Basic Memory vs Claude-Mem vs Hindsight

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.

Basic Memorybasicmachines-co/basic-memory

Claude-Memthedotmack/claude-mem

Hindsightvectorize-io/hindsight

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

2 of 3 jobs

1 of 3 jobs

3 of 3 jobs

All 3

Popularity and activity (from GitHub)

Stars

4,295

101,972Top

52,038

—

Gain this week

Unknown

—

Signal

Building history

—

Commits / 4 wk

216

744Top

455

—

Latest release

v0.23.2 · 2026-08-25

v15.0.1 · 2026-10-20Top

v1.0.0 · 2026-10-13

—

Commits / 12 wk

714

1,074

1,394

—

People committing / 12 mo

100+

—

Issues opened / closed, 30 days

74 / 70

141 / 129

473 / 382

—

Facts, with sources on each project page

Runs on my machine?Differs

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

Yes, local worker service with a SQLite database

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

Hosted by the vendor

Code licenceDiffers

AGPL-3.0 (copyleft)

Apache-2.0 (open core; hosted cloud and enterprise features are not in the repo)

MIT

—

Model weights licenceDiffers

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

No bundled model; uses the LLM provider you pick

No bundled LLM; licence depends on the model you connect

—

Commercial useDiffers

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

Yes, Apache-2.0 code

Yes, MIT code

—

Paid services needed?Differs

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

Needs a coding agent and an LLM (Anthropic plan, OpenRouter or Gemini key, or paid claude-mem observer); no local model option documented

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

Subscription

HardwareDiffers

Not documented

Not documented; software needs Node.js 20+, Bun and uv

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

—

Operating systemsDiffers

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

Windows setup notes in the README; macOS and Linux not stated explicitly

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

—

Setup effortDiffers

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

Easy, npx claude-mem install or the Claude Code plugin marketplace

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

—

Stars over time

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

Basic Memory
Claude-Mem
Hindsight

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.

Basic Memory vs Claude-Mem vs Hindsight (as alternatives to Mem0 Platform)
Figures from RepoQuarry, 21 Oct 2026. Sources: https://repoquarry.dev/compare?ids=basic-memory,claude-mem,hindsight&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
Basic Memory: free software; does 2 of 3 Mem0 Platform jobs
Claude-Mem: free software; does 1 of 3 Mem0 Platform jobs
Hindsight: free software; does 3 of 3 Mem0 Platform jobs

- Basic Memory: 4,295 GitHub stars, 714 commits in 12 weeks, licence AGPL-3.0 (copyleft)
- Claude-Mem: 101,972 GitHub stars, 1,074 commits in 12 weeks, licence Apache-2.0 (open core; hosted cloud and enterprise features are not in the repo)
- Hindsight: 52,038 GitHub stars, 1,394 commits in 12 weeks, licence MIT

Where they differ:
- Runs on my machine?: Basic Memory Yes, local files plus a SQLite index; air-gapped use supported; Claude-Mem Yes, local worker service with a SQLite database; Hindsight Yes, Docker, pip or embedded Python on your own machine
- Code licence: Basic Memory AGPL-3.0 (copyleft); Claude-Mem Apache-2.0 (open core; hosted cloud and enterprise features are not in the repo); Hindsight MIT
- Model weights licence: Basic Memory No separate model weights (optional FastEmbed models download on first use); Claude-Mem No bundled model; uses the LLM provider you pick; Hindsight No bundled LLM; licence depends on the model you connect
- Commercial use: Basic Memory Yes, under AGPL-3.0 copyleft terms (share source of modified versions offered over a network); Claude-Mem Yes, Apache-2.0 code; Hindsight Yes, MIT code
- Paid services needed?: Basic Memory None required by Basic Memory; you need an MCP-capable AI client, which may itself be paid; Claude-Mem Needs a coding agent and an LLM (Anthropic plan, OpenRouter or Gemini key, or paid claude-mem observer); no local model option documented; Hindsight Needs an LLM; local Ollama, LM Studio or llama.cpp work, hosted APIs and Hindsight Cloud are optional
- Hardware: Basic Memory Not documented; Claude-Mem Not documented; software needs Node.js 20+, Bun and uv; 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
- Operating systems: 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; Claude-Mem Windows setup notes in the README; macOS and Linux not stated explicitly; Hindsight Linux (x86_64, ARM64), macOS (Apple Silicon; Intel via slim package) and Windows x86_64
- Setup effort: Basic Memory Easy, uv tool install plus adding the MCP server to your AI client; Claude-Mem Easy, npx claude-mem install or the Claude Code plugin marketplace; Hindsight Easy; one Docker command or pip install hindsight-all, plus an LLM provider setting

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. basicmachines-co/basic-memory ↗thedotmack/claude-mem ↗vectorize-io/hindsight ↗

Basic Memory vs Claude-Mem vs Hindsight

Stars over time

Notes for a video or post

Cookie preferences

Report a problem