StackMap
Subscribe

agentsight vs Tracekit

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. — versus — Flight recorder for AI agents: policy-gates every tool call before it runs, holds risky ones for human approval, and signs each action into a tamper-evident log anyone can verify offline.

The curated verdict

Both answer 'what did my agent actually do'; AgentSight observes from outside via eBPF, Tracekit sits in the tool path and can block and sign.

agentsightTracekit
Stars798734
Forks121130
LanguageCPython
LicenseMITMIT
Last activitytodaytoday
Topicssecurity, coding, localsecurity, evals
Curated connections95

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.

Tracekit — the curator's take

Use it when agents touch real systems and you must prove to customers or auditors what happened — the signer sits outside the agent's reach, so a compromised agent can't rewrite history. `tracekit audit --since 7d` over your Claude Code logs is a zero-install way to see what it would have caught. Overkill for local tinkering; it gates and records, it doesn't sandbox — pair with real isolation for untrusted code.