MIDREAL

Home / hindsight

vectorize-io

hindsight

SurgingSurgingAt least 1,000 stars gained in 7 days, or at least 300 in 24 hours. More on the methodology page

vectorize-io/hindsight

Hindsight: Agent Memory That Learns

PythonCategories: Developer tools

Our summary

Hindsight is an agent memory system that enables AI agents to learn and retain information over time. It stores, recalls, and reflects on memories to improve agent performance on long-term memory tasks.

Who it is for: Developers building AI agents that need persistent memory

What the README claims

  • Achieves state-of-the-art performance on the LongMemEval benchmark Hindsight is the most accurate agent memory system ever tested according to benchmark performance. It has achieved state-of-the-art performance on the LongMemEval benchmark Not checked
  • Works with 25+ LLM providers Hindsight works with **25+ LLM providers** via `HINDSIGHT_API_LLM_PROVIDER` Not checked
  • Offers 60+ integrations **60+ integrations** — most need no code changes. Not checked
  • Can be deployed on multiple platforms including Linux, macOS, and Windows | Platform | Docker | Bare Metal (pip) | Embedded DB (pg0) | |----------|--------|------------------|--------------------| Not checked
  • Eliminates shortcomings of RAG and knowledge graph approaches It eliminates the shortcomings of alternative techniques such as RAG and knowledge graph Too broad to verify

Written by AI from the project's README on 2026-10-09. It does not affect the verdict.

Surging: 1,415 stars gained in 7 days (the rule needs 1,000, or 300 in 24 hours).

7-day star gain 1,415, up from 1,321 the week before.

Commits in the last 30 days: 390, down from 730 30 days earlier.

Gaining 1,415 stars this week, 0.6x its usual pace. Last push 1 day ago.

Verdict

REAL scored 53m ago

Hype
89
Reality
87
Hype Gap
+2
Momentum
0.6x
Confidence
60%
  • Responsive moves Reality +13 points.
  • Maintained moves Reality +12 points.

Rule verdict-2.0, scoring score-2.0. How we score. Backtest.

Alternatives

Projects we track that do a similar job, picked by AI. Not a recommendation.

Find them on

Maintained by

Maintained by 1 primary developer, 2 external contributors in the last 90 days.

  • vectorize-io is a GitHub organization.
  • GitHub account created April 2021.
  • Top contributors by commits: nicoloboschi 57%, cdbartholomew 9%, benfrank241 8%.

Why now 2% of its stars arrived in the last 7 days. Gaining 0.6x its usual weekly pace. No Hacker News posts in the last 7 days.

Stars StarsThe number of GitHub stars on the repository at our latest reading.
62,522
Gain 7d Gain 7dStars gained since our latest reading from at least 7 days ago.
+1,415
Pace Velocity (Nx usual pace)This week's star gain divided by the project's usual weekly gain. The usual gain is the average weekly gain over the 4 weeks before (days 8 to 35 ago), counted as at least 10 stars. 2.0x means twice the usual pace. Without a reading from 35 days ago, the ranking assumes 2% of the stars the project had 7 days ago as its usual weekly gain. More on the methodology page
0.6x usual 2,534 a week
HN points HN pointsHacker News points added up across posts that mention the project, published in the last 7 days.
0 7 days
Downloads DownloadsDownloads per day of the project's package, as the registry (npm or PyPI) reports them.
n/a
Contributors Contributors, all timePeople and anonymous contributors who have ever committed to the repository, as GitHub counts them. A small number is context, not a flaw: many solid projects are kept by one or two people.
291
Last release Latest releaseDays since the latest GitHub release was published.
2 days ago

Gain 24h Gain 24hStars gained since our latest reading from at least 24 hours ago. +215. Forks ForksThe number of GitHub forks of the repository at our latest reading. 7,398. Open issues Open issuesThe number of open issues on the repository at our latest reading, as GitHub counts them. 252. Days since push Days since pushDays since the last push to the repository. 1 day. Archived ArchivedWhether the owner has archived the repository on GitHub. An archived repository is read-only. no. Hacker News posts in 7 days Hacker News postsThe number of Hacker News posts that mention the project, published in the last 7 days.: 0. Watchers WatchersThe number of GitHub users watching the repository for notifications, at our latest reading. 116.

