Memmesh SDK

What it does

When your agent uses it

• : user is writing code that calls the MemMesh SDK
• Mentions @thinkfleet/memory-sdk
• ThinkFleetMemory
• Lattice.predict

Example prompts

• “@thinkfleet/memory-sdk”
• “ThinkFleetMemory”
• “memmesh sdk”
• “/memmesh-sdk”

Requirements

• Python 3
• Node.js
• A credential in MEMMESH_API_KEY
• Compatibility (from SKILL.md): Requires Node.js 18+. npm install @thinkfleet/memory-sdk. A MEMMESH_API_KEY (hosted) or a Cognito JWT. For a no-key local setup use the memmesh CLI + MCP instead.

Workflow steps

3 steps, taken from the step headings in SKILL.md.

1. 1install and authenticate
2. 2initialize
3. 3the core loop: observe → retrieve → (predict)

What it can do on your machine

Read from SKILL.md and the folder at commit bba48f8. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • npm

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • docs.memmesh.ai

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • MEMMESH_API_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

• Compatibility

  Requires Node.js 18+. npm install @thinkfleet/memory-sdk. A MEMMESH_API_KEY (hosted) or a Cognito JWT. For a no-key local setup use the memmesh CLI + MCP instead.

  From compatibility in the SKILL.md frontmatter.

Context cost

Memmesh SDK loads about 1.6k tokens when it runs. Until then it costs about 187 tokens; SKILL.md has 317 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~187

When it runs · the whole SKILL.md, loaded when a task matches

~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ThinkfleetAI/memmesh at commit bba48f8, republished under its Apache-2.0 licence (© ThinkfleetAI). 317 words, ~1,645 tokens.

name

memmesh-sdk

description

MemMesh TypeScript SDK reference (@thinkfleet/memory-sdk) for the hosted platform at app.memmesh.ai. Covers the ThinkFleetMemory client — observe / search / list, the predict + lattice prediction surface, closed-loop learning (recordDecision / recordOutcome), emergent behavior discovery, and the health / financial vertical packs. TRIGGER when: user is writing code that calls the MemMesh SDK, mentions "@thinkfleet/memory-sdk", "ThinkFleetMemory", "memmesh sdk", "lattice.predict", "predictTarget", or wants to add memory OR prediction to a TS/JS app. DO NOT TRIGGER for: the local MCP observe/recall loop (that's the always-on `memmesh` skill), CLI usage (use `memmesh-cli`), or wiring into an existing repo (use `memmesh-integrate`).

compatibility

Requires Node.js 18+. npm install @thinkfleet/memory-sdk. A MEMMESH_API_KEY (hosted) or a Cognito JWT. For a no-key local setup use the memmesh CLI + MCP instead.

license

Apache-2.0

metadata.author

thinkfleet

metadata.category

ai-memory

metadata.tags

memory, prediction, calibration, typescript, knowledge-graph

npm install @thinkfleet/memory-sdk
export MEMMESH_API_KEY="mm-your-api-key"   # from app.memmesh.ai

import { ThinkFleetMemory } from "@thinkfleet/memory-sdk";

const memory = new ThinkFleetMemory({
  apiKey: process.env.MEMMESH_API_KEY,      // or a Cognito JWT via `token`
  // baseUrl defaults to https://app.memmesh.ai
});

await memory.memory.observe({
  text: "Alice is vegetarian and allergic to nuts. She books gym classes on Mondays.",
  userId: "alice",
  projectId: "myapp",
});

const hits = await memory.memory.search({ query: "dietary restrictions", userId: "alice" });

// Or the synthesized, token-budgeted bundle (profile + patterns + predictions + top memories):
const ctx = await memory.context.build({ subjectKind: "user", subjectId: "alice", maxTokens: 2000 });

// Forward behavior prediction — what will this subject do next?
const preds = await memory.lattice.predict({ subjectKind: "user", subjectId: "alice", horizonDays: 30 });

// Declarative "predict ANY target" — no code change to add a new prediction:
const p = await memory.lattice.predictTarget({
  subject: { kind: "user", externalId: "alice" },
  target: { kind: "event_occurrence", name: "churn" },   // or numeric | event_time | anomaly
});
if (p.abstained) {
  console.log("abstained:", p.abstentionReason);         // honest "not enough evidence"
} else {
  console.log(p.probability, "±", p.calibration, "because", p.evidenceMemoryIds);
}

// Is the model actually calibrated? Check the reliability curve:
const cal = await memory.lattice.getCalibration({ subjectKind: "user" });

const d = await memory.learning.recordDecision({ subjectId: "alice", decision: "sent_winback_offer" });
await memory.learning.recordOutcome({ decisionId: d.id, outcome: "converted", value: 49.0 });
const eff = await memory.learning.getEffectiveness({ subjectKind: "user" });

const behaviors = await memory.behaviors.discover({ projectId: "myapp" });
// each carries prevalence, stability, and the evidence memories behind it

const g = await memory.context.queryGraph({ subjectId: "alice", asOf: "2026-01-01T00:00:00Z" });
// "what did we believe about Alice on Jan 1" — every edge has valid_from / valid_to

// Health
await memory.health.recordBiomarker({ subjectId: "alice", marker: "hba1c", value: 5.4 });
const risk = await memory.health.getCohortRisk({ condition: "prediabetes" });

// Financial
await memory.financial.ingestPrices({ symbol: "AAPL", bars: [...] });
const f = await memory.financial.predict({ symbol: "AAPL", target: { kind: "numeric", name: "close_5d" } });

await memory.consent.optOut({ subjectId: "alice" });
await memory.compliance.hardDeleteSubject({ subjectId: "alice" });   // GDPR right-to-forget
const audit = await memory.compliance.listAuditEvents({ subjectId: "alice" });

© ThinkfleetAI, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/memmesh-sdk of ThinkfleetAI/memmesh.

Open the folder on GitHubat commit bba48f8