Turnlog

Roadmap

What’s next — and what never will be.

Turnlog is actively built. This page is the honest version of where it’s going: order, not deadlines. Nothing here is a promise, and anything already released lives on the changelog instead.

The last block is the one that matters most. For a tool whose whole claim is that your sessions stay on your machine, what it refuses to build is part of the product.

01

Shipped

The highlights of recent releases, one line each. Full changelog →

  • Agent memory over MCP

    One command registers your history as a read-only MCP server, and Claude Code can query how past work was done without leaving your machine.

  • Search operators and saved searches

    Compose tool:, is:error, project:, model:, and date filters with free text — in the UI, the terminal, and over MCP — and keep the ones you re-run.

  • Cross-session file history

    Pick a path, read every change any session ever made to it, in order, with jumps back into the session that made it.

  • Resume chains stitched into one conversation

    Resuming a session no longer scatters it across near-duplicate rows; the parts are linked and the replay navigates between them.

  • HTML export with redaction

    Any session leaves as one self-contained styled page, optionally scrubbed of keys, tokens, emails, and home paths first.

  • Index health panel

    What was indexed, what could not be read, and how many record types the parser did not recognise — format drift as a number on screen rather than silent loss.

02

Next

What is actually being worked on. Listed in rough order of intent — not a schedule, and any of it can be overtaken by a better idea or a bug report.

  • 01

    Understand more of what Claude Code writes

    Newer record types still land in the index as “unrecognised”. Teaching the parser about them turns raw rows into readable ones — including the session titles Claude Code generates for itself, so sessions arrive already named.

  • 02

    A share panel, with redaction in the flow

    One place to choose the format, see exactly what redaction will scrub before it runs, and export part of a session instead of all of it.

  • 03

    Pick up a found session in one copy-paste

    You searched, you found the session, you want to keep going in it — that should be a button that hands you the exact resume command, not a hunt for the project directory.

  • 04

    Spend that understands chains

    Now that resumed sessions read as one conversation, the cost view should total them that way too.

03

Later

Real directions, paced by whether people actually ask for them. Nothing here is started.

  • 01

    Other coding agents

    Turnlog’s internal model was built provider-agnostic on purpose: a session, its turns, its tool calls. Adapters for Codex CLI, Gemini CLI, OpenCode, and Cursor are the natural next surface, and each is its own piece of work rather than a switch to flip.

  • 02

    One timeline across all of them

    That’s the reason the copy says “for Claude Code” as a qualifier and not as an identity. The day a second adapter ships, the interesting thing isn’t the adapter — it’s one searchable history of every agent you have ever pointed at a repository.

04 — Never

The list that doesn’t move.

Every item below would make Turnlog more valuable to build a business on, and every one of them would break the single promise the tool makes. They are not “not yet”. They are not on the list at all.

Telemetry

No usage pings, no crash reporting, no “anonymous” counters. The moment a local tool measures you, “it never leaves your machine” needs an asterisk — and asterisks are how trust dies.

Accounts

Nothing to sign up for, no license key, no login wall. Turnlog reads files that are already yours; asking who you are to do that would be theatre.

A cloud

No hosted version, no sync, no uploading an index “for convenience”. Your prompts and diffs are the most sensitive text on your disk and the safest place to keep them is where they already are.

Team sync

No shared workspaces, no seats, no org dashboards. Aggregating a team’s sessions requires a server that holds everyone’s history — the exact thing this tool exists to avoid. Sharing stays a file you export and send.

“Insights” dashboards

No productivity scores, no leaderboards, no AI summary of how you work. Turnlog reports what happened and what it cost; anything that grades a developer from their session log is a management product wearing a developer tool’s clothes.

Selling anything

No paid tier, no pro features held back, no upsell in the UI. It started as a $19 product and shipped MIT instead; every version stays installable from npm forever.

MIT · no accounts · no telemetry · no cloud · nothing for sale