agentsight vs failproofai
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 — Observability plus policy enforcement for agent harnesses: records every run across 12 harnesses (Claude Code, Codex, Cursor, Hermes…) and blocks dangerous tool calls with 39 built-in policies.
Both watch what a coding agent does on the machine. AgentSight observes from the kernel with eBPF — any binary, no hooks, no blocking; Failproof AI hooks the harness and enforces policies before a tool call runs. Observe-everything vs enforce-what-you-hook.
| agentsight | failproofai | |
|---|---|---|
| Stars | 671 | 2.1k |
| Forks | 101 | 444 |
| Language | C | MDX |
| License | MIT | NOASSERTION |
| Last activity | today | yesterday |
| Topics | security, coding, local | security, coding |
| Curated connections | 5 | 5 |
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.
failproofai — the curator's take
The one to install the day an agent first runs `rm -rf` or force-pushes: hooks into ten coding CLIs plus the Hermes and OpenClaw gateways, records sessions to a local dashboard on :8020, and enforces policies *before* the tool call runs — sanitize API keys, block .env reads, sudo, terraform/kubectl, destructive SQL, direct pushes to main. Custom policies are a JS file in .failproofai/ that returns allow/deny/instruct; packs are versioned GitHub repos. NOT a tracing platform for agents you built from code (the Python SDK gives tracing but enforcement needs a hook in your runtime), and note the source-available licence and optional cloud — local works without an account.