Durable, asynchronous LLM workflow engine in Rust
Continuation-passing durability with live/batch switching, but LangGraph and Temporal already own this space.

LLM code execution via Lua REPL reduces token costs vs. tool-calling loops.
Rust developers building LLM applications; anyone reducing LLM inference costs
Anthropic MCP · Cloudflare Workers AI
Continuation-passing durability with live/batch switching, but LangGraph and Temporal already own this space.
Firecracker MicroVM isolation beats Copilot Workspace on security, but category's saturated.
Sandboxed Rust execution for AI agents, but Devin already owns this category.
Pre-execution budget reservation stops runaway agents before they burn $200.
VLCs over VLAs: LLMs write Python code against live robots instead of predicting actions.
Single Rust binary, zero runtime deps, self-extending skills, local or routed LLMs.