Skip to content
RepoQuarry

Hindsight vectorize-io/hindsight

Self-hostable agent memory server that extracts facts, entities and relationships from conversations and recalls them for AI agents.

Hindsight at a glance

Checked 15 Oct 2026

Hindsight by Vectorize is an MIT-licensed memory server (v1.0.0, October 2026) with retain, recall and reflect operations, memory banks, an MCP endpoint per bank and plugins for coding agents such as Claude Code and Cursor. It stores memories in PostgreSQL with pgvector (embedded or external). It needs an LLM to extract facts: hosted APIs or local Ollama, LM Studio or llama.cpp. Runs via Docker, pip or Helm; a paid Hindsight Cloud also exists. Hardware requirements are not documented.

Cite this pageRepoQuarry. “Hindsight.” Checked 15 Oct 2026. https://repoquarry.dev/projects/hindsight

How much of Mem0 Platform does it replace?

3 of 3 jobs. Covers the same memory jobs when self-hosted; you run the server and supply an LLM yourself.

Partial: Long-term memory for chat assistants Partial replacement
Partial: Memory for coding agents Partial replacement
Partial: Knowledge graph memory Partial replacement

Facts, with sources

Every answer links to where we found it. We read the documentation; we did not install it.

Report a correction
QuestionAnswerSourceChecked
Runs on my machine? Confirmed: Yes, Docker, pip or embedded Python on your own machine github.com · hindsight#quick-start ↗ 1d ago
Code licence Confirmed: MIT github.com · LICENSE ↗ 1d ago
Model weights licence Confirmed: No bundled LLM; licence depends on the model you connect github.com · hindsight#quick-start ↗ 1d ago
Commercial use Confirmed: Yes, MIT code github.com · LICENSE ↗ 1d ago
Paid services needed? Partial: Needs an LLM; local Ollama, LM Studio or llama.cpp work, hosted APIs and Hindsight Cloud are optional fully local (`ollama`, `lmstudio`, `llamacpp`), any OpenAI-compatible endpoint, and gateways github.com · hindsight#1-start-a-server ↗ 1d ago
Hardware Unknown: Not documented in the README; depends on the LLM you connect github.com · hindsight#readme ↗ 1d ago
Operating systems Confirmed: Linux (x86_64, ARM64), macOS (Apple Silicon; Intel via slim package) and Windows x86_64 Intel Macs: use `hindsight-all-slim` github.com · hindsight#supported-platforms ↗ 1d ago
Setup effort Confirmed: Easy; one Docker command or pip install hindsight-all, plus an LLM provider setting pip install hindsight-all -U github.com · hindsight#quick-start ↗ 1d ago

Get the weekly top 5 and what’s new, every Monday

We’ll email you once a week. Unsubscribe any time. We never share your email.

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