HN user
Multi-agent orchestration is where permissions become critical. Who can use which agent? What can each agent access? I'm building Pinchy (https://heypinchy.com) for exactly this: enterprise governance layer on OpenClaw with RBAC and audit trails. AGPL, self-hosted.
Similar problem space, different approach. I'm building Pinchy (https://heypinchy.com) — self-hosted and AGPL instead of managed SaaS. Key difference: plugin permission layer so agents get scoped tools instead of raw access. Both valid approaches for different use cases. (Disclosure: my project.)
Same experience. The productivity gain is real. The one thing I couldn't solve: using it with a team. Who can use which agent? What can each agent access? Started building Pinchy (https://heypinchy.com) — enterprise layer on OpenClaw with RBAC and audit trails. AGPL, Docker Compose. (Disclosure: I'm the builder.)
The governance gap mentioned in several comments here is real. I'm a daily OpenClaw user and started building Pinchy (https://heypinchy.com) to solve this: AGPL-licensed enterprise layer with plugin permissions, RBAC, and audit logging. Self-hosted, offline-capable. Very early stage — building in public. (Disclosure: my project.)
It really depends on your setup. Obviously, the more complex your application and the more tests you write, the longer it will take to run your test suite.
We use Guard to run only a limited subset of tests that’s related to what we’re implementing at the moment. I will probably cover Guard in a future blog post.
There are several other techniques to speed up your tests like running them in parallel or reducing database access. I personally can live with 1:27, but once it starts to annoy me again I will definitely investigate further methods and write a blog post about it.
How is your test setup? And what are your tricks to get around speed issues?