Every agent works from the same decisions
Claude Code, Cursor and Codex read one memory, so they give the same answer about the same code.
One memory every coding agent reads and saves to
Ditto gives Claude Code, Cursor, Codex and your other agents one shared memory of your project. Every session starts from what was decided, and what an agent learns is saved for the next one.
I'm starting the billing refactor. What did we decide about proration?
Prorate upgrades daily and bill downgrades at renewal. Annual plans are excluded, and Codex saved that edge case on 18 Sep.
From memory · 3 sourcesClaude CodeSession · 16 SepCodexSaved edge case · 18 SepGitHubPR #418 · 19 Sep
Agents give different answers about the same code because each works from its own notes.
Rework plus regression riskRestart a session and the agent has lost what it knew an hour ago.
Files re-read and decisions re-madeA known gotcha gets hit again because the fix was never saved where agents look.
Debugging time spent twiceYou paste the same background into every new session before the real work starts.
Tokens and minutes wasted up frontOne agent changes what another built because neither knows what the other did.
Double spend and broken buildsWhen work moves between agents or people, the details that matter drop out.
Wrong output shipped to clientsEvery agent you run reads from and saves to the same memory of your project.
Claude Code, Cursor and Codex read one memory, so they give the same answer about the same code.
A new or restarted session opens with the decisions and progress already saved.
When an agent solves a tricky bug, the fix is saved where every agent looks first.
Every session starts with the project's context, so the first prompt is the real task.
Before an agent edits code, it reads what the other agents did and why.
What an agent worked out is saved with the task, so the next agent or person starts from it.
Three steps, then every session starts with your project.
Connect Claude Code, Cursor or Codex over MCP, or OpenClaw and Hermes through the CLI.
It saves decisions, reasons and progress from your sessions, PRs and threads, and keeps them current.
Each agent searches the memory before it starts and saves what it learned when it finishes.
Connect Ditto once and stop re-explaining your work in each new session. Each tool searches the same memory and can save to it.
Ask in Claude Code and get what your team decided, with sources.
Explore Ditto for Claude Code →CodexAsk in Codex and get what your team decided, with sources.
Explore Ditto for Codex →CursorAsk in Cursor and get what your team decided, with sources.
Explore Ditto for Cursor →GitHub CopilotAdd Ditto as an MCP server and Copilot searches and saves the same memory.
Explore Ditto for GitHub Copilot →Gemini CLIAdd Ditto as an MCP server and Gemini CLI searches and saves the same memory.
Explore Ditto for Gemini CLI →OpenCodeSign in to Ditto from OpenCode and every session starts from the same memory.
Explore Ditto for OpenCode →WindsurfAdd Ditto as an MCP server and Windsurf searches and saves the same memory.
Explore Ditto for Windsurf →ClineAdd Ditto as an MCP server and Cline searches and saves the same memory.
Explore Ditto for Cline →AntigravityAdd Ditto to Antigravity's MCP config and its agents start from the same memory.
Explore Ditto for Antigravity →Your code and your project memory stay yours, and every agent works inside the limits you set.
Ditto's memory harness and integrations are open source.How Ditto handles your data
Your plan covers capacity and features. Credits pay for variable usage across AI, voice, tool actions and storage beyond your included allowance.
New plan preview. Rollout is in progress; check the offers available in your account before purchasing.
Explore Ditto with no card needed.
Plan includes:
Add a $5 initial deposit for more usage, with no subscription. Net credits follow the disclosed payment-fee reserve.
Paid chat connections, Ditto Review and remote control unlock after the deposit settles.More room for your everyday work.
Plan includes:
Shared capacity and credits for you and your team.
Plan includes:
A custom Ditto build for your business: our team writes the spec, builds it and supports it.
Coding agent memory lets an agent keep what it learns about your project and use it in later sessions. Ditto keeps one memory that every agent you connect can search and save to.
Claude Code, Cursor and Codex connect over MCP. OpenClaw and Hermes connect through the Ditto CLI. Any other MCP client can connect too.
A rules file holds what you wrote down and stays the same until you edit it. Ditto saves decisions and progress as agents work and keeps them current, and every agent reads the same memory.
Yes. What one agent saves, the others you connect can read, so Cursor can use what Claude Code learned.
Yes. The memory lives in Ditto, not in one model or tool, so a new model starts from the same project memory.
Yes. Claude Code keeps memory for its own sessions. Ditto adds one memory that Claude Code shares with your other agents and tools.
No. Ditto doesn't train on your code or your memory. When an AI tool reads your Ditto memory, that provider's policies apply to what it reads.
The new plans are Free, Flex with a $5 initial prepaid deposit and no monthly base fee, Plus at $19/month, and Pro at $97/month. Usage is prepaid with credits. See the pricing page for plan details and rollout availability.
Connect Claude Code, Cursor or Codex in a few minutes. Start on the free plan, then prepaid usage is available with Flex.
Read-only by defaultNo card to start