---
title: "What is Hindsight agent memory and how does it work?"
description: "Hindsight is an open-source memory system for AI agents from Vectorize: it extracts facts from conversations and offers retain, recall and reflect."
image: "https://bombos.ai/assets/og-en-v2.png"
---

# What is Hindsight agent memory and how does it work?

Short answer

Hindsight is an open-source, MIT-licensed long-term memory system for AI agents, built by Vectorize. Instead of storing raw conversations, it extracts facts, links them to entities and time, and exposes three operations: retain, recall and reflect. Recall runs semantic, keyword, graph and temporal search in parallel. You can self-host it on Postgres or use Hindsight Cloud.

*Piet Baudoin · published November 17, 2026 · November 17, 2026*

## What Hindsight actually stores

Hindsight is a memory server you put next to an agent. Its site puts the design choice plainly: “Hindsight does not store conversations.” When you send it a conversation or a document, a language model pulls out individual facts, gives them a time range where possible, links them to the people, companies and things they mention, and stores them in Postgres with pgvector.

The research paper behind it, “Hindsight is 20/20” (December 2025, by authors from Vectorize.io, Virginia Tech and The Washington Post), sorts those facts into four networks:

| Network | What it holds | Example |
| --- | --- | --- |
| World | Objective facts about the outside world | “The client’s fiscal year ends in March” |
| Experience | What the agent itself did and experienced | “I sent the draft on Tuesday and got edits back” |
| Opinion | Subjective judgments with a confidence score that can change | “This client prefers short summaries (confidence 0.7)” |
| Observation | Neutral summaries of an entity, built from the facts | A profile of one customer |

The current product site uses slightly different words: world facts, experience facts, observations, mental models and pages. A mental model is a standing answer to a question such as “what are this user’s preferences?”, which Hindsight keeps up to date in the background so reading it needs no LLM call.

## Retain, recall, reflect

Everything goes through three calls, available from Python, TypeScript, Go, a CLI, HTTP and MCP:

1.  **Retain** stores what happened. Extraction, entity linking and graph building run behind this call.
2.  **Recall** searches it back. Four searches run in parallel: semantic (vectors), BM25 keywords, graph (following entity links) and temporal (matching time ranges). The results are fused by rank, reranked by a cross-encoder and cut to a token budget, not a fixed number of results.
3.  **Reflect** reasons over the bank. It recalls memories and then writes an answer shaped by the bank’s background and disposition, and it can form new opinions along the way.

Memories live in **banks**. The README describes a bank as an isolated store, meant as one “brain” for one user, agent or project, with no leakage between banks. Each bank gets its own MCP endpoint at `/mcp/{bank_id}/`, switched on by default.

## How to run it

The quick start is a single Docker container that exposes the API on port 8888 and a UI on port 9999, with your LLM key passed as `HINDSIGHT_API_LLM_API_KEY`. For production there are Docker Compose with an external Postgres, Helm for Kubernetes and a pip install. More than 25 LLM providers can do the extraction, from OpenAI and Anthropic to local models through Ollama or llama.cpp. If you do not want to host it, Hindsight Cloud is the managed version. The code is MIT-licensed.

## The misunderstanding about the benchmarks

Hindsight’s site shows high scores, for example 94.6% on LongMemEval-S and 92.0% on LoCoMo, against an unnamed “next best” system. Those are vendor-reported numbers. The paper reports lower figures for its own setups (83.6% on LongMemEval with a 20B open model, 91.4% with Gemini 3 Pro writing the answers) and notes that the authors could not reproduce a competitor’s claimed LoCoMo score. The paper also says the benchmarks test factual recall, not the opinion and disposition features that make Hindsight different. So the scores tell you Hindsight retrieves facts well in those tests; they do not tell you it will remember your team’s way of working. How these benchmarks are built is explained in [How do you evaluate LLM agent memory?](https://bombos.ai/en/questions/ai-memory/how-to-evaluate-llm-agent-memory/)

## What this means for a team

Hindsight is built around banks per user or per agent, which is the right default for privacy. For a team it means you decide the layout yourself: one bank per person keeps knowledge apart, one shared bank mixes everyone’s facts and opinions together, and the README mentions tenant and auth extension points but gives little detail. You also run and secure the server, and every write passes through an LLM that can store something wrong, which is a reason to read [What is memory poisoning in AI agents?](https://bombos.ai/en/questions/ai-memory/what-is-memory-poisoning-in-ai-agents/) before you let agents write freely. For a comparison with Mem0, Zep and Letta, see [Mem0 vs Zep vs Supermemory vs Letta](https://bombos.ai/en/questions/ai-memory/mem0-vs-zep-vs-supermemory-vs-letta/).

