clampd

no profile record

投稿

[untitled]

1 ポイント投稿者 clampd3 か月前0 コメント

Clampd-Guard – Runtime Security for Claude Code and Cursor (PreToolUse Hook)

clampd.dev

3 ポイント投稿者 clampd3 か月前0 コメント

Show HN: Clampd – Your AI agent can DROP TABLE. We block it in <10ms

clampd.dev

3 ポイント投稿者 clampd4 か月前2 コメント

clampd

3 か月前議論

[dead]

clampd

4 か月前議論

[dead]

clampd

4 か月前議論

Thanks! Yes - since OpenRouter exposes an OpenAI-compatible API, the SDK already works with it today:

  client = clampd.openai(OpenAI(base_url="https://openrouter.ai/api/v1", api_key="..."), agent_id="my-agent")

Any OpenAI-compatible provider works - OpenRouter, Azure OpenAI, Groq, Together, etc. Clampd intercepts tool calls after the LLM responds, so it doesn't matter which provider you use.

clampd

4 か月前議論

[dead]

clampd

4 か月前議論

This is the "agent with a hammer" problem. The agent is optimized to make changes, so it changes things even when it shouldn't. What's missing is a feedback loop that says "your change made things worse."

clampd

4 か月前議論

It's great to see more security critical software being built in Rust. Memory safety in crypto code is exactly where Rust shines; one use after free in an HSM and your keys are gone. How are you handling side-channel resistance?

clampd

4 か月前議論

[dead]