Developers

Build with memory.

One command to install, three primitives to use — observe, recall, search. An official TypeScript SDK today — Python, Go, .NET, and Rust on the way — plus an MCP server for any agent framework and a growing library of runnable examples.

SDKs

Native clients, every stack.

Each SDK wraps the same engine — memory, prediction, temporal knowledge graph — behind an idiomatic client. Same concepts, your language.

TypeScript

Available
npm install @thinkfleet/memory-sdk

@thinkfleet/memory-sdk

Python

Coming soon
pip install thinkfleet-memmesh

thinkfleet-memmesh

Go

Coming soon
go get github.com/ThinkfleetAI/memmesh-go

github.com/ThinkfleetAI/memmesh-go

.NET

Coming soon
dotnet add package MemMesh

MemMesh

Rust

Coming soon
cargo add memmesh

memmesh

Quickstart

Remember, recall, reflect.

Seed a memory, search it semantically, and let the engine synthesize higher-order insights — in the language you already ship.

$npm install @thinkfleet/memory-sdk
typescript · quickstart
import { ThinkFleetMemory } from '@thinkfleet/memory-sdk'

const tf = new ThinkFleetMemory({ apiKey: 'sk-...', projectId: 'proj_...' })

// Remember something
await tf.memory.observe({
  subject: { kind: 'contact', externalId: 'sarah' },
  content: 'Prefers email over phone.',
})

// Recall it, semantically
const hits = await tf.memory.admin.search({ query: 'how to reach sarah', limit: 5 })

// Synthesize higher-order insights from what it has learned
const { insights } = await tf.memory.admin.reflect({ maxInsights: 3 })

Any agent, no SDK

Native memory over MCP.

Wire MemMesh into Claude, Cursor, or any MCP-compatible agent in one command — then call memory_observe, memory_recall, and memory_search as tools.

$npx @thinkfleet/memmesh install