alt Hacker NewsI wanted to try to reproduce the research results (https://github.com/statewright/statewright#research-results) locally but I wasn't able to find the code for it, have you publish the code for running those somewhere?
The research page (https://statewright.ai/research) mentions a patent, and a "core engine";
> Provisional patent application filed: #64/054,240 (April 30, 2026). 35 claims covering state machine guardrail enforcement for LLM agent tool access. The core engine remains Apache 2.0 open source.
I'm not sure I understand what the "core engine" is if it's not the "state machine guardrail runtime" which is what the patent cover. What parts are the open source parts exactly?
I find the idea really interesting and was nodding along the way as I read what you wrote, makes sense both for the human and the agent, seems like a really nice idea that'd help, but the patent kind of makes me want to run away and not look into it too deeply.
Replies
The not-quite-Apache-2 "Fair Source License, Version 1.1, ALv2 Future License" (https://github.com/getsentry/fsl.software/blob/main/FSL-1.1-...) includes the Apache 2 patent grant. That grants you conditional permission to use the software in ways that would, without the grant, infringe upon their patent. One of the conditions is that you may not make a claim against any party that the software infringes upon any patent, or else your patent grant is terminated.
Unfortunately, the license actually in the repo is not even a not-quite-Apache-2 license. It doesn't appear to be FSL-1.1-ALv2 at all: https://github.com/statewright/statewright/blob/main/plugins.... This notably does not include the patent grant, which makes it unclear whether use of the software would infringe upon the patent.
Thanks for digging deeper and I'm happy to clarify all three aspects:
Re: Reproducing the results: the engine, agent crate and demo TUI are all in the repo. If you have ollama running with a 13B+ model, task run:bugfix reproduces the simple bugfix result end to end. What isn't published yet is the SWE-bench experiment harness (task selection, patch scoring, control runs). I need to get that out, I prioritized the end-to-end simple Claude Code plugin for the launch. The demo crate (crates/demo) contains a demo TUI which calls ollama and runs the bugfix state machine interactively with code.
Re: Engine: The core engine (crates/engine/) is the pure Rust state machine evaluator. It's what Statewright is running on the backend. JSON in => transition decisions out. Agent (crates/agent/) builds on top of it to make it useful for LLMs. That all is Apache 2.0 with no restrictions.
Re: the Patent: The patent covers the method of using state machines to constrain LLM agent tool access at the protocol layer. It's defensive, it helps protect the managed service and the idea from "being scooped" from a larger company with more personnel and resources. It's not targeted against solo developers, self-hosters or researchers.
You'll find that the portions that I've released FSL 1.1 have explicit grants which do not restrict solo developers or single team self-hosting. The code released this way becomes Apache 2 in exactly 3 years. This is not unlike what Sentry and MariaDB did. I am planning on releasing more portions as FSL 1.1, I just hadn't crossed that bridge and honestly this thing seems to have gotten popular at the moment so I thought I'd set the record straight a bit