Skip to main content

A framework for building distributed evolvable multi-agent system.

Project description

Pantheon

A framework for building distributed LLM based multi-agent system.

Build Status Install with PyPi MIT license

Work In Progress

Installation

pip install pantheon-agents

Examples

See the examples folder for more advanced usage patterns and custom implementations.

TODO

  • REPL for meeting and agent
  • Reasoning with O1 / Gemini Flash Thinking / Deepseek-R1
  • Distributed
    • Tools
    • Agents
      • Support streaming response
      • Support use in team
  • Agent team
    • Sequential Team
    • Swarm Team
    • MoA(Mixture-of-Agents) Team
  • Memory persistence
  • Report generation
  • Vision ability
  • GUI
    • Web UI
    • Slack
  • Documentation

Start a chatroom and work with it

git clone https://github.com/aristoteleo/pantheon-agents.git
cd pantheon-agents

pip install -e .
export OPENAI_API_KEY=your_openai_api_key
python -m pantheon.chatroom

Then you can see a service id of chatroom, you can copy it, then open https://pantheon-ui.vercel.app/ paste the service id and click "Connect".

Pantheon CLI

The easiest way to start using Pantheon is through the CLI interface:

# Start with default settings
python -m pantheon.cli

See pantheon/cli/README.md for detailed documentation.

Project details


Download files

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

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

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

pantheon_agents-0.3.3rc1-py3-none-any.whl (98.4 kB view details)

Uploaded Python 3

File details

Details for the file pantheon_agents-0.3.3rc1-py3-none-any.whl.

File metadata

File hashes

Hashes for pantheon_agents-0.3.3rc1-py3-none-any.whl
Algorithm Hash digest
SHA256 52cb20a8ff1624293aef0fbbfa7c92cde378ac515ac19963e529ea36a0fcab7d
MD5 393c0587f9c746c1f2d0b24de92d9645
BLAKE2b-256 d019a0300753e224af88303bc897606c470142909cbd3a062bf48258ecf19103

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