StackMap
Subscribe

hindsight vs Memoria

Agent memory that learns, not just recalls: retain/recall/reflect API over Postgres, SOTA on LongMemEval. Self-host via Docker with UI; Python/TS clients, any LLM provider. — versus — Rust memory layer for AI agents with Git-style version control — snapshot, branch, merge and rollback over MatrixOne's copy-on-write engine, plus hybrid vector + full-text retrieval.

The curated verdict

Both add governance to agent memory; hindsight is retain/recall/reflect over Postgres, Memoria is version-controlled 'Git for memory' with auditable snapshots.

hindsightMemoria
Stars19k422
Forks1.2k53
LanguagePythonRust
LicenseMITApache-2.0
Last activity3 days ago27 days ago
Topicsmemory, agentsmemory
Curated connections44

hindsight — the curator's take

Pick it when you want a deployable memory *service* whose pitch is learning — agents that get better over time, not a transcript search. The LongMemEval lead was independently reproduced (Virginia Tech, Washington Post), which is more than most memory vendors offer, and the LLM side is pluggable down to Ollama/LM Studio for fully-local stacks. NOT an embedded library: you run a Docker service with Postgres and talk to it over HTTP — overkill for a single coding agent wanting session notes. The ™ and Hindsight Cloud signal a commercial trajectory; watch where the open/paid line lands.

Memoria — the curator's take

Pick it when memory auditability and reversibility matter — you want to branch an agent's memory, roll back a bad write, or trace the provenance of every fact, and you're fine running MatrixOne underneath. Overkill if you just need a simple recall store (memmachine, memmolt) or fully-local files (memanto) — the versioning engine and DB dependency are the cost. Young project, Apache-2.0.