Facts

License
MIT source, checked 22 Nov 2026
Language
Python source, checked 22 Nov 2026
Homepage
https://hindsight.vectorize.io/ source, checked 22 Nov 2026
Last release
v1.2.3, 19 Nov 2026 source, checked 22 Nov 2026
Releases
78 source, checked 20 Nov 2026
Contributors
291 source, checked 20 Nov 2026
Archived
no source, checked 22 Nov 2026

Nerd stuff

DockerSelf-hostedAPI

Languages
Python (detected), TypeScript (detected), MDX (detected), Rust (detected)
Interfaces
OpenAPI (detected)
Deployment
Docker (detected), Helm (detected)
Hardware
CUDA: referenced (detected), onnxruntime-gpu: referenced (detected)
Local models
llama.cpp: referenced (detected), Ollama: referenced (detected), vLLM: referenced (detected)
Auth
OAuth: referenced (detected), OIDC: referenced (detected)
License
MIT (detected)
Package ecosystem
npm (detected), Python packaging (detected)

The Receipts

SourceEvidenceDate
Hacker NewsThread, 2 points, 0 comments5 Oct 2026
Newsletter or feedI need a persistent memory service for LLM agents that offers a generous free tier for prototyping.15 Nov 2026
Newsletter or feedWhy AI Needs a Memory in Medicine: A Plain-Language Look at Agent Memory10 Nov 2026
Newsletter or feed# The 0 / 5 / 20 incident learning curve: watching an agent get better without retraining10 Nov 2026
Newsletter or feedMy Hindsight Debugging Agent Learned to Say "I Don't Know"9 Nov 2026
Newsletter or feedThe Fix Was Already in Our Postmortems. I Built an On-Call Agent That Actually Remembers It.9 Nov 2026
Newsletter or feedWatch an AI Learn in 3 Minutes: A Walkthrough of the TrialSleuth AI Demo9 Nov 2026
Newsletter or feedMY INCIDENT AGENT FORGOT EVERY OUTAGE UNTIL I GAVE IT HINDSIGHT9 Nov 2026
Newsletter or feedMY INCIDENT AGENT FORGOT EVERY OUTAGE UNTILL I GAVE IT HINDSIGHT9 Nov 2026
Newsletter or feedMy Incident Agent Forgot Every Outage Until I Gave It Hindsight9 Nov 2026
Newsletter or feedMy Incident Agent Forgot Every Outage Until I Gave It Hindsight9 Nov 2026
Newsletter or feedMy Incident Agent Forgot Every Outage Until I Gave It Hindsight8 Nov 2026
Newsletter or feedCatch the Risk Before the First Dose - Building an AI Drug Safety Reviewer That Remembers8 Nov 2026
Newsletter or feedWhy I Moved Audit Context out of Prompts, Into Hindsight.8 Nov 2026
Newsletter or feedWhat Changed When I Gave My Audit Agent Hindsight.?8 Nov 2026
Newsletter or feedCalling Hindsight From FastAPI Without Breaking the Event Loop7 Nov 2026
Newsletter or feedI Put Memory Before the LLM: Building a Support Agent That Learns From Failed Fixes.7 Nov 2026
Newsletter or feedHow Hindsight Helped My Sales Agent Remember a Deal-Killing Deadline7 Nov 2026
Newsletter or feedOne Hindsight memory changed what our vision model saw7 Nov 2026
Newsletter or feedEvery Transformer Has a Story: How Hindsight Memory Helps Our Agent Read It7 Nov 2026
Newsletter or feedWhy Our Transformer Agent Remembers Every Oil Test (Built with Hindsight)7 Nov 2026

What changed recently

GitHub release dates we stored. We do not track license changes yet.

