MemoriLabs /Memori
Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems. Built for enterprise, Memori works with the data infrastructure you already run, no rip-and-replace, and deploys across managed cloud, single-tenant cloud, VPC, and on-premises.
★ 17,590⑂ 3,993👁 75⑃ 492● 120▤ 38
+15
日增长
17,590
stars
3,993
forks
75
watchers
492
prs
120
issues
38
releases
README
Memory from what agents do, not just what they say.
Memori plugs into the software and infrastructure you already use. It is LLM, datastore and framework agnostic and seamlessly integrates into the architecture you've already designed.
→ Memori Cloud — Zero config. Get an API key and start building in minutes.
Choose memory that performs
Getting Started
Installation
TypeScript SDK
bash
npm install @memorilabs/memori
Python SDK
bash
pip install memori
Quickstart
Sign up at app.memorilabs.ai, get a Memori API key, and start building. Full docs: memorilabs.ai/docs/memori-cloud/.
Set MEMORI_API_KEY and your LLM API key (e.g. OPENAI_API_KEY), then:
TypeScript SDK
typescript
import { OpenAI } from 'openai';
import { Memori } from '@memorilabs/memori';
// Requires MEMORI_API_KEY and OPENAI_API_KEY in your environment
const client = new OpenAI();
const mem = new Memori().llm
.register(client)
.attribution('user_123', 'support_agent');
async function main() {
await client.chat.completions.create({
model: 'gpt-4o-mini',
messages: [{ role: 'user', content: 'My favorite color is blue.' }],
});
// Conversations are persisted and recalled automatically in the background.
const response = await client.chat.completions.create({
model: 'gpt-4o-mini',
messages: [{ role: 'user', content: "What's my favorite color?" }],
});
// Memori recalls that your favorite color is blue.
}
Python SDK
python
from memori import Memori
from openai import OpenAI
Requires MEMORI_API_KEY and OPENAI_API_KEY in your environment
client = OpenAI()
mem = Memori().llm.register(client)
mem.attribution(entity_id="user_123", process_id="support_agent")
response = client.chat.completions.create(
model="gpt-4o-mini",
messages=[{"role": "user", "content": "My favorite color is blue."}]
)
Conversations are persisted and recalled automatically.
response = client.chat.completions.create(
model="gpt-4o-mini",
messages=[{"role": "user", "content": "What's my favorite color?"}]
)
Memori recalls that your favorite color is blue.
Explore the Memories
Use the Dashboard — Memories, Analytics, Playground, and API Keys.
[!TIP]
Want to use your own database? Check out docs for Memori BYODB here:
https://memorilabs.ai/docs/memori-byodb/.
For disposable BYODB development databases, see the TiDB Zero provisioning
guide: docs/memori-byodb/databases/tidb.mdx.
LoCoMo Benchmark
Memori was evaluated on the LoCoMo benchmark for long-conversation memory and achieved 87% overall accuracy while using an average of 721 tokens per query. That is just 2.8% of the full-context footprint, showing that structured memory can preserve reasoning quality without forcing large prompts into every request.
Compared with other retrieval-based memory systems, Memori outperformed Zep, LangMem, and Mem0 while reducing prompt size by roughly 67% vs. Zep and lowering context cost by more than 36xTop issues
#495[Feature Request] CrewAI Framework Integration for Memori Python SDK7 comments · 2026-05-12#566[Feature] Add Neon Launchpad DB Provisioning.6 comments · 2026-05-28#303[Bug] How to delete user memories?5 comments · 2026-02-06#250[Feature] Support for Local & Custom OpenAI-Compatible Endpoints (Ollama/vLLM)3 comments · 2026-01-02#614[Feature] Documentation update3 comments · 2026-07-17#600[Feature] Add Dark Mode Toggle Support3 comments · 2026-06-20#366[Feature] Allow Batch/On-Demand Memory Extraction Instead of Per-Message Processing3 comments · 2026-03-14#175[FEATURE] Add support for AgentScope3 comments · 2025-11-24
Discussions
#607[Docs] Proposal: Add best-practices guide for API key management and rate-limit handling0 comments · 2026-06-28#526Version 3.3.40 comments · 2026-05-20#471Version 3.3.31 comments · 2026-05-05#449Version 3.3.20 comments · 2026-04-29#442Version 3.3.10 comments · 2026-04-27#438Developer questions: multi-patient, multi-workflow agent memory for diagnostic centres5 comments · 2026-04-27#415Version 3.3.00 comments · 2026-04-20#406Version 3.2.81 comments · 2026-04-13
Latest release
Version 3.3.6 v3.3.6 2026-05-28What's Changed Release version 3.3.6rc1 with exclusive Rust fastembed backend for … by @devwdave in https://github.com/MemoriLabs/Memori/pull/561 fix mysql datetime type by @devwdave in https://github.com/MemoriLabs/Memori/pull/562 Release version 3.3.6, updating changelog and project files to reflec… by @devwdave in https://github.com/MemoriLabs/Memori/pull/563 Full Changelog: https://github.com/MemoriLabs/Memori/compare/v3.3.5...v3.3.6