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
Metadata
Release files for antikythera-agent 1.8.5
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| antikythera_agent-1.8.5.tar.gz | 299.7 kB | Without provenance | Details for antikythera_agent-1.8.5.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| antikythera_agent-1.8.5-py3-none-any.whl | Python 3 | none | any | Details for antikythera_agent-1.8.5-py3-none-any.whl |
Total release size: 602.1 kB
Release files / antikythera_agent-1.8.5.tar.gz
| Download URL | antikythera_agent-1.8.5.tar.gz |
|---|---|
| Size | 299.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
8681512855d0da86730ada6b3ded2f5dcd186e0ec44a85723fd134890a204a42
|
|
BLAKE2b-256 checksum How to use checksums |
5a3c63f25dad34736b0e01e0cf71843e98682311f3b773287c809746df74c729
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.11.15
|
Release files / antikythera_agent-1.8.5-py3-none-any.whl
| Download URL | antikythera_agent-1.8.5-py3-none-any.whl |
|---|---|
| Size | 302.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
ef1cf2cc122247e237accdd4a23e898a10c28888073376a61ce9c4fb0ffa37b3
|
|
BLAKE2b-256 checksum How to use checksums |
10ed7d5c3e252570bf824e4d7f58c6721bd299e9cb4a475a9f99cb60a8fda821
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.11.15
|
Security for antikythera-agent 1.8.5
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.