Skip to main content

Aurelion Agent — base agent loop, tool calling, tracing, and LLM provider interface

Project description

aurelion-agent

Part of the AURELION Ecosystem

A modular base agent loop with tool calling, multi-provider LLM support, and built-in trace observability. Drop it into any project to get a production-ready agent in minutes.

Install

pip install aurelion-agent

Quickstart

from aurelion_agent import BaseAgent, LLMProvider

class MyAgent(BaseAgent):
    name = "my-agent"
    system_prompt = "You are a helpful assistant."

agent = MyAgent(llm=LLMProvider(provider="groq", model="llama-3.3-70b-versatile"))
trace = agent.respond("What is data minimisation?")
print(trace.last_response)

Providers

Supports: groq, openai, anthropic (claude), ollama, gemini, mistral

LLMProvider(provider="openai", model="gpt-4o")
LLMProvider(provider="ollama", model="llama3")
LLMProvider(provider="anthropic", model="claude-3-5-sonnet-20241022")

Trace Sinks

Wire observability into any agent with built-in sinks:

from aurelion_agent import FileSink, AgentOpsSink, stdout_sink

agent = MyAgent(
    llm=LLMProvider(provider="groq"),
    trace_sinks=[
        stdout_sink,
        FileSink("traces.jsonl"),
        AgentOpsSink("https://your-agentops-instance.fly.dev", api_key="..."),
    ]
)

Tool Calling

from aurelion_agent import BaseAgent, LLMProvider, tool

class ResearchAgent(BaseAgent):
    name = "researcher"
    system_prompt = "You research topics thoroughly."

    @tool
    def search_web(self, query: str) -> str:
        """Search the web for information."""
        # your implementation
        return results

Architecture

aurelion-agent is the Agent module of the AURELION modular cognitive architecture:

KERNEL    → Knowledge schema and organizational structure
MEMORY    → Persistent storage and retrieval
NEXUS     → Agent orchestration and routing
ADVISOR   → Strategic planning and knowledge management
AGENT     → This package — AI collaboration and prompt protocols

Links

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

aurelion_agent-0.2.0.tar.gz (24.3 kB view details)

Uploaded Source

Built Distribution

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

aurelion_agent-0.2.0-py3-none-any.whl (27.4 kB view details)

Uploaded Python 3

File details

Details for the file aurelion_agent-0.2.0.tar.gz.

File metadata

  • Download URL: aurelion_agent-0.2.0.tar.gz
  • Upload date:
  • Size: 24.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.9

File hashes

Hashes for aurelion_agent-0.2.0.tar.gz
Algorithm Hash digest
SHA256 5acb30c682d66f87fd786ac11dfc94deceacf9344f0b00cb845c34e21217ea38
MD5 398b2cf28b2d09b4053df9845d8a4874
BLAKE2b-256 4c37da1aa018caa77847c31e24a62f7c2445dbcc1f3d7e3497821e3a53d0391b

See more details on using hashes here.

File details

Details for the file aurelion_agent-0.2.0-py3-none-any.whl.

File metadata

  • Download URL: aurelion_agent-0.2.0-py3-none-any.whl
  • Upload date:
  • Size: 27.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.9

File hashes

Hashes for aurelion_agent-0.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 6d6cc5ea2b91a242b11fd68efee013975e3fb31c5010bdc73f116c04afd6b7ef
MD5 22d2809b5643e5ef265f5eb7cc0a74db
BLAKE2b-256 e454d4a600dcfc0f6c6b9da6c075bb8ba731582a791981f0c6524b083ba1a244

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