## Where Bombos fits

Hindsight is a strong building block if you want to wire memory into your own agent and run it yourself. Bombos starts from the team instead: one shared memory for every AI tool the team already uses, from Claude and ChatGPT to Copilot, Cursor and your own agents, with team knowledge, learned rules about how you work and the knowledge already in mail, documents and repos, and you can see what each answer rests on. It runs in our cloud or on your own server, and one person can try the plugin first for their own agents.

## Related questions

Is Hindsight free to use?

The code is open source under the MIT license, so self-hosting costs only your own infrastructure and the LLM calls it makes. Hindsight Cloud is a managed version; its site mentions free credit at sign-up but lists no price tiers.

Does Hindsight need an LLM?

Yes. Extracting facts, resolving entities and running reflect all use a language model. The Docker quick start asks for an LLM API key, and the README lists more than 25 providers, including local options such as Ollama and llama.cpp.

Can I use Hindsight with Claude Code or Cursor?

Hindsight's site lists integrations for more than 20 coding harnesses, including Claude Code, Codex CLI and Cursor CLI, and every memory bank exposes an MCP endpoint with retain, recall and reflect as tools.

Are Hindsight's benchmark scores independent?

The scores on its site and in its paper are reported by the authors, most of whom work at Vectorize. The paper itself notes it could not reproduce one competitor's LoCoMo claim, which shows how hard these numbers are to compare.

## Sources

1.  [Hindsight (official site, Vectorize)](https://hindsight.vectorize.io/)
2.  [vectorize-io/hindsight (GitHub README)](https://github.com/vectorize-io/hindsight)
3.  [Hindsight is 20/20: Building Agent Memory that Retains, Recalls, and Reflects (arXiv 2512.12818)](https://arxiv.org/html/2512.12818v1)

## What does your AI forget?

1.  01You tell us which AI you use and where it keeps starting over.
2.  02We show what a shared memory changes there, on your own examples.
3.  03You keep the plan, with or without Bombos.

![Piet Baudoin](https://bombos.ai/assets/team/piet-klein.jpg)

**Piet Baudoin**You talk to Piet, from the Bombos teamDutch team from Utrecht and Nijmegen · data in Europe

## More questions about AI memory

-   [How does memory work in an n8n AI agent?](https://bombos.ai/en/questions/ai-memory/how-does-memory-work-in-n8n-ai-agents/)
-   [What is Vertex AI Memory Bank and how does it work?](https://bombos.ai/en/questions/ai-memory/what-is-vertex-ai-memory-bank/)
-   [How does Anthropic's memory tool for Claude agents work?](https://bombos.ai/en/questions/ai-memory/how-does-the-claude-memory-tool-work/)
-   [What are the types of memory in AI agents?](https://bombos.ai/en/questions/ai-memory/types-of-ai-agent-memory/)
-   [What are the privacy risks of AI agent memory?](https://bombos.ai/en/questions/ai-memory/privacy-risks-of-ai-agent-memory/)
-   [What is memory poisoning in AI agents, and how do you defend against it?](https://bombos.ai/en/questions/ai-memory/what-is-memory-poisoning-in-ai-agents/)
-   [What is ReasoningBank, the memory framework that learns from failures?](https://bombos.ai/en/questions/ai-memory/what-is-reasoningbank/)
-   [What is SimpleMem (Efficient Lifelong Memory for LLM Agents)?](https://bombos.ai/en/questions/ai-memory/what-is-simplemem/)

[All questions about AI memory →](https://bombos.ai/en/questions/ai-memory/)


