Skip to main content

A Python library for building low-code, capable and extensible autonomous agent systems.

Project description

emp-agents

A library for building low-code, capable and extensible autonomous agent systems open sourced by Empyreal.


Docs

Read the docs here


Quick Start

pip install emp-agents
import asyncio
import os

from eth_rpc import set_alchemy_key

from emp_agents.agents.skills import SkillsAgent
from emp_agents.tools.dexscreener import DexScreenerSkill
from emp_agents.tools.protocol.erc20 import ERC20Skill
from emp_agents.tools.protocol.wallets import SimpleWalletSkill
from emp_agents.types import OpenAIModelType

if alchemy_key := os.environ.get("ALCHEMY_KEY"):
    set_alchemy_key(alchemy_key)


agent = SkillsAgent(
    skills=[
        ERC20Skill,
        SimpleWalletSkill,
        DexScreenerSkill,
    ],
    default_model=OpenAIModelType.gpt_4o,
    openai_api_key=os.environ.get("OPENAI_API_KEY"),
)


if __name__ == "__main__":
    asyncio.run(agent.run())

Available SkillSets

SkillSets are designed to extend the capabilities of the agent by providing a collection of tools that can be used to perform tasks. The following SkillSets are currently available

Creating a Custom SkillSet

SkillsSets is a collection of tools that can be used to build agents. To create a custom SkillsSet, you can subclass the SkillsSet class and implement the tools property. SkillSets are designed to be modular and extensible and they are supported both by the OpenAI models and Anthropic models.

You can see an example of a custom SkillsSet in the docs.

Future Work

Some of the features we are working on open sourcing are:

  • Agent Autonomy
  • Simulacrum SkillSet
  • Agent Memory system
  • Research SkillSets
  • Prebuilt Agent Templates
  • Pluggable library components

Reach out at EmpyrealSDK if you would like to learn more about the project.

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

emp_agents-0.1.5.post1.tar.gz (35.3 kB view details)

Uploaded Source

Built Distribution

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

emp_agents-0.1.5.post1-py3-none-any.whl (50.1 kB view details)

Uploaded Python 3

File details

Details for the file emp_agents-0.1.5.post1.tar.gz.

File metadata

  • Download URL: emp_agents-0.1.5.post1.tar.gz
  • Upload date:
  • Size: 35.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.0.1 CPython/3.12.8

File hashes

Hashes for emp_agents-0.1.5.post1.tar.gz
Algorithm Hash digest
SHA256 166ec91cb494c16bf4c07d09329bfaf1ba8a9b9172ac67fe5f3d60379bb1e1c7
MD5 484d58608e50049c7d4879529bc14e75
BLAKE2b-256 b09cfaeac87d80fe9ee8aeb0ed804df25c994c66d9f803cac14298ebf23a567c

See more details on using hashes here.

File details

Details for the file emp_agents-0.1.5.post1-py3-none-any.whl.

File metadata

File hashes

Hashes for emp_agents-0.1.5.post1-py3-none-any.whl
Algorithm Hash digest
SHA256 5436177667a6e95fbe8b05ee7c5684707baafba7bc215796cfbbde3edbcea093
MD5 71e1fa3055380077d92191fb981c5a55
BLAKE2b-256 3c756766b3677d11c1ecd06e559507a51fad1a61f5249899ab3ef1ef7e69da1f

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