Hindsight vs Basic Memory vs Ai-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.

Hindsightvectorize-io/hindsight

Basic Memorybasicmachines-co/basic-memory

Ai-memoryakitaonrails/ai-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

3 of 3 jobs

2 of 3 jobs

3 of 3 jobs

All 3

Popularity and activity (from GitHub)

Stars

52,038Top

4,295

11,924

—

Gain this week

Unknown

—

Signal

Building history

—

Commits / 4 wk

455

216

1,156Top

—

Latest release

v1.0.0 · 2026-10-13

v0.23.2 · 2026-08-25

v3.1.2 · 2026-10-20Top

—

Commits / 12 wk

1,394

714

1,917

—

People committing / 12 mo

100+

—

Issues opened / closed, 30 days

473 / 382

74 / 70

195 / 196

—

Facts, with sources on each project page

Runs on my machine?Differs

Yes, Docker, pip or embedded Python on your own machine

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

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

Hosted by the vendor

Code licenceDiffers

MIT

AGPL-3.0 (copyleft)

MIT

—

Model weights licenceDiffers

No bundled LLM; licence depends on the model you connect

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

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

—

Commercial useDiffers

Yes, MIT code

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

Yes, MIT allows commercial use

—

Paid services needed?Differs

Needs an LLM; local Ollama, LM Studio or llama.cpp work, hosted APIs and Hindsight Cloud are optional

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

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

Subscription

HardwareDiffers

Full API image 1.5 GB RAM minimum (2 GB recommended), slim 512 MB; PostgreSQL 512 MB+; 2 vCPUs on CPU only is fine for development; GPU helps the reranker in production

Not documented

Not checked yet

—

Operating systemsDiffers

Linux (x86_64, ARM64), macOS (Apple Silicon; Intel via slim package) and Windows x86_64

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

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

—

Setup effortDiffers

Easy; one Docker command or pip install hindsight-all, plus an LLM provider setting

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

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

—

Stars over time

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

Hindsight
Basic Memory
Ai-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.

Hindsight vs Basic Memory vs Ai-memory (as alternatives to Mem0 Platform)
Figures from RepoQuarry, 21 Oct 2026. Sources: https://repoquarry.dev/compare?ids=hindsight,basic-memory,ai-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
Hindsight: free software; does 3 of 3 Mem0 Platform jobs
Basic Memory: free software; does 2 of 3 Mem0 Platform jobs
Ai-memory: free software; does 3 of 3 Mem0 Platform jobs

- Hindsight: 52,038 GitHub stars, 1,394 commits in 12 weeks, licence MIT
- Basic Memory: 4,295 GitHub stars, 714 commits in 12 weeks, licence AGPL-3.0 (copyleft)
- Ai-memory: 11,924 GitHub stars, 1,917 commits in 12 weeks, licence MIT

Where they differ:
- Runs on my machine?: Hindsight Yes, Docker, pip or embedded Python on your own machine; Basic Memory Yes, local files plus a SQLite index; air-gapped use supported; Ai-memory Yes, a single local binary and server; Docker image also available
- Code licence: Hindsight MIT; Basic Memory AGPL-3.0 (copyleft); Ai-memory MIT
- Model weights licence: Hindsight No bundled LLM; licence depends on the model you connect; Basic Memory No separate model weights (optional FastEmbed models download on first use); Ai-memory No single model licence. The default path makes no LLM calls; optional LLM and embedding models have separate provider/model terms.
- Commercial use: Hindsight Yes, MIT code; Basic Memory Yes, under AGPL-3.0 copyleft terms (share source of modified versions offered over a network); Ai-memory Yes, MIT allows commercial use
- Paid services needed?: Hindsight Needs an LLM; local Ollama, LM Studio or llama.cpp work, hosted APIs and Hindsight Cloud are optional; Basic Memory None required by Basic Memory; you need an MCP-capable AI client, which may itself be paid; 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
- Hardware: Hindsight Full API image 1.5 GB RAM minimum (2 GB recommended), slim 512 MB; PostgreSQL 512 MB+; 2 vCPUs on CPU only is fine for development; GPU helps the reranker in production; Basic Memory Not documented; Ai-memory Not checked yet
- Operating systems: Hindsight Linux (x86_64, ARM64), macOS (Apple Silicon; Intel via slim package) and Windows x86_64; 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; Ai-memory Linux and macOS supported; Windows via WSL2 supported, native Windows experimental
- Setup effort: Hindsight Easy; one Docker command or pip install hindsight-all, plus an LLM provider setting; Basic Memory Easy, uv tool install plus adding the MCP server to your AI client; Ai-memory Easy; install script then ai-memory setup (PowerShell script on Windows)

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. vectorize-io/hindsight ↗basicmachines-co/basic-memory ↗akitaonrails/ai-memory ↗

Hindsight vs Basic Memory vs Ai-memory

Stars over time

Notes for a video or post

Cookie preferences

Report a problem