2 projects
tulip-agents
The safest way to build agentic AI — a full-stack, open-source agent SDK where control is native: a cognitive router picks the shape, GSAR grounds every claim, and every risky action must clear an admission gate. Proven first in the security domain.
tulip-frameworks
Drop Tulip's control runtime (admit() gate + tamper-evident audit) into the agent framework you already use — LangChain, LangGraph, CrewAI, the OpenAI Agents SDK, LlamaIndex.