---

```json
{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://bombos.ai/#organization","name":"Bombos","url":"https://bombos.ai/","logo":"https://bombos.ai/assets/bombos-bee.png","description":"Bombos is the memory layer under every AI your team uses. One shared memory for Claude, ChatGPT, Copilot, Cursor and your own agents, that learns how you work.","sameAs":["https://www.linkedin.com/company/bombos-ai","https://www.youtube.com/@truebombos","https://www.instagram.com/truebombos/","https://bsky.app/profile/bombostrue.bsky.social","https://www.threads.com/@truebombos","https://mastodon.social/@Bombos","https://www.tiktok.com/@truebombos","https://t.me/truebombos","https://www.pinterest.com/truebombos/","https://github.com/bombos-ai","https://linktr.ee/bombos.ai","https://bombosai.substack.com","https://hashnode.com/@bombosai","https://hackernoon.com/u/bombos","https://dev.to/bombos"],"email":"info@bombos.ai","areaServed":["NL","Europe"],"knowsLanguage":["nl","en"],"contactPoint":{"@type":"ContactPoint","email":"info@bombos.ai","contactType":"sales","url":"https://bombos.ai/en/contact/","availableLanguage":["nl","en"]}},{"@type":"WebSite","@id":"https://bombos.ai/#website","name":"Bombos","url":"https://bombos.ai/","inLanguage":["nl-NL","en"],"publisher":{"@id":"https://bombos.ai/#organization"}}]}

{"@context":"https://schema.org","@type":"Article","headline":"What is Hindsight agent memory and how does it work?","description":"Hindsight is an open-source memory system for AI agents from Vectorize: it extracts facts from conversations and offers retain, recall and reflect.","abstract":"Hindsight is an open-source, MIT-licensed long-term memory system for AI agents, built by Vectorize. Instead of storing raw conversations, it extracts facts, links them to entities and time, and exposes three operations: retain, recall and reflect. Recall runs semantic, keyword, graph and temporal search in parallel. You can self-host it on Postgres or use Hindsight Cloud.","datePublished":"2026-11-17T00:00:00.000Z","dateModified":"2026-11-17T00:00:00.000Z","author":{"@type":"Person","name":"Piet Baudoin"},"publisher":{"@type":"Organization","@id":"https://bombos.ai/#organization","name":"Bombos","logo":{"@type":"ImageObject","url":"https://bombos.ai/assets/bombos-bee.png"}},"image":"https://bombos.ai/assets/og-en-v2.png","mainEntityOfPage":"https://bombos.ai/en/questions/ai-memory/what-is-hindsight-agent-memory/","inLanguage":"en-US","isPartOf":{"@type":"CollectionPage","name":"AI memory","url":"https://bombos.ai/en/questions/ai-memory/"},"citation":[{"@type":"CreativeWork","name":"Hindsight (official site, Vectorize)","url":"https://hindsight.vectorize.io/"},{"@type":"CreativeWork","name":"vectorize-io/hindsight (GitHub README)","url":"https://github.com/vectorize-io/hindsight"},{"@type":"CreativeWork","name":"Hindsight is 20/20: Building Agent Memory that Retains, Recalls, and Reflects (arXiv 2512.12818)","url":"https://arxiv.org/html/2512.12818v1"}]}

{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Bombos","item":"https://bombos.ai/en/"},{"@type":"ListItem","position":2,"name":"Questions","item":"https://bombos.ai/en/questions/"},{"@type":"ListItem","position":3,"name":"AI memory","item":"https://bombos.ai/en/questions/ai-memory/"},{"@type":"ListItem","position":4,"name":"What is Hindsight agent memory and how does it work?","item":"https://bombos.ai/en/questions/ai-memory/what-is-hindsight-agent-memory/"}]}

{"@context":"https://schema.org","@type":"FAQPage","mainEntity":[{"@type":"Question","name":"Is Hindsight free to use?","acceptedAnswer":{"@type":"Answer","text":"The code is open source under the MIT license, so self-hosting costs only your own infrastructure and the LLM calls it makes. Hindsight Cloud is a managed version; its site mentions free credit at sign-up but lists no price tiers."}},{"@type":"Question","name":"Does Hindsight need an LLM?","acceptedAnswer":{"@type":"Answer","text":"Yes. Extracting facts, resolving entities and running reflect all use a language model. The Docker quick start asks for an LLM API key, and the README lists more than 25 providers, including local options such as Ollama and llama.cpp."}},{"@type":"Question","name":"Can I use Hindsight with Claude Code or Cursor?","acceptedAnswer":{"@type":"Answer","text":"Hindsight's site lists integrations for more than 20 coding harnesses, including Claude Code, Codex CLI and Cursor CLI, and every memory bank exposes an MCP endpoint with retain, recall and reflect as tools."}},{"@type":"Question","name":"Are Hindsight's benchmark scores independent?","acceptedAnswer":{"@type":"Answer","text":"The scores on its site and in its paper are reported by the authors, most of whom work at Vectorize. The paper itself notes it could not reproduce one competitor's LoCoMo claim, which shows how hard these numbers are to compare."}}]}
```
