HackerTrans
トップ新着トレンドコメント過去質問紹介求人

softie123

7 カルマ登録 先月

投稿

[untitled]

1 ポイント·投稿者 softie123·4 日前·0 コメント

Show HN: Shotlist – Make your AI agent prove its work with real screenshots

github.com
4 ポイント·投稿者 softie123·18 日前·2 コメント

Show HN: Pgsemantic – Point at your Postgres DB, get vector search instantly

github.com
3 ポイント·投稿者 softie123·28 日前·0 コメント

Show HN: A police department for your Claude Code agents

github.com
11 ポイント·投稿者 softie123·先月·8 コメント

Show HN: Agent-pd – A zero-token audit log to catch rogue Claude Code subagents

github.com
6 ポイント·投稿者 softie123·先月·2 コメント

コメント

softie123
·18 日前·議論
[flagged]
softie123
·先月·議論
thats exactly what i went for. also I am keeping all the logs compressed so may be i can build something to build later
softie123
·先月·議論
Idea is not to deny permissions to everything but just keep a log on what the agents are doing thats not in line with our permissions and also you have to know what they are bypassing so we can put them in deny list later. Very useful when you spawn many agents working in parallel. This is more of an observability tool.
softie123
·先月·議論
[dead]
softie123
·先月·議論
Tested this with 40 agents doing research at the same time it worked pretty good
softie123
·先月·議論
[flagged]