# supermemoryai/supermemory

> Memory and context engine for AI: extracts facts from conversations, builds user profiles, combines RAG and memory in one API, runs locally or in the cloud.

- Magnitude: 1.7 out of 10 — Cooling
- Stars: 31,049 total · +5 stars on 2026-10-01 (UTC), ≈ 14 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: TypeScript · License: MIT · Created: 2024-02-27 · Last push: 2026-09-30
- GitHub: https://github.com/supermemoryai/supermemory · Homepage: https://supermemory.ai/docs · Page: https://gitnova.dev/en/r/supermemoryai/supermemory

## Useful for

- Connect the MCP server to Claude Code or Cursor so the assistant remembers context across sessions
- Add memory and user profiles to an AI app via a single API without configuring a vector DB
- Self-host the engine with one command and plug in Ollama for offline use

## Why it’s here

- 5 stars so far today, about 14 expected by the end of the day.
- Interest is fading: the two-day pace is 19% of the previous week and a half.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 2,726
- Issues and pull requests: 1,734
- Watchers: 110
- Average over the last week: 27 per day
- Usual pace: 88 per day
- Latest release: server-v0.0.8 (2026-08-17)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-10-04 … 2026-11-02: None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None

## Magnitude by day, last 14 days

09-18 4.2, 09-19 4.8, 09-20 4.2, 09-21 2.8, 09-22 3.1, 09-23 2.2, 09-24 2.0, 09-25 2.0, 09-26 1.7, 09-27 1.9, 09-28 1.9, 09-29 2.1, 09-30 2.1, 10-01 1.7

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-01 11:14 UTC, updated every 30 minutes.