ship it
Pick the workflow that matches your mess.
Every use case above installs the same way: one curl, one binary, under a minute. Ringlet is open source under MIT.
use cases
What people actually do with Ringlet.
Ringlet is one CLI for every AI coding agent. Here's how that plays out in practice — each is a real workflow built from profiles, provider switching, cost tracking, hooks, and sandboxed remote sessions. No invented benchmarks, just what the tool does.
Multiple agents, one machine
Developers who use more than one AI coding CLI
Every agent CLI wants to own a dotdirectory — ~/.claude, ~/.codex — and they collide. Ringlet gives each agent its own profile: an isolated HOME, credentials, history, and MCP config, so five agents coexist on one machine with zero cross-contamination.
Read the workflow →Switch providers per project
Teams optimising cost or routing agents through a gateway
Anthropic-shaped agents (Claude Code, Droid, OpenCode) can run against MiniMax, OpenRouter, or any Anthropic-compatible proxy. Ringlet binds a profile to a provider and injects the right base-URL and credentials at launch — the agent's config is never touched.
Read the workflow →Cost visibility across agents
Engineering managers and FinOps
Ringlet parses the token-usage events every agent emits and writes them to a per-profile SQLite ledger. `ringlet usage` aggregates spend across every agent and provider, with CSV export for billing reconciliation.
Read the workflow →Audit agent tool use
Security-conscious teams
Ringlet's event hooks fire on pre-tool-use, tool-use, stop, notify, cost-threshold, and daily-rollup. Wire them to a shell command or webhook to log every tool call, alert on destructive shell commands, or run a pre-flight guard.
Read the workflow →Remote agent sessions
Developers running agents on remote boxes
Run the Ringlet daemon on a server and access the agent's PTY from your laptop's browser. Sessions exec inside a sandbox and the PTY is proxied over an authenticated WebSocket, rendered with xterm.js in the local web dashboard.
Read the workflow →Standardise a team
Engineering teams
Standardise on one orchestrator instead of a per-developer shell-alias mess. A shared TOML registry repo defines the team's standard profiles; every developer's machine is ready in one setup-script run, with credentials isolated per project and cost itemised.
Read the workflow →