TiDB
Technical Preview

TiDB Cloud FilesystemThe workspace your agents share

One filesystem, held by several runtimes at once, that knows what an agent leaves behind — dirty tree, new objects, test output, artifacts.

bash · tiAVAILABLE NOW
TypeScript · PythonSDK — COMING SOON
# once — install the CLI, then teach your agent to use it
curl -fsSL https://tidb.link/ti-cli-install | sh
curl -fsSL https://tidb.link/fs-skill.md >> AGENTS.md
# per sandbox — mount, resume, hand off
ti fs mount --mount-path ~/workspace
cat ~/workspace/TASK.md
echo "done: auth fix" >> ~/workspace/HANDOFF.md
Read the TiDB Cloud CLI overview

What makes it different

Three things TiDB Cloud Filesystem does that your sandbox disk can't

All three exist for one reason: a distributed database sits under this filesystem, so it can promise things a disk can't.

Git-aware workspace

A resumed workspace still has its git state

The branch, the uncommitted changes, the objects the agent created — all of it comes back on resume. Not a fresh clone; the actual working state.

WHAT COMES BACK, IN ORDER

01clean tree

the committed baseline

02dirty overlay

uncommitted modifications

03object pack

objects the agent created

ti fs-git clone-git-workspace · hydrate-git-workspace · add-git-worktree

Rebuildable vs persistent

Keep what your agent needs. Drop the noise

node_modules and dist can be rebuilt anywhere, so they stay local. What can't be rebuilt — test results, failure logs, patches — is what persists.

THE SPLIT, FILE BY FILE

PERSISTED

sourcelock filepatchestest resultsfailure logs

LOCAL-ONLY

node_modules.tsbuildinfodist.turbocoverage

The split follows the project's own shape, not a config file you maintain.

Any file, any format

One place for everything the agent touches

An agent's working set is never just code — it's source, uploads, datasets, test output, artifacts. One durable workspace holds all of it, instead of a repo plus a bucket plus a log shipper.

THE WORKING SET, IN ONE PLACE

app.tsxupload.pdfdataset.csvjunit.xmlbuild.logpatch.diff

The same path from CLI, IDE, agent and CI — one namespace.

Proof at scale

Agent workspace continuity, running in production

0+

file systems in production behind Kimi Work (Moonshot AI)

TiDB Cloud Filesystem holds the agent workspaces behind Kimi Work, Moonshot AI's desktop AI agent for knowledge workers — which is why the runtimes that execute those agents stay disposable.

How it works

Execution is disposable. State is not

Two planes, one namespace. Runtimes come and go above; the workspace below is addressed as a service and outlives all of them.

EXECUTION — EPHEMERALSANDBOX Aclones, edits, buildsendsSANDBOX Bcontinues the taskendsCI JOB / REVIEWERreads without mountingSTATE — DURABLEsame filesystem tokenTiDB Cloud Filesystem — one workspacesource tree · git state · uncommitted work · test output · artifacts

One coding agent task, eight steps — each leaves state the next one needs

A coding agent doesn't touch a filesystem once. It touches it at every step, and the loop ends where a sandbox volume can't follow.

01

Enter the repository

Tree and metadata arrive first; content loads on access.

metadata-first · lazy hydration

02

Search

Content grep and filename find, with build noise kept out.

fs search-file-content · fs find-files · ignore policy

03

Read context

Handler, config, test and failing log arrive as one batch.

inline small files · batch read

04

Edit files

Writes land locally first; a journal keeps them recoverable.

local-first write · journal · async writeback

05

Build and test

Rebuildables stay local. Results, logs and patches persist.

build profile · local-only overlay

06

Save Git state

Baseline, dirty overlay and new objects — modelled separately.

ti fs-git · clean tree · dirty overlay · object pack

07

Checkpoint

Layer commands are in the CLI — not yet a preview guarantee.

fs create-layer · create-layer-checkpoint · rollback-layer — preview, not guaranteed

08

Hand off

The next runtime opens the same workspace. Same token, no mount required.

filesystem token · one namespace · fs read-file, mountless

Where it fits

Start with the boundary your state has to cross

You're in the right place if —

01TIME
SANDBOXENDSTASK STILL RUNNING

A sandbox or ephemeral job ends before the task is done.

02SETUP
REPORUN 1RUN 2RUN 3

Each run clones and prepares the same repository again.

03CONCURRENCY
AGENT 1AGENT 2AGENT 3ONE WORKSPACE

Several agents need the same repository or document set at once.

04PORTABILITY
E2BMODALCILOCALTHE SAME WORKSPACE, FOLLOWED ACROSS

Work moves between E2B, Modal, Daytona, CI or a local tool.

Several kinds of storage persist real work.
Which one is right depends on what has to survive, and what it has to cross.

WHAT YOU NEED TO KEEP

USE

A durable disk attached to one workload

Block storage

A shared POSIX filesystem for compute clients in one cloud

Network file storage

Objects, artifacts, datasets, backups or archives

Object storage

Analytics over large tables, or an AI data workflow

TiDB Cloud Lake

Committed source history, branches and merges

Git hosting

What an agent remembers across conversations

Agent memory

Snapshots and forks of work inside one sandbox platform

Platform-native persistence

One active working directory crossing runtime, session, agent or reviewer boundaries

TiDB Cloud Filesystem

Hands-on lab

Try it in a real sandbox

A guided, 120-minute lab using a virtual machine.

Straight answers

What TiDB Cloud Filesystem is, and what it isn't yet

A durable working directory for coding agents. A runtime uses normal file operations, while the workspace stays available beyond that runtime's lifecycle — so the next session, sandbox, agent or reviewer opens the same workspace instead of rebuilding it.

Get started

Nothing to rebuild. Everything to build on

Write from one runtime. Let it end. Reopen the workspace from another and check that the second run continues from the first. That's the whole test.