Agents keep forgetting, and the fix just became github’s biggest mover this week. vectorize’s…
agents keep forgetting, and the fix just became github’s biggest mover this week. vectorize’s hindsight gained 16k stars in seven days, scores 91.4% on longmemeval, and gives any mcp agent persistent memory under mit.
stateless agents now have an open-source answer.
Context
Verified source: the vectorize-io/hindsight GitHub page, in an undated snapshot, shows 47,936 stars, an MIT license and a creation date of Oct 30, 2025. An ACL Anthology demo paper and an arXiv paper (Dec 14, 2025) describe Hindsight as an agent memory system with retain, recall and reflect operations.
The arXiv paper lists authors at Vectorize.io, The Washington Post and Virginia Tech.
The MIT license and the agent-memory purpose match the sources. The 16,000 stars in seven days, the 91.4% on LongMemEval and the MCP support were not seen in the sources read, so unsupported here, not refuted. The repo is a year old, and the snapshot star count is a total, not a weekly gain. Vectorize publishes a benchmark repo with LongMemEval results, which is where to check the score. 'Stateless agents now have an open-source answer' is the author's opinion.
Related work
- hindsight-benchmarks README ↗LongMemEval and LoComo results.
- arXiv paper ↗Dec 14, 2025.
- ACL Anthology demo paper ↗System demonstration.
Watch next
- Read the hindsight-benchmarks README for the LongMemEval number and how it was run.
Sources
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 1 October 2026 at 04:02 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →