Birbla

Join the discussion

Write your take first — we'll ask for email only when you're ready to publish.

Sign in
  • Hacker News
  • How will credentials be injected via Gateway for each user ? If we have 5 users with one gateway, how it knows whose github credential to inject ?
    by Jayakumark
  • You can define different profiles that are associated with different credentials. Take a look here https://clawpatrol.dev/docs/credentials/#single-credential-t...
    by rough-sea
  • really interesting work! i am curious how you handle rule configuration for different protocols such as Postgres or ssh. Thanks for open-sourcing it under MIT.
    by Hans_Cui
  • There's a plugin API https://clawpatrol.dev/docs/plugins/
    by rough-sea
  • Seems like a more general solution to a Tesla API Firewall that i was thinking about. My idea was to use some kind of gateway/firewall LLM to check commands that another agent would send to the Tesla API.
    by thatsit
  • I wonder why u used go? i thought Deno would use to rust/ts. is it because of ecosystem? i've touched some agent guardrails. and i used python
    by hyde0395
  • Not sure why I would put another software to check that the agent doesn't do "SQL writes", rather than providing them... with a read-only account?

    It looks like those projects are trying to reinvent service-accounts and permissions... Just define the permissions for each of your APIs, and provide only endpoints to these (through MCP or whatever) to your agents...

    by oulipo2
  • It's not about enforcing read-only - we want agents to do destructive things. Like rebooting a pod, rolling back a deployment, etc.

    Plus a lot of these services are reached by tunneling through something else. We tunnel into k8s where it has dangerous credentials.

    We also don't want to define MCPs for everything. The principle is that the agent doesn't need code changes, including skills/MCPs - it just accesses systems.

    Claw Patrol lets us give agents more access because it's watching everything at the wire. `kubectl delete pod foo` waits for slack approval, SELECT on env_vars runs through an LLM judge to check if it actually returns secret data. For our setup this is security policy that is a single file, checked into git, that gates access across 14 k8s clusters, clickhouse, postgres, a dozen other HTTP APIs.

    by rough-sea
  • The product looks great and I'm really interested in trying it out. Very cool, congrats on shipping! Also...as a parent of young kids: this name made me laugh out loud. The OG image on the marketing site is a fun easter egg.

    For those here without young kids in their life: https://en.wikipedia.org/wiki/Paw_Patrol

    by mmcclure
  • This is very interesting. I build something like this but native to claude code and something that focus on just logging the violation. My question is if you are terminating a process with in the workflow will that about all other things that executed before. anyway would love your feed back on this https://github.com/varmabudharaju/agent-pd
    by varmabudharaju
  • *abort
    by varmabudharaju
  • claw patrol runs on the network level. There’s no process being terminated - HTTP/SQL/etc are rejected based on rules that you define. it’s resilient to the agent making changes to its own hooks or bypassing a local sandbox.
    by undefined_void
  • Nice library and fast Go code, which is nice to know. I'm solving the similar problem, but on different level. The agentic runtime (Go too) I'm developing, applying safety guards on different layers, including redaction and compression plugins. Do you only block the agentic request or you can redact it in the middle? How do you solve LLM caching problems? What your agent see when it's request is blocked? Does it try to reformulate the request or just stops?
    by denn-gubsky
  • Nice work shipping this.

    Disclosure: author of a related tool here. I have create agent-vault-proxy for a very similar reason. It also can help keep credentials out of the agent process. The agent gets a placeholder, the proxy swaps in the real secret in transit.

    I read them as complementary: action firewall in front, credential broker behind. https://github.com/inflightsec/agent-vault-proxy

    by radku
  • That’s great! IIUC Agent vault is an HTTPS proxy whereas Clawpatrol is a WG/Tailscale exit node so it can handle other protocols like Postgres and SSH without processes co-operating via HTTP_PROXY
    by undefined_void
  • This is a really cool library to look at even if you aren't running openclaw directly.

    Lots of good concepts to seek inspiration from.

    1. process-scoped egress policy

    2. policy-as-code

    3. explicit approval classes

    4. normalized network/ guardrail receipts.

    5. structured guardrail outcomes

    6. centralized decision rules

    by Apylon777
  • Thanks! Don't forget wire level protocol parsing - this is important because agents usually can spawn subprocesses and if they have postgres credentials, you're just one psql call away from disaster if you only have MCP/HTTP proxies in place.
    by rough-sea
  • I think this sounds very cool! It sounds similar to Agent Vault (github.com/Infisical/agent-vault) but with an added feature of having security policies for denial/human-in-the-loop of traffic based on the contents of requests?

    The nice thing about Agent Vault is the encryption of credentials and other ways they handle making sure those don't leak from storage. I suppose you could potentially wrap the two in layers as well (agent -> Claw Patrol -> Agent Vault -> external network)

    EDIT: looking at some of the comments, it sounds like Claw Patrol can work with protocols beyond HTTP/S, so potentially covers more surface area than AV

    by jameslk
  • Yes works at the wire level, not http. Have a look at the example config file https://github.com/denoland/clawpatrol/blob/d2e531d8cb0f1a3a...

    Claw Patrol holds credentials - so probably doesn't make sense to layer with AV - but it's true that AV has more sophisticated storage of creds (eg using 1p)

    by rough-sea
  • Great name by the way, as someone who's been forced to watch the show by cousins.
    by satvikpendem