Back to browse
Durable, asynchronous LLM workflow engine in Rust

Durable, asynchronous LLM workflow engine in Rust

by rescrv·Jun 9, 2026·1 point·0 comments

AI Analysis

●●SolidBig BrainNiche Gem

Continuation-passing durability with live/batch switching, but LangGraph and Temporal already own this space.

Strengths
  • Explicit continuation-passing style makes workflow state serializable and inspectable.
  • Live to batch execution switching without code changes is genuinely useful for cost optimization.
  • Leaves prompts, tools, and storage in user's code instead of imposing framework opinions.
Weaknesses
  • v0.1.0 built over a weekend with OpenAI support not yet implemented.
  • Durable workflow orchestration is crowded with Temporal, LangGraph, and Prefect.
Target Audience

Rust developers building AI agent systems or workflow orchestration

Similar To

Temporal · LangGraph · Prefect

Post Description

I built this over the weekend to scratch a personal itch. Might be useful to others. Supports transparently switching live to batch without code changes.

Similar Projects

Infrastructure●●●Banger

Sayiir – A simple durable workflow engine (Rust core, Python/Node.js)

Checkpoint-based recovery beats determinism constraints; embed without separate server, unlike Temporal/Airflow.

Big BrainDark HorseSolve My Problem
ybsoft
103mo ago