⬢github Rust · 18 ★ +11 since we first saw it · pushed 1 d ago · MIT

trigora-dev/trigora

Durable execution for long-running AI agents and programs.

Trigora is a durable execution platform for long-running AI agents and general programs written in TypeScript, Python, or Rust. It can suspend execution across events, timers, external calls, and child programs, then recover after failure from committed continuation state instead of replaying completed execution history, using its Transparent Continuation Checkpointing (TCC) approach. It includes a CLI, local runtime, and a managed cloud offering.

Why now: It was featured in a Show HN post highlighting its 'durable execution without history replay' pitch, positioning it as an alternative to replay-based workflow engines for AI agent workloads.

Who it is for: Developers building long-lived AI agents or workflows that must survive failures, wait on humans or events, and run for hours or days.

durable-executionai-agentsrustworkflow-enginefault-tolerance

ai-agentscheckpointingdeveloper-toolsdistributed-systemsdurable-executionfault-tolerancepythonrusttypescriptworkflow-engine

Open on GitHub →

Stars over our 67 snapshots: 7 to 18, since 16 h ago.

Where people talked about it

API: https://socialmediatrends-api.osmike.com/v1/repos/trigora-dev/trigora