shinefuer/frugent
Cost-efficient coding-agent runtime: prefix-aware prompt-cache routing, poisoning-safe semantic cache, budgeted context compression, request batching/dedup, cascading model routing with DP-optimal policies, hard budget scheduling, span-level cost attribution, sandboxed tools, synthetic workload factory. NumPy core, CPU-only torch extra.
GitHub repository with 37 stars and 240 forks.
Language: Python
Topics: coding-agent, context-compression, cost-optimization, llm-agents, model-cascade, numpy, observability, prompt-caching, python, sandboxing