NewsLab
Aug 28 13:44 UTC

Show HN: Talos – An AI agent with a permission kernel between model and shell (talos-agent.ch)

7 points|by kurdman_007||2 comments|Read full story on talos-agent.ch

Comments (2)

2 shown
  1. 1. kurdman_007||context
    Hi HN — maker here. I built Talos because I wanted to hand an agent a terminal without handing it my trust model. Every tool call (read, write, exec, delegate) passes a small deterministic kernel, ~645 lines of Python, that returns allow, needs-human or deny. Unattended runs can't ask, so needs-human becomes deny. The agent can never grant itself anything.

    Around that kernel: 23 gated tools, a UID-separated worker for delegated code, MCP servers confined to that worker from an operator-owned registry (no marketplace, no third-party code in the agent process), a hash-chained audit log, Ed25519-signed updates verified before anything unpacks, and a read-only live dashboard that has no approve button, by design.

    Numbers the CI enforces on every page of the site: 2063 tests, 179/179 adversarial cases, 645 kernel lines, 0 inbound ports. The site has a browser reimplementation of the policy kernel you can poke at without installing anything, a replayed real session, and an honest comparison to OpenClaw and Hermes — including what Talos doesn't have (breadth; that's doctrine, not backlog).

    Happy to answer anything — especially the parts where the design is wrong.

    Site: https://talos-agent.ch — Source (MIT): https://github.com/talos-kernel/talos

  2. 2. ericpauley||context
    Trademark C&D in 3, 2, 1...