compound
Which host should serve your open model? Run your workload across pinned, verified providers and get one table: success, cost, latency, cache hits.
- 8
- TypeScript
- Apache-2.0
- 3 wk ago
Which host should serve your open model? Run your workload across pinned, verified providers and get one table: success, cost, latency, cache hits.
LLM-driven evolution of prompts and pipelines. Evolves the prompt and the pipeline's parameters together against your labeled data, cuts losing candidates early, and shows every measurement behind the winner. Open source.
A physics-grounded, agent-driven digital twin for HP Metal Jet S100 3D printer
Turn repeated LLM classification calls into a small, fast, local model for one fixed task.
GUI for the shrewd package for building fast, locally runnable text classifiers from your own labels and LLM-generated labels. Supports both standard classifiers and Jev style decision panels.
A dataset-free agent artifact optimizer that compresses agent customizations, preserving behavior and quality.
A brief experiment applying GEPA (optimize_anything) to automatically compress Python solutions on code.golf.