Your teammates' agents already know what yours figured out.

MemBridge reads the session logs your Claude Code and Codex agents already write, distills what each one worked out, and gets it to everyone else's agents. At startup, mid-session, and on demand.

One command, about two minutes, no account. npm i -g @membridgeai/membridge

your session · Thursday 09:41
Claude Code · payments-api
How it reaches your agents

Three moments, and one of them is ours alone.

Most memory tools stop at writing a file. The useful part is what happens after the session has already started, and months later when nobody remembers who did it.

We measured how much this costs: across 6,104 real agent sessions from 310 developers, the median developer spends 31% of their tokens re-orienting an agent in code it has already seen. Read the Context Ledger →

At startup

Every session opens briefed

What the team's agents worked out gets written into the instruction files your agents already read, attributed by person. Nobody writes a doc. Nobody re-explains the architecture.

Mid-session What a context file cannot do

A teammate's decision lands while you work

Your agent opens a file a teammate's agent made a call about, and that call enters the running session. Once, exactly when it matters. No doc, no Slack, no human relaying it.

On demand Scoped to your team's real work

Your agent searches the whole team's history

A ranked search over what every agent on the team has actually done, exposed over MCP so any agent can query it directly. The useful answer is usually months old.

The app

What the team looks like from the outside.

Every agent session across your team, who can see which project, and where knowledge is concentrated in one person's head.

Everything below is a mock of the shipped app, filled with sample data. The numbers are illustrative, not measured. Every screen in the sidebar is in the app today. Click through it.

Team
You
Jules

Today

Thursday, 30 July
✓ synced 2m ago
2live now
7sessions today
6updates shared
4/4members synced
Happening now
Priya · Codexapi-gateway 14m
Intentrotate the vault credentials for tenant onboarding
Marcus · Claude Codeweb 3m
Intentport the checkout flow off the legacy SDK
Projects · this week
api-gatewayShared
Fixed proration on mid-cycle plan changes · Jules, 2h
14 sessions · last 7 days✓ up to date
webShared
Cut checkout load time by lazy-loading the editor · Marcus, yesterday
9 sessions · last 7 days✓ up to date
billingShared
Added a retry budget to the webhook dispatcher · Sam, yesterday
6 sessions · last 7 days✓ up to date
infra-secretsPrivate
Rotated the signing keys after the March incident · Priya, 3d
4 sessions · last 7 days✓ up to date
Who sees what
ProjectSessions · 7dSync Priya Marcus Jules Sam
api-gateway14✓ up to date
web9✓ up to date ·
billing6✓ up to date ··
infra-secrets Private4not shared

Tick a cell to grant or revoke, without opening the project. A private project cannot be granted until it is shared. Every change lands in the audit trail.

Pending invites
Expires in 6 days
Members · 4 people
Priya Ramanowner · 3 projects ✓ key verified
Marcus Belladmin · 2 projects ✓ key verified
Jules Okaformember · 3 projects ✓ key verified
Sam Ortizmember · 2 projects ✓ key verified
Audit · last 30 days
Jul 28
Marcus granted Jules access to billing
Jul 24
Priya changed Marcus to admin
412sessions
61%repeat opens answered by memory
4/4members syncing
1,284memory entries shared
Knowledge concentration · only one person has touched it
Priya Ramaninfra-secrets · 38 sessions, nobody else 1 person
Activity by person · last 30 days
Priya Raman142 sessions · 138 shared a summary 34%
Marcus Bell118 sessions · 115 shared a summary 29%
Jules Okafor96 sessions · 94 shared a summary 23%
Sam Ortiz56 sessions · 55 shared a summary 14%
Cross-tool reach
Claude Code248 sessions 60%
Codex164 sessions 40%

One memory across both, so switching tools mid-task doesn't reset anything.

Memory delivery how agents on this machine receive project memory
Context blockWritten into the instruction files your agents already read CLAUDE.md · AGENTS.md✓ installed
Recall on readAnswers a repeat file open from memory instead of re-reading it ✓ serving
Session summariesThe agent writes up what it worked out when a session ends ✓ installed
MCP serverLets any agent query this project's memory directly claude code · codex · cursor✓ registered
Privacy
Share plaintext with teamOff means teammates' apps decrypt locally; the server stores your content only as ciphertext ✓ end-to-end
Share verbatim promptsSummaries and file paths sync; what you typed stays on this machine off
Redaction patternsBuilt-in key, token and credential shapes, plus your own 23 built-in · 2 custom
Excluded foldersNever watched, never synced ~/clients · ~/personal
Daemon
RunningLocal only, bound to 127.0.0.1 v0.3.4 · port 7437✓ running

Your sessions, summaries and code leave this machine only as what you have explicitly shared with your team, encrypted.

In the real app, live rows show the ask a session opened with, never a guess at what it is doing.

What your team gets

Everything else it does without anyone maintaining it.

Cross-tool memory. Claude Code and Codex share one store. Switching tools doesn't reset context.

Auto-registers over MCP. Finds the agents you have installed and wires itself in.

