How it works
Your whole team's AI, on the same page
Your team already works with AI. BaseThread is the shared context underneath it: every teammate's AI logs what it does and what you decide, we harmonize it in the cloud, and push it back so everyone's AI stays current, automatically.
Witness log harmonize push back
The problem
Every AI starts from zero
Your AI re-learns the same context every session. A teammate's AI never sees what yours decided. Context lives in one person's chat history and dies there. The bigger the team, the worse it gets.
Objection
Wait, doesn't my AI already remember?
Your AI's built-in memory is personal, and it's trapped in one app. Claude remembers your chats. ChatGPT remembers your projects. Cursor reads your repo's rules. None of them share what your teammate's AI learned, and none of them work across the other tools your team uses. BaseThread is the shared layer that does.
How it works
Your AI does the work. BaseThread remembers it, for everyone.
Reads before it works
Your AI pulls the latest team context through MCP, so it starts every task current. Desktop clients go through the BaseThread Mac app's local MCP server; cloud clients like ChatGPT go straight to mcp.basethread.ai.
Writes as it goes
It records activity, decisions, and tasks into the shared ledger, and updates the context docs themselves, all as the work happens. It works in the area you're in, so it reads and writes the right slice. No manual note-taking.
Harmonized and shared back
We reconcile everyone's streams in the cloud and push the canonical version back to every teammate's AI.
Activity Decisionsand Tasksflow through the same ledger.
Not a tool that remembers
Your team's second brain
A personal second brain (Notion, Obsidian) is yours, and you maintain it by hand, for one person. BaseThread is a team second brain: a shared context graph your AI writes to as it works and every AI tool reads from, kept current automatically.
// it writes back as it works bt.writeFile({ area: "Product", title: "Pricing model", update: "moved to per-seat", })
Your AI writes the brain as it works, not you.
It writes itself
Your AI logs activity and decisions and updates your context as it works, so the brain grows without anyone maintaining it.
It focuses where you are
Your AI works in the area you're in and reads and writes the right slice, not a wall of everything.
Shared, not siloed
Every teammate's AI runs on the same brain, harmonized in the cloud, so the whole team is current without a standup.
It remembers the people
1:1 notes and the running history with everyone you work with, on BaseThread or not, so your AI knows each relationship, not just each project.
It tells you where things stand
A synthesized 'where this stands' read on any team, project, or your whole workspace, refreshed on its own, so you catch up in one glance.
It scales past projects
Group big efforts into initiatives, a tier above projects, so a launch or a quarter-long push has one home and your AI keeps its context together.
More on the idea: what a second brain for your team's AI really means.
The third stream
Not just memory. It coordinates the work.
Activity and decisions look back; tasks look forward. Your AI creates, assigns, and tracks tasks across tools, not just remembers them.
Create from any tool
“Add a task to follow up with Globex after the demo, due Friday.” Created in place, in whatever AI you’re already in.
Assign to a teammate
Delegate the pricing-copy sign-off to PMM. It lands in their list, and their AI sees it at the start of the next session.
Track to done
Ask what’s on your plate, what you delegated, and what’s still open. Status is read from the shared task stream, not a guess.
The levels
Context, shaped like your company
Company → Products → Teams → Projects → Me, plus initiatives that group bigger efforts and the people you work with. Your AI pulls exactly what's relevant to the task in front of it, not a wall of everything.
People, not just projects
Your AI remembers everyone you work with.
Projects are not the only thing worth keeping context on. People are. BaseThread keeps your 1:1 notes and the running history with each person, teammates and outside contacts alike, private by default and shareable when it helps. Your AI reads it before your next conversation, so you walk in caught up on what you discussed, what you promised, and what is next.
Teammates and contacts
Anyone you work with, on BaseThread or not, gets a running relationship history.
1:1 notes that stick
What you discussed, what you promised, and what is next, kept in one place per person.
Private by default
Your people notes are yours, shareable only when it helps the team.
Catch up in one read
Know where anything stands, without scrolling the history.
You should not have to read a month of activity to know where a project is. BaseThread synthesizes a current 'where this stands' summary for any team, project, or your whole workspace, kept fresh on its own, with one click to regenerate. Walk into anything already caught up.
Where this stands
Project: Payments revamp
Pricing moved to per-seat (decided this week). Retry-cap wiring shipped; the idempotency review is open with Raj. Next up: the PaymentIntents migration, blocked on access. Three teammates active in the last two days.
The context graph
One question, the exact right context
Every node, every link, queryable. When a question lands, the graph routes through the few nodes that matter, so your AI answers with citations instead of a generic guess.
A question lands
“What did we decide about pricing, and why?”
Asked in Cursor by Maya
The graph routes
- Decision: Move to simple per-user pricing
- Activity: Q1 pricing review meeting
- Activity: Cohort pricing feedback
- Project: Pricing v2 · Products layer
Pulled from exactly the nodes that matter. Not the whole graph.
Your AI answers, grounded
“You moved to simple per-user pricing in the Q1 review. Usage caps and per-action billing were parked. Rationale: most accounts are small teams.”
Citations: decision:7f2a, activity:8c2a, activity:91f3
Works with the AI you already use
Two ways your AI reaches your team's context
The BaseThread Mac app spins up a local MCP server on your machine for desktop AI. Cloud-bound AI like ChatGPT connects to our remote MCP at mcp.basethread.ai. Both paths read and write the same team context, no new app to learn, so your AI can create and update context, scoped to where you are working.
Path 1 · Local MCP
The Mac app spins it up
The Mac app spins up a local MCP server on your machine. Any MCP-capable AI on the same machine connects to it, reads your team's context, and writes activity, decisions, and tasks back. Fast and offline-capable.
your-mac → local MCP → BaseThread
Path 2 · Remote MCP
Hosted at mcp.basethread.ai
Our hosted MCP endpoint at mcp.basethread.ai. No install. AI that runs in the cloud or a browser connects directly. The right call for clients that can't use a local server, like ChatGPT or hosted agents.
cloud AI → mcp.basethread.ai → BaseThread
Both paths reach the same BaseThread cloud and the same harmonized team ledger. Pick whichever fits the AI you're using; switch back and forth without losing context.
The tools you already use
Your AI is the integration
Your AI tools read your graph, and they already reach the tools where your work happens. Notion, Jira, Slack, HubSpot, your AI reads them with the access it already has and writes the signal, the decisions, context, and activity, into the right place in your graph, scoped to the team or project you are working in. BaseThread never connects to your tools or holds their credentials. You connect nothing new.
Harmonization
Everyone on the same page, without anyone managing it
BaseThread merges duplicate activity beats, reconciles conflicting decisions, links related entries across streams, and retires the ones that got superseded, so your team's shared context stays clean and current on its own.
Raw streams
- Sarah's Claude CodeActivityShipped the magic-link auth flowkept
- Maya's CursorDecisionMove to simple per-user pricingkept
- Raj's ClaudeActivityShipped magic-link auth (per Sarah's PR)duplicate
- Mia's ChatGPTDecisionPer-action pricing parkedsuperseded
- Priya's CursorTaskPricing-copy sign-off, due Frikept
Canonical ledger
- Shipped the magic-link auth flowActivityLogged by Sarah's Claude Code. Duplicate from Raj's Claude merged.
- Move to simple per-user pricingDecisionSupersedes "Per-action pricing parked." Linked.
- Pricing-copy sign-off, due FriTaskAssigned to PMM. Open. Linked to the pricing decision.
Your context, protected
Encrypted in transit and at rest, role-based access at every level, and never used to train AI models. You own your data.
