pippin  by pippinlovesyou

Digital Being framework for autonomous agents

Created 1 year ago
541 stars

Top 58.8% on SourcePulse

GitHubView on GitHub
Project Summary

Pippin is an open-source framework for building autonomous digital agents that learn user objectives, integrate with tools via APIs or OAuth, and dynamically create/test new activities to achieve goals. It targets developers and power users looking to create self-improving AI agents capable of complex task execution and adaptation.

How It Works

Pippin employs a modular architecture with distinct components for core logic, memory, state management, and activity selection. Agents learn objectives and persona, then leverage a memory system to track past actions. They can connect to over 250 tools via Composio for OAuth-based integrations or use direct API keys for custom skills. The framework supports multiple LLM models, allowing different models to be assigned to specific tasks like code generation or reasoning.

Quick Start & Requirements

  • Install dependencies using uv pip install -r requirements.txt after setting up a virtual environment.
  • Python 3.9+ recommended.
  • A Composio developer key is optional but recommended for OAuth integrations.
  • Onboarding can be done via CLI (python -m tools.onboard) or Web UI (python -m server).
  • Launch the agent with python -m framework.main.
  • Official Docs: https://github.com/pippinlovesyou/pippin

Highlighted Details

  • Integrates with 250+ tools via Composio for OAuth-based skill connections.
  • Supports dynamic code generation for new activities, allowing agents to adapt and self-improve.
  • Offers flexible onboarding through a CLI wizard or a web-based UI.
  • Enables multi-LLM configurations for specialized task delegation.

Maintenance & Community

  • The project is actively maintained by pippinlovesyou.
  • Contributions are welcomed via pull requests.

Licensing & Compatibility

  • MIT License.
  • Permissive license suitable for commercial use and integration into closed-source projects.

Limitations & Caveats

The framework requires at least one LLM API key or local model configuration to start, and Composio integration is recommended for full functionality. Manual skill creation requires understanding Python and the framework's API.

Health Check
Last Commit

1 year ago

Responsiveness

Inactive

Pull Requests (30d)
0
Issues (30d)
0
Star History
5 stars in the last 30 days

Explore Similar Projects

Starred by Eric Zhu Eric Zhu(Coauthor of AutoGen; Research Scientist at Microsoft Research), Elvis Saravia Elvis Saravia(Founder of DAIR.AI), and
2 more.

deepagents by langchain-ai

2.0%
10k
Framework for building advanced LLM agents
Created 7 months ago
Updated 1 day ago
Starred by Elie Bursztein Elie Bursztein(Cybersecurity Lead at Google DeepMind), Chip Huyen Chip Huyen(Author of "AI Engineering", "Designing Machine Learning Systems"), and
7 more.

SuperAGI by TransformerOptimus

0.1%
17k
Open-source framework for autonomous AI agent development
Created 2 years ago
Updated 1 year ago
Starred by Elvis Saravia Elvis Saravia(Founder of DAIR.AI), Chip Huyen Chip Huyen(Author of "AI Engineering", "Designing Machine Learning Systems"), and
5 more.

activepieces by activepieces

0.5%
21k
Open-source Zapier alternative for AI workflow automation
Created 3 years ago
Updated 17 hours ago
Starred by Wes McKinney Wes McKinney(Author of Pandas), Chip Huyen Chip Huyen(Author of "AI Engineering", "Designing Machine Learning Systems"), and
22 more.

autogen by microsoft

0.4%
55k
Agentic framework for multi-agent AI applications
Created 2 years ago
Updated 1 month ago
Feedback? Help us improve.