Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Self-hosted company OS, Claude Code and Codex agents in departments

github.com

Post reply on HN
Print view View original

21–30 of 30 posts

Re: Show HN: Self-hosted company OS, Claude Code and Codex agents in departments

#23

Post by dimitrismrtzs »

NimadFlow wrote: post #17

If you organize agents by department, who verifies an agent's 'completion' report? In my experience, reviews using the same model rarely caught its own mistakes—only a different model or execution receipts (rc·sha256·stderr) caught them. How are you handling this here?

OtoDock does not verify a report by itself, but you can set it up in your installation. A delegated agent runs as a normal session on the platform, so the whole run is persisted, every tool call and its output, and both the delegating agent and a human can open that session instead of trusting the summary. Delegation can also pin a different model or engine per lane, so the reviewer can run on Codex or a local model while the worker ran on Claude.

For the deterministic part I use scripts, not agents. For example to publish a new version I have a script with all the gates, it runs the tests and the scanners and refuses the export if anything is off. The agent cannot declare a release done, the script does.

Re: Show HN: Self-hosted company OS, Claude Code and Codex agents in departments

#24

Post by dimitrismrtzs »

nerdsnipe wrote: post #18

Looks great. I didn't like the paperclip system with my main issue being that agents would go over daily budgets all too often. Looking forward to giving this a try.

Glad you like it. If you test it out I would love any feedback!

Re: Show HN: Self-hosted company OS, Claude Code and Codex agents in departments

#26

Post by NimadFlow »

dimitrismrtzs wrote: post #23
NimadFlow wrote: post #17

If you organize agents by department, who verifies an agent's 'completion' report? In my experience, reviews using the same model rarely caught its own mistakes—only a different model or execution receipts (rc·sha256·stderr) caught them. How are you handling this here?

OtoDock does not verify a report by itself, but you can set it up in your installation. A delegated agent runs as a normal session on the platform, so the whole run is persisted, every tool call and its output, and both the delegating agent and a human can open that session instead of trusting the summary. Delegation can also pin a different model or engine per lane, so the reviewer can run on Codex or a local model…

[dead]

Re: Show HN: Self-hosted company OS, Claude Code and Codex agents in departments

#30

Post by coder-pm »

dimitrismrtzs wrote: post #14
madamelic wrote: post #12

I have been playing with something similar and I see these types of projects all the time. My criticism of things like this is that they seem to rely heavily on the ~*~magic~*~ of LLMs to do everything and try to paper over gaps with major hand-waving on everything beyond "agents do everything" when in reality, the most critical part is agents NOT doing much and relying on 'boring' deterministic backbones in an autom…

I agree with your points, and that is how it is built. The backbone in OtoDock is deterministic code, the model only runs inside a session. Schedules are cron, triggers are webhooks, permissions are a fail closed gate per tool, cost limits are set per user and per agent, and delegation between agents is configured from the admin and the agent managers, an agent cannot change any of that. Agents only see the tools and…

[dead]
Post reply on HN