v1 · LoCoMo 61.0%

Memoryinfrastructure
forAIagents.

Three endpoints turn raw conversation into a queryable, per-user knowledge graph — and stream back answers, not just memories.

LoCoMo
61.0%

Reproducible

Uptime
99.9%

Business SLA

Endpoints
3

add · search · ask

memhq · liveforming
$ memhq
knowledge graph
graph:user_420 nodes · 0 edges

pip install memhq·npm install @memhq/sdk

Production-grade APIs99.9% uptime SLASOC2 in progressNYC regionPer-user privacy by default

How it works

Three calls. Add, search, ask.

Most memory libraries hand you a vector store and call it a day. MemHQ gives you the full pipeline — extraction, retrieval, and grounded synthesis — behind a typed API.

Add
01

Ingest a fact, conversation, or document. An async pipeline extracts memories, embeds them, and stores them in a per-user graph.

mem.add({
  userId: "u_42",
  content: "Prefers concise replies"
})
Search
02

Hybrid BM25 + vector retrieval with Reciprocal Rank Fusion. Returns ranked memories with scores and provenance.

mem.search({
  userId: "u_42",
  q: "tone preferences?"
})
Ask
03

Server-side: retrieve, ground, and synthesize a cited answer in one round trip. No retrieve-stuff-prompt-LLM dance.

mem.ask({
  userId: "u_42",
  q: "tone preferences?"
})

Use cases

What you build on top of memory.

SESSION 1 · SESSION 2day 1day 30← remembers

Chatbots that remember you across sessions

Conversation history compresses into durable memories. Day-30 the bot still knows what day-1 told it.

MEMHQagent.run #1agent.run #2agent.run #3result #1result #2result #3state persists between runs

Agents with long-term memory across runs

State that persists between agent invocations — no scratchpad gymnastics, no re-priming on every loop.

org knowledgegraph:org_acmegraph:u_42graph:u_91

Shared org knowledge, per-user privacy

Group graphs for what the team knows. User graphs for what only they know. Both queried in one call.

BEFOREChunkerVector DBEmbedderRerankerSynthCacheAFTERmem.ask()one endpoint · cited answer

RAG-quality answers without building a pipeline

Chunker, vector store, reranker, synthesizer — collapsed into one managed endpoint with citations.

Integrations

Drop into your stack.

Wire MemHQ into the framework you already use. SDKs in Python and TypeScript, an MCP server for desktop and IDE assistants, and a REST API for everything else.

from memhq import MemHQ
mem = MemHQ(api_key="sk_live_…")

mem.add(user_id="u_42", content="I drive a Rivian R1S and Tesla Model Y")

answer = mem.ask(user_id="u_42", q="What cars do I own?")
# → "You own a Rivian R1S and a Tesla Model Y." [m_72ad, m_72ae]

Benchmark

Built on a reproducible benchmark, not marketing copy.

MemHQ scores 61.0% on the LoCoMo memory benchmark using standard published methodology — full reproducibility in our docs. Per-category breakdown to the right; the harness, prompts, and snapshots are linked so you can re-run it against your workload.

LoCoMo · per-category accuracyN = 1,540
Single-hop0.0%
Temporal0.0%
Multi-hop0.0%
Open-domain0.0%
MemHQ · LoCoMostandard methodology · gpt-4o-mini judge

Start building memory into your agent in 60 seconds.

Free Hobby tier. No card required. Three endpoints between you and an agent that remembers.