8 projects
smriti-cache
Semantic and exact caching for LLM calls — cut costs by catching duplicate and similar prompts.
yajna
Unified pipeline orchestrator — fluent builder API for composing agent execution pipelines.
vyavastha
Environment, secrets, and runtime config management for LLM agents
smriti-agent-cache
Semantic and exact caching for LLM calls — cut costs by catching duplicate and similar prompts.
avastha
Persistent state management for LLM agents across sessions
margadarshak
Production request routing for multi-agent systems
agent-pipeline
Unified pipeline orchestrator — fluent builder API for composing agent execution pipelines.
agent-retry
Zero-dependency Python library for resilient LLM agent calls — exponential backoff, jitter, fallback chains, and dead letter queues.