Cite this

hindsight is a GitHub project at https://github.com/vectorize-io/hindsight written mainly in Python, described there as "Hindsight: Agent Memory That Learns".

Source: https://midorreal.com/project/vectorize-io-hindsight, checked 22 November 2026. The same facts as JSON: /project/vectorize-io-hindsight.json.

Rank history

Peak day: +4,665 stars on 28 Sep 2026, 55 days ago.

Label timeline

  • 6 Oct 2026: Surging

Stars

24 Oct 202622 Nov 2026
Stars each day Stars each dayThe highest star count we recorded on each day., last 168 days. Without JavaScript this shows the last 30 days.

Events in this window

Dated items we stored, last 30 days. They sit near the chart, they do not explain it.

Stars gained each day Stars gained each dayThe difference in the daily peak star count between consecutive days that both have a reading., between readings on consecutive days. Last 30 days in the fallback.

Packages

- We checked npm, PyPI, Docker Hub, crates.io and Homebrew and found no package that links to this repository.

Signals

SourceWhat we measuredChecked
GitHub62,522 stars, 1,415 gained in 7 days22 Nov 2026
Hacker News1 post stored, 0 points in the last 7 days12 Oct 2026
Feed mentions38 mentions in tracked newsletters and blogs15 Nov 2026
npmNo linked package found-
PyPINo linked package found-
Docker HubNo linked package found-
crates.ioNo linked package found-
HomebrewNo linked package found-
deps.devNot tracked yet-
Hugging FaceNot tracked yet-
BlueskyNot tracked yet-
Stack ExchangeNot tracked yet-
YouTubeNot tracked yet-

Attention vs adoption

Attention: above 52% of tracked projects 52%
Star velocity against all tracked projects

Adoption: not enough data to rank
Downloads, dependents and pulls

Not enough comparable data yet to set attention against adoption. This describes the numbers; it is not a verdict.

Compared with Developer tools

MeasureThis projectCategory median
Star velocity0.60.5
Days since release2.19.2
Contributors, all time2913
Median time to first reply on issues27 hours12 hours
Commits in the last 30 days39041.5

Star velocity: above 51% of Developer tools projects

Days since release: above 20% of Developer tools projects

Contributors, all time: above 93% of Developer tools projects

Median time to first reply on issues: above 63% of Developer tools projects

Commits in the last 30 days: above 85% of Developer tools projects

Compared with the project's first category only. A percentile line appears only where at least 30 projects in the category have the measure. This describes the numbers; it is not a verdict.

Compare with

Hacker News

Points by day Hacker News points by dayPoints on Hacker News posts that mention the project, grouped by the day each post was published. across 1 post and 1 day, 2 points in total.
PostPoints PointsThe points the post has on Hacker News.Comments CommentsThe number of comments on the post on Hacker News.Date
Hacker News post 2 0 5 Oct 2026

Repo health

  • Languages LanguagesShare of the repository's code by bytes, as GitHub's language detection reports it. The five biggest languages are named and the rest are grouped as Other.Python 70%, TypeScript 17%, MDX 9%, Rust 2%, Shell 1%, Other 1%
  • License LicenseThe SPDX license id GitHub detects, and a class: Open source (OSI) if the license is on the Open Source Initiative approved list, Source-available if the code is readable but the license limits use, Unclear if GitHub cannot match a known license, No license detected if it finds none. A public repository without a license is not open source.MIT, Open source (OSI)
  • Repository age Repository ageTime since the repository was created on GitHub. This is the repository, not necessarily the project, which may have existed elsewhere before.12 months, created 30 Oct 2025
  • Release dates Release datesThe date of the first and the latest GitHub release, and the latest release tag. Projects that ship without GitHub releases show none.First release 4 Dec 2025, current version v1.2.3 (19 Nov 2026)

