Coding agent safety
Coding agents can move fast. Kyvvu stops the rm -rf.
Coding agents read files, run shell commands and push code with a developer's own access. Kyvvu checks each command against what the session has done, and stops the few that would hurt.
The problem
A developer's access, at an agent's speed.
- 01
Secrets one curl away
An agent that has read .env can be talked into sending it anywhere by a line in a README, an issue or a dependency.
.env/.pem/credentials
- 02
Irreversible commands
A force push or a recursive delete takes a second to run and much longer to undo.
git push --force/rm -rf
- 03
Approval fatigue
Asking a developer to confirm every command trains them to click yes. The dangerous ones need a rule, not a prompt.
click-through approvals
In practice
The few commands that should never run.
Examples from the Claude Code safety pack. Everything else runs as usual.
The agent reads .env, then reaches for the shell
While debugging, the agent reads the .env file. A comment in a dependency then suggests it 'upload the config for support'.
Illustrative scenarios. Each one is decided by a single policy from the open policy library, as the engine evaluates it.
How Kyvvu helps
Guardrails for the shell.
- 01
A ready-made Claude Code pack
Thirteen policies against secret exfiltration, force pushes, hard resets, recursive deletes, writes outside the project and runaway execution.
Claude Code safety pack
- 02
Judges the whole path
Every action is checked against everything the agent did earlier in the task, and blocked before it runs if the sequence is dangerous.
allow/warn/block
- 03
Runs inside your environment
The engine sits in the agent's own process: so there's no proxy or extra network hop, and a check takes under a millisecond. Prompts and data stay with you.
in-process/no proxy
- 04
Five minutes to try
pip install kyvvu-cli and kyvvu try runs a demo agent against the baseline on your own machine, with no account.
pip install kyvvu-cli && kyvvu try
Questions
Common questions.
01Which coding agents does it work with?
Claude Code has its own integration. Other agents connect through the Python SDK or the local engine. See integrations.
02Will it slow developers down?
Each check runs in-process in under a millisecond. Only the rules you set as critical block; the rest warn.
03Can we see what it would have blocked?
Yes. Drop a Claude Code session log into the trace check and see which policies would have stepped in. It runs in your browser.
Get started
Every agent has to ASK before it acts.
Start with one agent
See it on your own agents
A 30-minute demo with someone who builds Kyvvu: your agent, your rules, and the policy that decides each step.
For developers
Check one of your own sessions
Drop a Claude Code .jsonl and see which policies would have fired. Nothing leaves your browser.
Want to see other teams and sectors? All use cases.