Vocabulary

tide works in parallel and names each piece after the sea. The model and the interface use the same words.

≋wavea subagent
Another conversation, with its own context and tools, that hands back only its conclusion. Runs in the foreground or background, on the model and thinking level you ask for: “use waves with haiku”.
⏵currenta background process
A dev server, a build or the tests running while the session goes on. Ctrl+B sends the running command there. When it ends, the result reaches the model.
∿surfweb search
Searches with Exa, no key needed. web_fetch reads HTML pages and PDFs and returns clean markdown.
›steer, follow-uptalking to a run
A steer enters the running run at its next step: Enter while it works. A follow-up waits for it to end: Alt+Enter. Reports from currents and waves arrive as follow-ups.

What it does

Three features set tide apart. The rest is what any coding agent needs.

Sessions that survive a crash

Each session is a SQLite file. Kill the terminal mid-run and tide picks the run back up when it opens. Come back after a break and a short recap says where things stand. tide -c continues, tide -r picks one.

/goal, until it's done

Give it a goal and tide works run after run. After each one, an Opus judge reviews the work and says what is missing, until the goal is met or a cap on runs or cost is hit.

A safety-net for destructive commands

Everything runs without asking, except what is destructive or public: recursive deletes, rewriting git history, DROP, and anything that writes to Slack. Those wait for your answer, and in print mode they are blocked.

And the rest

  • Memory Say “remember this” and the fact is saved for later sessions, in the same folder as Claude Code’s memory, so the two share it. Only a short index enters the prompt; each fact is read when it matters.
  • /btw A side question mid-work, answered from the context without tools, without stopping the run or touching the history.
  • Prompt suggestions After each run your likely next message shows up dimmed; Tab accepts it.
  • Skills Folders with a SKILL.md, in the Claude Code and Pi format, from .agents/skills and .claude/skills. A project's own skills are always offered to the model.
  • MCP and Code Mode The MCP config from the project, Pi, Claude Code and its enabled plugins (Slack included), with OAuth. Tools sit behind a search, and one script can call several at once.
  • @ files Type @ in the editor to pick a file from the project and reference it.
  • /context What fills the context window, part by part, on a colour map. Auto-compaction runs before it fills up.
  • Models A Claude subscription through the Claude Code login, or any provider Pi supports. Ctrl+P switches.
  • tide update Moves to the newest release; a session says when one is out.
  • Orca In an Orca terminal, tide shows up in the sidebar with the run's state, and its tab shows a spinner while it works and » while currents run.

Principles

  1. One user. No profiles, no speculative options. A feature earns its place by being used.
  2. Light. The core is Pi Durable and pi-tui. Every feature is an extension, with a test.
  3. Native. No third-party plugins at runtime. A plugin worth having is rewritten as tide code.
  4. Pinned versions. Durable is experimental, so every dependency has an exact version.
  5. One source of truth. Skills, subagents, AGENTS.md and .mcp.json are read from where they already live.

More of what I make at pedrorobalo.com