--- title: AcceptLabs emoji: ⚖️ colorFrom: blue colorTo: yellow sdk: static pinned: false --- # AcceptLabs Open-source infrastructure for governing agentic systems. We work on a simple question: when an AI agent acts, who authorised it, and can you prove it afterwards? Most of the conversation around agent safety focuses on what models *can* do. We focus on what they're *permitted* to do, at runtime, with evidence. ## MIDAS Our primary project is **MIDAS** — an authority governance engine that treats decisions as first-class objects. Where policy engines like OPA answer *"is this allowed?"*, MIDAS answers *"does this agent have the authority to execute this decision, in this context, right now?"* — and produces a signed audit envelope so the answer is verifiable later. Built in Go with a Postgres backend. Designed to sit alongside existing policy and identity infrastructure rather than replace it. - Repository: [github.com/accept-io/midas](https://github.com/accept-io/midas) - Written in Go, Postgres-backed - Complementary to OPA and similar policy engines ## What we publish here This Space will host model artefacts, evaluation datasets, and demos related to agent governance — including reference workloads for testing authority boundaries, drift detection benchmarks, and worked examples from the broader MIDAS ecosystem. ## Get involved - Issues, PRs, and design discussions: [github.com/accept-io/midas](https://github.com/accept-io/midas) - We engage actively in technical discussion on agent governance, runtime decision systems, and enterprise architecture for AI --- *AcceptLabs maintains MIDAS as an open-source project under the [accept-io](https://github.com/accept-io) GitHub organisation.*