3 projects
routecut
Drop-in LLM cost router: classify each prompt by task class and route it to the cheapest sufficient model. Shows the dollars saved on every call.
memgov
Provider-agnostic governance layer for AI agent memory: reuse-aware decay, confidence-gated recall injection, and memory-health metrics. Governs the memory you already have (mem0/Zep/vector DB) instead of storing it.
agentcap-guard
Provider-agnostic hard dollar budgets + loop detection for AI agent runs. Stops the spend before it happens.
