Beyond Amnesic Intelligence and Single-Player Memory.
Today's models are amnesic: stateless, blank at the start of every session. The memory that covers for that, the harness's own files and skills, is single-player: stuck in one tool, for one person, with no way to share it or carry it. Common fixes both. One memory that persists across sessions, moves across every model and harness you run, and your whole team can work from. Own your memory. Rent the intelligence.
01 Where this starts
You rebuild the same context, over and over.
You build up context with an assistant in one tool, then move to a better one and start over, because what the first one knew doesn't come with you. A teammate joins and briefs their own assistant from scratch. Everyone keeps re-deriving what someone, or something, already worked out.
The harnesses aren't bare; they already keep memory, skills, and settings for you. The catch is that all of it is bound to one vendor and one person: what you build up in Claude Code can't move to Codex, and none of it can be handed to the people you work with. There's no place it lives on its own; it's just a feature of whatever tool you used last.
02 What memory is
Memory isn't a feature. It's the product.
Every harness bolts memory on as a feature of itself: Claude Code keeps its own, Codex keeps its own, each in its silo. Common makes it the product instead: one shared, synced memory you own, that any harness reads from and writes to. Pull memory out of the tool and three things that were impossible become routine:
Portability. Your memory follows you across tools. What you build up in Claude Code is there in Codex, and you can drive both off it at once. The harness becomes the part you swap, not the part your memory is trapped in.
Sharing. You hand out exactly the parts you choose: one project, a body of reference, nothing more, to a person or an agent acting for them. Access is per part, per person.
Collaboration. A whole team works from one memory. Because the layer is opinionated about how work accumulates (a shared filesystem, not scattered chat logs), the agents build on each other's work instead of re-deriving it.
To do that, Common breaks your memory into three layers, all routed through the Common Cloud. Here's each, starting with the hub:
The Common Cloud
The hub every Common routes through
It sits between your local Common, a full working copy, and everything else: your machines, collaborators, and connected sources. It mediates sync the way Dropbox does and enforces the access rules you set, per project. Background jobs run here too: the nightly dream cycle improves your memory while you sleep.
Hub
Common Knowledge
Reference memory: on-demand mirrors of the sources you reference, local and grep-able
Docs, Sheets, Gmail, Calendar, Notion, Slack, Linear: the apps a person or a small team already lives in. Pull one in and the cloud keeps a local copy current on every machine, so the agent greps it at filesystem speed instead of round-tripping a connector. Lazy by design: it mirrors only what you reach for, never your whole Drive.
Flows in
Common Ground
Working memory: the agents' own evolving work, the project's record
Strategy, findings, running state, the markdown and static HTML that accumulate as you work: the project's source of truth, not a memory file off to the side. It fixes the agent forgetting between sessions.
Flows out
Common Harness
Procedural memory: your agent's whole setup, no longer locked to one harness
Sessions, memory, custom skills, settings, and the secrets it runs with: everything that makes an agent yours, today trapped in whatever harness built it because harnesses don't interop. Common keeps it in a neutral form any harness can read, so the setup you grew in one is waiting when you open another. Secrets ride along encrypted, decrypted locally only when an agent reaches for one. The harness underneath becomes a detail you can swap.
Harness-agnostic
03 In practice
Common runs in the background; you just keep working
There's no Common app to open. You work in the harness you already use (Claude Code, Codex, Cursor), pointed at the same docs and spreadsheets as always. You auth the Common MCP once, through that harness; after that it runs underneath: Knowledge mirrors your sources down, your agent writes Ground as it works, and a daemon backs up your Harness. All of that is automatic. The decisions stay yours: who can see a project, and how hard the nightly dream cycle runs.
Common Knowledge doesn't mirror your whole Drive, or every doc you can technically open. There isn't the space for that, and a folder crammed with everything is just noise the agent has to wade through. So Knowledge is lazy: an artifact lands in Common only when you reach for it. You paste a link into your harness, or ask the agent for a specific doc, sheet, or thread. That's when it lands. From then on it stays in sync like everything else in your Common.
Say you're in a harness chat working through a launch plan and you drop in a Google Doc link. Common Cloud mirrors that one doc down into Common Knowledge, a live local copy the agent greps at filesystem speed, next to everything else you've pulled in. It reads the doc, cross-references your Ground, and drafts what you needed.
Your colleagues never leave Google Docs: they keep editing in the UI they know, and the mirror keeps your copy current, one-way or two-way if you want the agent's edits to flow back.
You linked the doc, so the cloud mirrored it down; your team keeps editing in Google Docs as if nothing changed.
