Mem0 (open source) vs Ai-memory vs Basic Memory

Side by side, as alternatives to Mem0 Platform. Rows that differ are highlighted; the strongest value in a row is marked. Unknown means no source yet.

Mem0 (open source)mem0ai/mem0

Ai-memoryakitaonrails/ai-memory

Basic Memorybasicmachines-co/basic-memory

Mem0 Platformpaid product

Cost and coverage

Price

$0 software; you run it

Free Hobby tier (10,000 add and 1,000 retrieval requests a month); Starter $19/month, Pro $249/month, Enterprise custom source ↗

Long-term memory for chat assistants

Partly

Yes

Memory for coding agents

Partly

Yes

Knowledge graph memory

Partly

Yes

Jobs covered

1 of 3 jobs

3 of 3 jobs

2 of 3 jobs

All 3

Popularity and activity (from GitHub)

Stars

67,542Top

11,924

4,295

—

Gain this week

Unknown

—

Signal

Building history

—

Commits / 4 wk

1,156Top

216

—

Latest release

ts-v3.3.1 · 2026-09-25

v3.1.2 · 2026-10-20Top

v0.23.2 · 2026-08-25

—

Commits / 12 wk

132

1,917

714

—

People committing / 12 mo

49+

100+

—

Issues opened / closed, 30 days

111 / 27

195 / 196

74 / 70

—

Facts, with sources on each project page

Runs on my machine?Differs

Yes, as a Python/Node library or a self-hosted Docker server

Yes, a single local binary and server; Docker image also available

Yes, local files plus a SQLite index; air-gapped use supported

Hosted by the vendor

Code licenceDiffers

Apache-2.0

MIT

AGPL-3.0 (copyleft)

—

Model weights licenceDiffers

No bundled weights; licence depends on the LLM and embedding model you connect

No single model licence. The default path makes no LLM calls; optional LLM and embedding models have separate provider/model terms.

No separate model weights (optional FastEmbed models download on first use)

—

Commercial useDiffers

Yes, Apache-2.0 code

Yes, MIT allows commercial use

Yes, under AGPL-3.0 copyleft terms (share source of modified versions offered over a network)

—

Paid services needed?Differs

Needs an LLM and embeddings (OpenAI by default); local models via Ollama are documented

None for ai-memory itself (zero-LLM default); it needs an agent CLI such as Claude Code, Codex or OpenCode, which may be paid

None required by Basic Memory; you need an MCP-capable AI client, which may itself be paid

Subscription

HardwareDiffers

Not documented; depends on the LLM and embedding model you run

Not checked yet

Not documented

—

Operating systemsDiffers

Linux (Ubuntu) is used by the project CI. This is test/build evidence, not a complete Windows/macOS support guarantee.

Linux and macOS supported; Windows via WSL2 supported, native Windows experimental

Windows x86_64, Linux x86_64/ARM64 and macOS are listed in the semantic-search compatibility table; Intel Macs need an ONNX Runtime pin or OpenAI embeddings for local semantic search

—

Setup effortDiffers

Easy, pip install mem0ai (server via docker compose)

Easy; install script then ai-memory setup (PowerShell script on Windows)

Easy, uv tool install plus adding the MCP server to your AI client

—

Stars over time

Switch to Growth % to compare projects of different sizes fairly.

Mem0 (open source)
Ai-memory
Basic Memory

Focus a point, use arrow keys, or tap for its value.

Tracked daily since 15 Oct 2026. Dashed history: estimated from public records of when people starred the repo. Lines connect observations only; gaps contain no measured points.

Growth % starts at each project's first observed point in the shown range. Zero-star starts are unavailable.

Notes for a video or post

A plain summary with today's date and a link to the sources. Check each project page before you publish.

Mem0 (open source) vs Ai-memory vs Basic Memory (as alternatives to Mem0 Platform)
Figures from RepoQuarry, 21 Oct 2026. Sources: https://repoquarry.dev/compare?ids=mem0,ai-memory,basic-memory&product=mem0-platform

Mem0 Platform: Free Hobby tier (10,000 add and 1,000 retrieval requests a month); Starter $19/month, Pro $249/month, Enterprise custom
Mem0 (open source): free software; does 1 of 3 Mem0 Platform jobs
Ai-memory: free software; does 3 of 3 Mem0 Platform jobs
Basic Memory: free software; does 2 of 3 Mem0 Platform jobs

- Mem0 (open source): 67,542 GitHub stars, 132 commits in 12 weeks, licence Apache-2.0
- Ai-memory: 11,924 GitHub stars, 1,917 commits in 12 weeks, licence MIT
- Basic Memory: 4,295 GitHub stars, 714 commits in 12 weeks, licence AGPL-3.0 (copyleft)

Where they differ:
- Runs on my machine?: Mem0 (open source) Yes, as a Python/Node library or a self-hosted Docker server; Ai-memory Yes, a single local binary and server; Docker image also available; Basic Memory Yes, local files plus a SQLite index; air-gapped use supported
- Code licence: Mem0 (open source) Apache-2.0; Ai-memory MIT; Basic Memory AGPL-3.0 (copyleft)
- Model weights licence: Mem0 (open source) No bundled weights; licence depends on the LLM and embedding model you connect; Ai-memory No single model licence. The default path makes no LLM calls; optional LLM and embedding models have separate provider/model terms.; Basic Memory No separate model weights (optional FastEmbed models download on first use)
- Commercial use: Mem0 (open source) Yes, Apache-2.0 code; Ai-memory Yes, MIT allows commercial use; Basic Memory Yes, under AGPL-3.0 copyleft terms (share source of modified versions offered over a network)
- Paid services needed?: Mem0 (open source) Needs an LLM and embeddings (OpenAI by default); local models via Ollama are documented; Ai-memory None for ai-memory itself (zero-LLM default); it needs an agent CLI such as Claude Code, Codex or OpenCode, which may be paid; Basic Memory None required by Basic Memory; you need an MCP-capable AI client, which may itself be paid
- Hardware: Mem0 (open source) Not documented; depends on the LLM and embedding model you run; Ai-memory Not checked yet; Basic Memory Not documented
- Operating systems: Mem0 (open source) Linux (Ubuntu) is used by the project CI. This is test/build evidence, not a complete Windows/macOS support guarantee.; Ai-memory Linux and macOS supported; Windows via WSL2 supported, native Windows experimental; Basic Memory Windows x86_64, Linux x86_64/ARM64 and macOS are listed in the semantic-search compatibility table; Intel Macs need an ONNX Runtime pin or OpenAI embeddings for local semantic search
- Setup effort: Mem0 (open source) Easy, pip install mem0ai (server via docker compose); Ai-memory Easy; install script then ai-memory setup (PowerShell script on Windows); Basic Memory Easy, uv tool install plus adding the MCP server to your AI client

Stars show popularity, not quality. Check each project page before publishing.

Want share images and a ready video description? Open a project's creator kit.

Numbers: GitHub, fetched nightly. Facts: read from each project's own documentation, with the source on its page. How we check. mem0ai/mem0 ↗akitaonrails/ai-memory ↗basicmachines-co/basic-memory ↗

Mem0 (open source) vs Ai-memory vs Basic Memory

Stars over time

Notes for a video or post

Cookie preferences

Report a problem