Skip to content
RepoQuarry

Opencode 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.

Also replaces Mem0 Platform: + Claude-Mem+ Mem0 (open source)+ Ai-memory+ Basic Memory

Opencodeanomalyco/opencode
Hindsightvectorize-io/hindsight
Mem0 Platformpaid product
Cost and coverage
Price
$0 software; you run it
$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
No: No
Partial: Partly
Confirmed: Yes
Memory for coding agents
Partial: Partly
Partial: Partly
Confirmed: Yes
Knowledge graph memory
No: No
Partial: Partly
Confirmed: Yes
Jobs covered
1 of 3 jobs
3 of 3 jobs
All 3
Popularity and activity (from GitHub)
Stars
218,961Top
52,038
—
Gain this week
Unknown
Unknown
—
Signal
Building history
Building history
—
Commits / 4 wk
986Top
455
—
Latest release
v1.19.3 · 2026-10-16Top
v1.0.0 · 2026-10-13
—
Commits / 12 wk
2,164
1,394
—
People committing / 12 mo
420+
100+
—
Issues opened / closed, 30 days
3742 / 4694
473 / 382
—
Facts, with sources on each project page
Runs on my machine?Differs
Confirmed: Yes, CLI and desktop app
Confirmed: Yes, Docker, pip or embedded Python on your own machine
Hosted by the vendor
Code licence
Confirmed: MIT
Confirmed: MIT
—
Model weights licenceDiffers
Partial: No single bundled model licence. OpenCode connects to models/providers; their individual terms apply.
Confirmed: No bundled LLM; licence depends on the model you connect
—
Commercial use
Confirmed: Yes, MIT code
Confirmed: Yes, MIT code
—
Paid services needed?Differs
Partial: Needs a model provider: local models via Ollama, LM Studio or llama.cpp, or a paid API
Partial: Needs an LLM; local Ollama, LM Studio or llama.cpp work, hosted APIs and Hindsight Cloud are optional
Subscription
HardwareDiffers
Unknown: Not checked yet
Confirmed: 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
Confirmed: Windows, macOS and Linux (CLI and desktop app)
Confirmed: Linux (x86_64, ARM64), macOS (Apple Silicon; Intel via slim package) and Windows x86_64
—
Setup effortDiffers
Confirmed: Easy; one-line install script, npm or brew
Confirmed: 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.

  • Opencode
  • Hindsight
218,96133,118 2026-10-152026-10-21 Tracked daily begins 2026-10-15Opencode, 2026-10-19: 216,871 stars, trackedOpencode, 2026-10-20: 218,068 stars, trackedOpencode, 2026-10-21: 218,961 stars, trackedHindsight, 2026-10-15: 50,013 stars, trackedHindsight, 2026-10-16: 50,199 stars, trackedHindsight, 2026-10-17: 50,610 stars, trackedHindsight, 2026-10-18: 51,073 stars, trackedHindsight, 2026-10-19: 51,340 stars, trackedHindsight, 2026-10-20: 51,761 stars, trackedHindsight, 2026-10-21: 52,038 stars, tracked
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.

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. anomalyco/opencode ↗vectorize-io/hindsight ↗

Cookie preferences

Choose what we may store in your browser. You can change this any time from Cookie settings in the footer.

Essential

Security, and remembering this choice. rq-consent · 12 months

Always on