Viewing profile — Acacian

Acacian

HN member

Building Aegis — open-source security framework for AI agents. https://github.com/Acacian/aegis

comment
Comment #47616145
LangChain, CrewAI, OpenAI Agents, Anthropic, LiteLLM, Pydantic AI, Google ADK — I went through 11 frameworks looking for basic runtime security: injection detection, PII masking, a…

Thu, Apr 02, 2026, 3:53 PM UTC
story
Show HN: I tested 11 AI frameworks for basic security – none passed
Thu, Apr 02, 2026, 3:51 PM UTC
story
Comment #47587203
Tue, Mar 31, 2026, 1:37 PM UTC
comment
Comment #47542793
[dead]

Fri, Mar 27, 2026, 2:04 PM UTC
story
Show HN: Aegis – Security framework for AI agents
Fri, Mar 27, 2026, 2:00 PM UTC
comment
Comment #47529617
[dead]

Thu, Mar 26, 2026, 12:26 PM UTC
comment
Comment #47529597
[dead]

Thu, Mar 26, 2026, 12:23 PM UTC
comment
Comment #47529590
[dead]

Thu, Mar 26, 2026, 12:22 PM UTC
comment
Comment #47529586
The base rate argument here is the right one. I maintain a solo project with 3,800+ tests and 92% coverage — zero stars for months because I never promoted it. Stars measure market…

Thu, Mar 26, 2026, 12:21 PM UTC
comment
Comment #47501877
The verification pipeline is the most valuable part of your workflow. Most people who use AI for literature reviews skip exactly that step — they trust the output and move on. What…

Tue, Mar 24, 2026, 12:52 PM UTC
comment
Comment #47501819
[dead]

Tue, Mar 24, 2026, 12:45 PM UTC
comment
Comment #47501806
[dead]

Tue, Mar 24, 2026, 12:44 PM UTC