One interception layer under every agent you support
Standardize agents the way you standardize everything else: one on-device layer, byte-exact, that every product plugs into - never a second proxy to run.
What you turn on
You provide the paved road for hundreds of developers, and agents showed up on it faster than you could pave a governed lane for them.
One layer for all agents
Claude Code, Codex and MCP route their traffic through a single on-device point; editors like Cursor connect via MCP.
Registry and discovery
Fleet Control inventories every enrolled device and surfaces the agents that nobody ever declared.
Policy as a code path
Compose Guard and Fleet rules into versioned packs, simulate them, and stage enforcement by device group.
Why it fits the paved road
No stacking tax
Every product is a stage on the same stream, so adding a capability never adds a hop or a failure surface.
Flat, stateless edge
Devices do the work and the edge stays stateless, so cost stays flat as your developer count grows.
Reversible by design
Every agent config restores byte-for-byte on uninstall, so adopting the layer is never a one-way door.
More in this view
Same spine, a neighbouring starting point.
Individual developer
Surfil sits beside the agent you already use, byte-exact, so you get lower spend, a secret firewall and memory that carries over - with nothing new to learn.
See this path →Engineering lead
Give every developer the same interception point, watch cost and risk in one pooled view, and roll out guardrails on evidence instead of on a mandate.
See this path →Security engineer
Zero-trace by construction, fail-closed enforcement and offline-verifiable evidence - the posture that turns an agent ban into a governed, reviewable rollout.
See this path →Turn on the first stage today
The install is reversible byte-for-byte, and the first signed receipt arrives after one normal week of traffic.