AI coding tools run with your credentials.Rye is your control plane.
Every prompt that leaves a developer machine passes through Rye. Secrets get stripped. Policies enforce. Everything is logged.
Connections
Active Policies
Local supervision is active before an assistant starts.
Model API traffic has a network checkpoint.
Requests can be tied back to a real process.
Architecture
One control plane between your AI tools and LLM providers
Rye proxies every request. Prompts are scanned, secrets are stripped, policies are enforced — then clean requests are forwarded to the model.
Before / after Rye
Turn model traffic into accountable AI egress.
The interesting Rye claim is not that it has another secret scanner. Rye sits at the point where AI coding tools leave the developer workstation, so each request can be allowed, redacted, blocked, or queued for approval before the provider sees it.
- source
- 10.0.4.23
- destination
- api.openai.com:443
- method
- CONNECT
- bytes_out
- 184912
- developer
- unknown
- tool
- unknown
- repo_path
- unknown
- prompt_risk
- unknown
- provider_call
- already sent
- request_id
- rye_req_8f2c1a
- decision
- BLOCK
- reason
- policy.no_proprietary_code
- developer
- mrodriguez
- device
- macbook-eng-118
- tool
- cursor
- matched_path
- src/billing/mrr.ts
- provider_call
- not_sent
- policy_version
- synced workspace policy
Show the product state, then show the decision.
The strongest demo is a short capture: run a wrapped agent, trigger a policy, then inspect the status and decision trail. That is more credible than a feature list because the artifacts are recognizable to the buyer's security team.
A trimmed status check from the Rye CLI shows the daemon, proxy, intercept targets, and wrapped apps.
$ rye status
Daemon: running
Proxy: up
Auth: logged in
Listen: 127.0.0.1:18080
Intercepting: openai.com, anthropic.com, cursor.com, windsurf.com
Wrapped Apps:
claude active
codex activeThe decision record should answer what matched and whether the model provider ever received the request.
decision = blocked
reason = policy.no_proprietary_code
actor = mrodriguez
device = macbook-eng-118
tool = cursor
repo = payments-api
matched_path = src/billing/mrr.ts
provider_call = not_sentSecurity proof
Replace compliance promises with questions Rye can answer.
Developer identity plus the registered workstation that made the request.
Cursor, Claude Code, Codex, Windsurf, Zed, or another supervised process.
The policy decision records the rule, reason, and whether the upstream call was sent.
File path context connects the model request back to the repo area under review.
Wrapped sessions can connect model traffic to local process and file activity.
Setup path
Put Rye where the request leaves the laptop.
Developers keep their AI tools. Rye wraps the process, routes model traffic through the local proxy, and records the policy decision.
Wrap the agent
rye wrap claudeRye launches the assistant under supervision so process, device, and workspace context are present from startup.
Route model traffic
rye up --install-ca --intercept-patterns openai.com,anthropic.com,claude.com,chatgpt.com,cursor.com,windsurf.comThe local proxy becomes the control point for model API traffic and evaluates requests before they reach the provider.
Inspect decisions
rye history --last 1hRecent supervised traffic shows process attribution, device identity, destination, model, and policy decision.