StackMap
Subscribe

Adrian vs agentsight

Runtime security for AI agents: watches actions AND reasoning traces to catch prompt injection, tool poisoning and out-of-remit behavior — blocking before the action lands. SDKs + Claude Code plugin. — versus — System-level observability for AI agents via eBPF and TLS tracing: correlates prompts and model calls with the processes, files and network the agent actually touched — no SDK, no proxy.

The curated verdict

Both look for agents misbehaving at runtime. Adrian inspects actions and reasoning for injection and tool poisoning; AgentSight audits the actual system effects — which files changed, which services got requests — from outside the agent.

Adrianagentsight
Stars556671
Forks91101
LanguagePythonC
LicenseApache-2.0MIT
Last activity16 days agotoday
Topicssecurity, agentssecurity, coding, local
Curated connections75

Adrian — the curator's take

The interesting bet is judging reasoning traces, not just tool calls, against a working model of the agent's remit — the OpenAI/DeepMind-cited combo that catches what injection-trained classifiers miss. Know the deployment shape: the quickstart routes your agent's actions AND thoughts through their managed dashboard; self-hosting exists but is the longer path. Young (★460) and a startup's wedge product — run audit mode first and measure false positives on your own traffic before trusting block mode in production.

agentsight — the curator's take

Use it when the agent is a closed CLI (Claude Code, Codex, Gemini CLI, OpenClaw) and its own logs don't explain a failure: AgentSight watches at the kernel boundary, so it sees the model traffic *and* every exec, file write and outbound connection, and ties them together. That's the layer LangSmith-class tools can't reach without owning the app code. NOT for prompt/eval-level tracing of an app you wrote (use an OTLP tracer), and it's Linux-with-eBPF: on macOS you're out of luck. Not an enforcement tool — it observes and advises, it doesn't block.