Open Issues Need Help
View All on GitHubAI Summary: Enhance Handit's Release Hub to suggest optimal model changes in addition to prompt modifications, based on performance analysis and detected issues. This involves integrating model selection logic into the existing optimization pipeline, potentially incorporating metrics like accuracy, latency, and cost-effectiveness to guide model recommendations.
🧠 Open-source optimization engine for LLM agents. Track logs, evaluate behavior, generate insights, and improve agent performance through manual versioning and analysis. Built to make AI actually work.
AI Summary: Enhance Handit's monitoring capabilities to track and display the average percentage of the total context window used by each model. This involves adding functionality to the Handit SDKs (Python and JavaScript) to capture context window usage data and updating the Handit dashboard to visualize this data.
🧠 Open-source optimization engine for LLM agents. Track logs, evaluate behavior, generate insights, and improve agent performance through manual versioning and analysis. Built to make AI actually work.