top for your coding agent. Watch every model call, tool call and dollar your
agent spends, live.
Claude Code · OpenCode · Codex · IBM Bob · Pi · any agent that can use an HTTPS proxy. One binary on macOS or Linux. No Kubernetes, no account.
curl -fsSL https://www.rossoctl.dev/cortex/install.sh | shThen, in a new terminal:
agentop configure claude-code enable # once — or opencode, codex, bob, pi
claude # start (or restart) your agent as you always do
agentop observe # in another terminal: watch it liveNext: Getting started. It shows what you should see, how to read the screen, and how to undo it.
Setup asks once before changing anything. If something looks wrong, agentop doctor
names the fix. To move to a newer release later, run agentop update. Can't reach
rossoctl.dev? The same script is in this repo.
Used your agent before Cortex? agentop import adds its past sessions and their
cost from the transcripts on disk. Run agentop import --dry-run first to count
them. See Importing agent history.
See where your tokens go. Every session's tokens, cost and context fill, live. Open one to read the whole conversation, and the tool list it re-sends every turn.
agentop observe
agentop cost --window month --by agentSwitch any agent to another inference server. Provider down, or your team has its own gateway? Point the agent at another server without changing the agent's settings: a LiteLLM gateway, a provider's API, or a model on your own machine.
agentop server add work https://llm.example.com --main opus --helper haiku # once; asks for the key
agentop server use work --agent claude-code # new sessions go thereAfter the add, you can also switch in agentop observe: press A for the
agents, then S on one.
Guides: inference servers · pricing
Your agent uses Cortex as its HTTPS proxy. Cortex decrypts the traffic with a CA made on your machine, runs it through a pipeline of plugins, and sends it on re-encrypted. Running Cortex covers each piece.
| Agent | Connect it | |
|---|---|---|
| Claude Code | agentop configure claude-code enable |
Guide |
| OpenCode | agentop configure opencode enable |
Guide |
| Codex | agentop configure codex enable |
Guide |
| IBM Bob | agentop configure bob enable — the editor and the bob shell command both |
Guide |
| Pi | agentop configure pi enable |
Guide |
| Any other agent | agentop exec -- <command> |
Guide |
status and disable check and undo each one.
- Loopback only. Cortex contacts the servers your agent asks for, or the one you
route it to. Its own calls: LiteLLM's public price list, hourly
(
pricing.bundled: falseturns it off), and the model list of any server you add. - Your own CA, created locally in
~/.cortex/ca. Never added to a keychain by Cortex. - Bad certificates aren't intercepted. When a server's certificate fails, Cortex leaves that connection encrypted end to end.
- Read-only until you turn on pruning, server routing or an enforcing script.
- History on disk in
~/.cortex/sessionsand~/.cortex/cost.agentop uninstallremoves Cortex;--purgealso deletes~/.cortex.
The same binary runs as a Kubernetes sidecar: a verifiable identity per workload, the right credentials for each downstream call (AuthBridge), guardrails, egress control and spend caps. Start with Running Cortex in Kubernetes.
The same binary also runs on a remote machine — a VM, a home server, a pod — with
agentop connecting over an encrypted tunnel. See
Running Cortex on a remote machine.
Getting started · Using agentop · Troubleshooting · All docs
agentop reference · plugin catalog · script plugins · policy in praxis mode · install stats (from GitHub's download counts, no telemetry)
Something broke? Tell us with the Laptop feedback form under new issue, or on Slack. A half-finished install with the error pasted in helps more than a polished report never sent. To contribute, see CONTRIBUTING.md; to report a vulnerability, SECURITY.md.
Licensed under Apache 2.0.