# Hindsight

> Open-source agent memory system from Vectorize focused on agents that learn: retain, recall and reflect operations over memory banks, with an MCP server and a managed cloud.

- id: `hindsight`
- category: Tools (`tools`)
- url: https://hindsight.vectorize.io/
- repo: https://github.com/vectorize-io/hindsight
- docs: https://hindsight.vectorize.io/
- status: active
- pricing: freemium
- license: MIT
- tags: memory, long-term-memory, mcp, self-hosted, open-source
- llms.txt: https://hindsight.vectorize.io/llms.txt
- access notes: MCP server docs: https://hindsight.vectorize.io/developer/mcp-server. Cloud sign-up: https://ui.hindsight.vectorize.io.
- related: Mem0 (https://indexagentica.com/entries/mem0/); Zep (https://indexagentica.com/entries/zep/); Letta (https://indexagentica.com/entries/letta/); Graphiti (https://indexagentica.com/entries/graphiti/); Supermemory (https://indexagentica.com/entries/supermemory/)
- sources: https://github.com/vectorize-io/hindsight , https://vectorize.io/pricing , https://hindsight.vectorize.io/developer/mcp-server , https://hindsight.vectorize.io/llms.txt
- added: 2026-10-18
- updated: 2026-10-18
- last verified: 2026-10-18
- maintainer: Vectorize
- submitted by: agentica-curator
- page: https://indexagentica.com/entries/hindsight/
- json: https://indexagentica.com/api/entries/hindsight.json

Builds observations, mental models and knowledge pages on top of raw memories; Vectorize reports state-of-the-art LongMemEval results and publishes live benchmarks at benchmarks.hindsight.vectorize.io (paper: arXiv 2512.12818). Run the server with Docker or embedded in Python, then use the Python/TypeScript clients, an LLM wrapper, framework and coding-agent integrations, or the per-bank MCP endpoint (`http://localhost:8888/mcp/{bank_id}/` when self-hosted). Self-hosted is MIT and free; Hindsight Cloud is pay-as-you-go on token usage with free credits to start; Enterprise on request.