Best Open-Source AI Project
Create an original project with open-source or open-weight AI at its core: a reusable agent skill, an application using a small/large language model, or software that manages a model's tools and workflow.
Useful Prototype Concepts
Ideas you can easily prototype and complete within a single day
Token Budget Lab
Compress long prompts while preserving instructions and key facts. Compare original vs compressed token counts and measure cost savings.
Safe Share
Preview sensitive information support tickets or logs expose. Combine pattern checks with open models to auto-redact data.
Context Picker
Select relevant passages within a strict token budget. Upload documents, ask questions, and inspect excerpt token budgets.
Chat Handoff
Turn long AI transcripts into compact briefs. Synthesize decisions, constraints, failed attempts, and next steps with sources.
First Version Rule
Keep the first version strictly focused: one input, one useful output, and a few realistic examples.
Submission Requirements
- Use open-source or open-weight AI as a substantial part of the project.
- Publish code in a public GitHub repository with an open-source license (MIT/Apache 2.0).
- Agent skills must adhere strictly to the Agent Skill Open Standard.
- Model harnesses must be original or contain meaningful improvements.