On disk, it's just folders. Three names are reserved (knowledge, ground, harness); anything else at the root is a project. Knowledge flows in, Ground flows out; every project gets its own knowledge/ and ground/, plus whatever else the agent makes. The root harness/ is different: it mirrors your agent's whole setup across your machines and harnesses, private to you, secrets encrypted until an agent reaches for one.
│ ├── knowledge/mirrors land here · gdocs · sheets · email
│ ├── ground/Common Ground — md + static html your agents evolve
│ └── model/anything else the agent makes (not reserved)
│
├── q3-launch/same folders, every project
│ └── …
│
└── client-acme/→ shared with a partner, scoped
├── knowledge/
└── ground/
knowledge/ flows in, ground/ flows out, and the agent adds whatever else a project needs. Common Harness sits once at the root, keeping your whole setup portable.
04 Common features
More than a place to put things
Because your memory lives in one synced, logged layer instead of scattered files, a lot comes with it:
History & rollback. An append-only log in plain language, not raw diffs. Restore any file to any earlier version, the way you'd roll back a Google Doc.
Attribution. Every change carries the person and the agent behind it: You · Claude Code, a teammate · their agent.
Intelligent sync. When two people touch the same thing at once, an LLM merges both edits instead of keeping the last writer the way a shared drive would.
Observability. Tokens, model, harness, and who, accumulated per project, so you can see how much agent work has gone into each project.
The dream cycle. Overnight, with no session running, the cloud tidies your Ground (de-duplicating, fixing links, refiling what drifted) so you wake to a cleaner tree. Turn up the nightly budget and it does more: surfacing tomorrow's todos, spotting automations worth building, flagging what needs attention.
05 How it compares
Their memory is a feature off to the side. Yours is the product.
Other tools add memory as a feature of one app. Common's memory is the product itself: it evolves with you, and stays portable, collaborative, and sovereign while the intelligence underneath gets swapped. Here's how it compares to what people reach for today.
Alternative
What it is
What Common adds
claude-mem
Per-session memories for one user, kept local.
Owns the substrate they derive from, synced across people and machines.
Agent-memory APIsMem0 · Zep · Letta
A store the agent calls inside the turn.
An owned, portable layer that lives outside the turn.
CLAUDE.md & memory files
Notes one harness reads at startup.
A synced, multiplayer record with per-project access and blame.
Dropbox · Drive · iCloud
Generic file sync across devices.
Agent-native: Knowledge in, Ground out, a change log, per-project ACL.
Each is a memory feature inside one app, for one person. Common is the product beneath them.
06 The point
Own your memory. Rent the intelligence.
The model and the harness are rented. They keep getting better and cheaper, and swapping one for the next should cost you nothing. What you build with them is your memory, the part that lasts: your sources, your decisions, the work your agents author, the record of who changed what. It compounds, and it carries your name, not the vendor's.
Today your memory is the most neglected layer in the stack: scattered across apps, forgotten between sessions, locked inside whatever tool you used last. Common gathers it into one place you control, synced across your machines and agents, shared with the people who should see it, and compacted each night so it's worth more by morning. The intelligence gets swapped out; the memory is what you keep.
— Workspaces
One workspace, personal or enterprise
The five Common Components — Knowledge, Ground, Config, Harness, Skills — together make a Common Workspace: one self-contained, synced filesystem, the way an Obsidian vault is one self-contained knowledge base — except multiplayer and synced rather than solo and local.
That container is what lets you hold more than one. A personal workspace and an enterprise workspace, sealed by default and linked only where you choose: the classic motion — adopt it solo, expand it across the org — with a hard airgap between the two.
Common Config
Secrets, keys, and settings — the smallest component
The fewest bytes and the tightest handling. Encrypted at rest and in transit; each secret is decrypted locally the moment an agent reaches for it, never before.
Encrypted
Common Skills
Reusable tools and prompts your agents call
Shared at the root or scoped to a single project. Write a tool once and every agent with access can call it, wherever it runs.
Shared
— The one missing thing
Three pains, one substrate
Name the three symptoms; they're all one substrate apart.
No common ground. Collaborating with another person and their agent is barely possible. There's no shared place the work lives, so there's nothing to grant access to — permissioning can't even exist yet. The substrate has to come first.
Context by duct tape. Getting the right context into a single agent is a patchwork of brittle connectors and grudging APIs, with a remote source of truth forever a step out of sync with what's actually on disk. The agent spends its turn fetching instead of thinking.
The agent forgets. Not literally — there's a transcript to scroll, and lately a memory file the harness scribbles to. But both miss the point: a log and a sticky note sit beside the work, assisting it. The real unlock is the work itself as a living system of record — decisions, findings, data refined by compute into insight — compounding on disk and read first by whatever model picks it up next. Memory shouldn't be a static file off to the side; it should be front and center: the project's state of record.
One fix for all three: a constantly-synced filesystem that mirrors your sources in, captures the agents' work, and gives you a real place to grant access. That's Common.
No common ground
No shared place the work lives — so access control can't exist.
One synced tree, per-project ACL
A shared substrate you can finally scope.
sync
Context by duct tape
Brittle connectors; remote always a step out of sync.
Common Knowledge
Your sources, local and legible at filesystem speed.
mirror
The agent forgets
Nothing writes yesterday down where the model reads first.
Common Ground
The project's evolving state of record, compounding on disk.
flush
Three pains, three mechanisms — the whole product, mapped one to one.
— How it feels
You stop managing state — it's just there
The whole idea is that you stop managing state and just have it. Sit down at any machine and your projects are already current — nothing to sync by hand, nothing to remember to save. A background process watches the tree and keeps everything in step, continuously.
Every project sits at the top level of one folder — one per deal, launch, or research thread — side by side, never buried inside one big archive. The shared things many projects need — skills, secrets, and your harness's own state — live at the root. The layout is flat, legible, and identical on every machine and for every collaborator.
And it syncs continuously: there's no gate where each change has to be reviewed and approved before it lands. You still get full history, rollback, and attribution — they just never get in the way.
Before — one folder, no per-project line
one big folder/ everything tangled together
├─ deal-room/
├─ q3-launch/
├─ research/
├─ finance/
└─ ops/
After — shared at the root, projects at the root
~/Common/
├─ config/ shared setup
├─ knowledge/ org-wide mirrors
├─ deal-room/ a project
├─ q3-launch/
└─ client-acme/ shared with a partner
— Why it stays human
You can outsource thinking. You can't outsource accountability.
There's a line from an IBM training manual in 1979 that has aged into a warning.
A computer can never be held accountable, therefore a computer must never make a management decision.IBM training manual · 1979
You can hand an agent your thinking — the drafting, the synthesis, the legwork. What you can't hand it is accountability: when the call is wrong, the agent can't answer for it; a person does. And accountability needs something else you can't delegate — understanding. You can't stand behind a decision you don't understand.
So the job was never to take the human out of the loop. It's to get the human to understanding faster. Common outsources the thinking by building the unified context layer underneath the agents — and then spends its effort closing the gap between what the agents did and what the person understands, so they can take the decision, own it, and move. The agent does the work; the person keeps the accountability; Common is what lets them actually be accountable at the speed the work now moves.
That's why Common is built around people, not agents. The unit isn't an autonomous agent humming away in the dark — it's a person, accountable, with agents working their Common Ground, and a blame trail that records who decided what. Which quietly reframes the entire multiplayer story.
— The arc
It looks like agents collaborating. It's really accountable people, putting their agents to work.
It's the most proven motion in software — a tool you adopt solo that quietly turns multiplayer — but pointed at people, not bots.
It starts single-player: a personal utility where your own context finally syncs itself, current everywhere, nothing to push or pull. But the file you were already keeping for yourself turns out to be exactly the file a collaborator's agent needs. Single-player becomes multiplayer the instant a second person writes to the same tree — and it scales from there to a whole team. That's the real unlock.
The headline isn't "watch agents work together." It's accountable people putting their agents to work on the same ground. Because every project is its own top-level folder, a project is a shareable unit: grant a partner read access to one deal room — their agent and yours now share its live Common Ground — without exposing anything else you keep. A contractor sees only the project they're on. That per-project, per-person scoping is exactly what a single shared repository structurally cannot express.
And the boundary can run far larger than one folder. Link a personal Common to a company's Common and its Common Knowledge flows into context where it's allowed to. But the two must stay sealed by default — a hard airgap, so private data never bleeds into corporate and the reverse holds just as firmly. Think identity-scoped Commons — the way an enterprise account and a personal account already sit side by side but separate, except here it's the data layer, not the chat history. Links are explicit, directional, and scoped; nothing crosses unless someone draws the line.
Sharing context with a person and their AI should be as ordinary as sharing a folder — and keeping two worlds apart, as ordinary as not sharing one.
deal-room/ → partner · readq3-launch/ → contractor · scopedwork ⇄ company Common · linkedpersonal · airgapped