Provides transactional intelligence for AI agents, enabling safe tool execution with pre-flight invariant checks, sub-second filesystem snapshots/rollback, causal tracing, belief contradiction detection, and 15 native MCP tools for Claude Code.
Universal verifiable recovery for long-running AI agents with semantic checkpoints, idempotent action ledger and hash chained log as a deny by default MCP server. Framework agnostic with adapters for LangGraph, LangChain and OpenAI plus gateway and OTel.
Safe, reversible tool execution for AI agents. It sits between an agent and its tool servers, adding contracts, dry-run planning, policy, approvals, saga execution, and rewind.
Provides durable mission state for AI agents, enabling crash-safe recovery, verified completion, and explicit reconciliation of uncertain side effects without duplicate or blind retries.
