Finally, an open-source runtime security layer for your agent harnesses. AI agents can call tools, run shell commands, modify files, and interact with production systems. But when something goes wrong, teams often have to reconstruct what the agent actually did from scattered logs after the fact. Agent Beacon is... built to change that. It runs locally and records agent activity as it happens, including: → Tool calls → Shell commands → File changes → Approval decisions → Session and harness context The useful part is that it normalizes all of this into the same event format across 23+ agent harnesses. So instead of writing different detection logic for Claude Code, Codex, or another harness, security teams can reason about the underlying action itself. A command executed is a command executed, regardless of which harness produced it. Beacon also records how confidently an event was captured. An action can be directly observed from the runtime or inferred from indirect evidence. That matters when you start writing security rules against this data. For example, you can detect when an agent reads an environment variable, modifies a sensitive file, executes a suspicious command, or performs an action without the expected approval. And the detection happens while the session is still unfolding, not days later during incident reconstruction. Everything runs locally by default. You can inspect sessions through the dashboard, write your own detection rules, or forward the same normalized events to tools like Splunk, Datadog, Elastic, Sentinel, or CrowdStrike. Beacon GitHub: (don't forget to star 🌟) I also wrote a detailed article on the same, covering how important runtime security is and how to build it for your agent harnesses. The article is quoted below.show more

Check out Beacon and let us know what you think:

the agent can touch production, but at least the postmortem can stop asking which terminal tab had the keys.

So basically a flight recorder for AI agents lol. Needed this badly, my Claude Code and Cursor setup has zero telemetry right now. Installing tonight

Normalizing across 23+ harnesses into one event format is the part that actually matters. Most teams write detection logic per-tool and it rots the moment someone swaps Claude Code for Codex. Confidence-tagging inferred vs observed events is the right call too, treating both the same way is how you get false positives nobody trusts.

Well said @akshay_pachaar! The world needed this!

All those agent events generate a flood of data, and picking the right insight to share can waste hours. SandHive finds the right threads and lets you decide what goes online. If you found this helpful, reshare with your network. Find me →

If you cannot replay the agent’s first git call, you cannot audit the default. Steal: log `git status` before trust — not only the model output.

when a harness does something the event schema doesn't have a slot for yet, does Beacon drop it or flag it as unknown?

Agent Beacon addresses a critical gap in AI agent security.

capture confidence lets teams tune rules to evidence quality

an open-source runtime security layer for agent harnesses is overdue when agents touch shell and prod. what's the first signal teams actually look at after an incident?

normalization is the only part that survives a codex to claude swap. on podcode we ended up writing our own event format because the harness logs all looked like slightly different dialects of the same thing.

The audit trail needs tool args, policy decisions, and resulting state—not just a transcript. Otherwise replaying the incident is still guesswork.

inferred events should trigger different rules than observed ones