Development

  • Commits in the last 7 days Commits in the last 7 daysCommits to the repository in the last 7 days, as GitHub counts them.100
  • Commits in the last 30 days Commits in the last 30 daysCommits to the repository in the last 30 days, as GitHub counts them.390
  • Commits in the last 90 days Commits in the last 90 daysCommits to the repository in the last 90 days, as GitHub counts them.1,592
  • Contributors, all time Contributors, all timePeople and anonymous contributors who have ever committed to the repository, as GitHub counts them. A small number is context, not a flaw: many solid projects are kept by one or two people.291
  • Releases ReleasesThe number of GitHub releases, and how many days ago the latest one was published.78, latest release 2 days ago
  • Releases in the last 90 days Releases in the last 90 daysHow many GitHub releases were published in the last 90 days.11
  • Issues in the last 30 days Issues in the last 30 daysIssues opened and issues closed in the last 30 days, as GitHub search counts them.417 opened, 349 closed
  • Pull requests merged in the last 30 days Pull requests merged in the last 30 daysPull requests merged in the last 30 days, as GitHub search counts them.357

Maintenance

  • Median time to first reply on issues Median time to first reply on issuesMedian time between an issue being opened and the first comment from someone other than its author, over a sample of the last 30 closed issues. Issues with no reply are left out of the median and counted separately.27 hours
  • Median time to close issues Median time to close issuesMedian time from opening to closing, over a sample of the last 30 closed issues.18 hours
  • Sampled issues with no reply Sampled issues with no replyHow many of the sampled closed issues never got a comment from someone other than their author.7 of 11
  • Stale open issues Stale open issuesOpen issues with no update in the last 90 days, as GitHub search counts them.0
  • Open pull requests Open pull requestsPull requests open now, as GitHub search counts them.10

Hygiene

  • Automated tests or builds (CI) Automated tests or builds (CI)Whether the repository has at least one GitHub Actions workflow file in .github/workflows.Yes
  • A tests folder A tests folderWhether the repository has a top-level folder named tests, test, __tests__ or spec.No
  • A license A licenseWhether GitHub detects a license file in the repository.Yes
  • Contributing guide Contributing guideWhether the repository has a contributing guide.Yes
  • Code of conduct Code of conductWhether GitHub finds a code of conduct in the repository.Yes
  • CODEOWNERS file CODEOWNERS fileWhether the repository has a CODEOWNERS file, which names who reviews changes to which files.No
  • A Dockerfile A DockerfileWhether the repository has a Dockerfile at its top level.No

Security

  • Security policy Security policyWhether the repository has a SECURITY.md or SECURITY.rst file.Yes
  • Unpatched high or critical advisories Unpatched high or critical advisoriesPublished GitHub security advisories rated high or critical on this repository that list a vulnerable version with no patched version.0
  • Signed latest release Signed latest releaseWhether the latest GitHub release has an attached signature file (.sig, .asc or .sigstore).No

Badge

For maintainers: one measured fact, no verdict. First spotted by Mid or Real at 46,277 stars on 6 Oct 2026

Markdown

[![Mid or Real](https://midorreal.com/badge/vectorize-io-hindsight.svg)](https://midorreal.com/project/vectorize-io-hindsight)

HTML

<a href="https://midorreal.com/project/vectorize-io-hindsight"><img src="https://midorreal.com/badge/vectorize-io-hindsight.svg" alt="Mid or Real"></a>

Verdict badge: Mid or Real: REAL It shows the verdict as this page shows it today.

Markdown

[![Mid or Real: REAL](https://midorreal.com/badge/vectorize-io-hindsight.svg?style=verdict)](https://midorreal.com/project/vectorize-io-hindsight)

HTML

<a href="https://midorreal.com/project/vectorize-io-hindsight"><img src="https://midorreal.com/badge/vectorize-io-hindsight.svg?style=verdict" alt="Mid or Real: REAL"></a>

Passport

Copy these facts into a post, a README or a page. Cite as "Source: Mid or Real". Full record: JSON.




First tracked 6 Oct 2026 at 46,277 stars.

Projects blowing up

How we call a verdict

Is this your project? Claim it

Figures by method 1.0