Ask why about any file. Which session touched this line, by whom, and the reasoning behind it.

Per-project access control. Pick exactly who sees which project, changed in one grid.

One-command onboarding. A new teammate joins with a single invite link.

Roles and an audit trail. Owner, admin, member. Every membership and sharing change recorded.

Health at a glance. Who's syncing, whose keys are verified, and anything that quietly stopped reaching the team.

Runs local. A daemon on each machine. No agent of ours in your CI, no repo upload.

Privacy

The server can't read your team's work.

End-to-end encrypted

Team sync is encrypted on by default. Keys are generated on each laptop and never leave it, so the backend stores ciphertext it cannot open. The content is what gets encrypted; routing details (author, project, timestamp, tool) stay readable so sync and access control can work.

Prompts stay local

Summaries and file paths sync. Your verbatim prompts stay on your machine unless you opt in, per session or per project.

Keys rotate on exit

Removing someone mints a new team key sealed only to the people who remain. Secrets are stripped before anything is written or sent.

Get it

Two minutes, no account.

Install on one repo and watch a session get distilled. Team sync is a separate, deliberate step.

Desktop app for macOS (Apple Silicon) and Windows. On Linux or an Intel Mac, the npm command runs the same daemon and serves the same dashboard in your browser.

$ npm install -g @membridgeai/membridge

Node 18 or newer. The desktop app adds a menu bar or system tray icon and start at login. Everything else it does, the CLI does too.

Free while we're early. No account, no card, through v1.0. When we charge it will be per seat for team sync. Individual use stays free.

MemBridge is early. If you want to see what breaks before you standardise on it, you are exactly who we want to hear from.

What it does to your machine

  • Your files stay yours. Memory lands between its own <!-- membridge --> markers in CLAUDE.md and AGENTS.md. Your own notes are never touched, and membridge remove restores every file exactly.
  • It registers as an MCP server with the agents it finds installed, so they can query team memory directly.
  • It starts at login when you install the desktop app, so the daemon is running when your agents are. Turn it off from the tray menu or in Settings.
  • Four small runtime dependencies, no build step, and the source is available to read under the Functional Source License 1.1 (FSL-1.1-ALv2).
  • The macOS app is signed and notarized by Apple, with the ticket stapled into the download, so it opens without a Gatekeeper prompt. The installer also verifies a pinned SHA-256 and refuses to install on a mismatch.
Does our code leave the machine?

No. MemBridge reads your agent sessions locally and writes memory to disk on the same machine. Your sessions, summaries and code go nowhere until you turn on team sync, and even then it is only what your sessions concluded: decisions, summaries, and file paths, never your source code. Team sync is end-to-end encrypted, so the backend stores ciphertext it has no key for. Separate from your work content, MemBridge sends anonymous usage counters and diagnostics tied to a random install id (turn them off with the diagnostics setting or MEMBRIDGE_NO_DIAGNOSTICS=1), and it asks GitHub about once every six hours whether a newer release exists.

What happens to secrets that show up in a session?

They are stripped before anything is written to disk or sent to your team. MemBridge matches the shapes of AWS, GitHub, Google, Slack, OpenAI and Anthropic keys, JWTs, PEM blocks, connection strings with inline credentials, and bearer tokens, plus a high-entropy catch-all for the ones nobody has a pattern for. Redaction runs at every boundary, including on data arriving back from your teammates.

How is this different from maintaining CLAUDE.md ourselves?

A hand-written context file is the startup half of this, and it only stays useful while somebody keeps editing it. MemBridge writes that file for you from what your sessions actually concluded. The two things it does that a file cannot: deliver a teammate's decision into a session that is already running, and answer a question against months of your team's history that no file would still contain.

Which tools does it work with?

Claude Code and Codex are first class. Their sessions are what MemBridge reads, and they share one memory, so switching between them mid-task doesn't reset anything.

Cursor is different, and the distinction matters if your team is split. MemBridge registers itself over MCP with Cursor, so Cursor can query everything the team knows. It does not read Cursor's sessions yet, so work done in Cursor does not feed back into the shared memory. Cursor consumes, it does not yet contribute.

What happens when someone leaves the team?

Removing them revokes access to every shared project immediately and mints a new team encryption key sealed only to the people who remain, so their copy stops being able to read anything new. Membership and sharing changes are all recorded in an audit trail.

Can people keep some work private?

Yes, at three levels. Verbatim prompts stay on your machine by default; only summaries and file paths sync unless someone opts in. Any project can be kept private, and shared projects have per-person access. A developer can pause capture entirely for a project without affecting anyone else.

Do people have to change how they work?

No. It watches the sessions your team already runs and writes to the instruction files your agents already read. Nobody writes documentation for it, and nobody has to remember to record anything.

Talk to us

Or see it on your own code.

Send us a note and we'll set it up on a repository your team actually works in, then show the hand-off firing between two real sessions. No slides, and nothing to uninstall afterwards if it isn't for you.

Useful to know beforehand: how many engineers, which agents they run, and whether your repos live on GitHub.