

Built Distribution

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

antikythera_agent-1.8.4-py3-none-any.whl (300.8 kB view details)

Uploaded Python 3

File details

Details for the file antikythera_agent-1.8.4.tar.gz.

File metadata

  • Download URL: antikythera_agent-1.8.4.tar.gz
  • Upload date:
  • Size: 298.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/7.0.0 CPython/3.11.15

File hashes

Hashes for antikythera_agent-1.8.4.tar.gz
Algorithm Hash digest
SHA256 c86532c5310238aee23021d577c3ad701062fa8d23d9c0ba0d1c999e93a633b7
MD5 6b7e8d21406771bfae727a0c5da21efc
BLAKE2b-256 85abf1b64df3df8999da4728749ad55e48499361facf3e9c66aca370b0f8ad0d

See more details on using hashes here.

File details

Details for the file antikythera_agent-1.8.4-py3-none-any.whl.

File metadata

File hashes

Hashes for antikythera_agent-1.8.4-py3-none-any.whl
Algorithm Hash digest
SHA256 5af62bf1f6fd1bbf0979f06d4141841450218902fac0e0a8d77a764de09ee7aa
MD5 5a1741ac6b82564898344c2065d62d13
BLAKE2b-256 10b250d73f4c02eaa9ee3db128d044ba245f4a9bb26074bff480789bd395a69f

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 Sentry Error logging StatusPage Status page