> ## Documentation Index
> Fetch the complete documentation index at: https://gligabao.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# gligabao

> Minimal memory system for AI. A small, self-hosted HTTP service that turns text into a temporal knowledge graph and answers questions from it.

![gligabao](https://github.com/user-attachments/assets/a4cf6b9f-2bdb-4c16-8ed4-558eca33e4a7)

## Long-term memory for your AI application

gligabao is a small, self-hosted HTTP service. You send it free-form text; it turns that text into a knowledge graph. Later you ask questions in natural language and it answers from what it stored, **citing the facts it used**.

> **[Quickstart](https://gligabao.mintlify.site/getting-started/quickstart.md)**
>
> Build the binary, start the server and remember your first fact in minutes.

> **[How it works](https://gligabao.mintlify.site/getting-started/how-it-works.md)**
>
> Remember, query and the bi-temporal graph underneath.

> **[API reference](https://gligabao.mintlify.site/api-reference/overview.md)**
>
> Every endpoint: remember, query, datasets, graph export, ontologies, timeseries.

> **[Embed in Go](https://gligabao.mintlify.site/embedding/go-library.md)**
>
> Use gligabao as a library inside your own Go program.

## The two core calls

```sh Remember theme={null}
curl -X POST localhost:7878/v1/gb/remember \
  -H 'content-type: application/json' \
  -d '{"user_id": "u1", "text": "Alice works at Acme and lives in Paris."}'
```

```sh Query theme={null}
curl -X POST localhost:7878/v1/gb/query \
  -H 'content-type: application/json' \
  -d '{"user_id": "u1", "query": "Where does Alice work?"}'
```

**1. Remember**

An LLM extracts *entities* and *edges* (relations such as `works_at`) from the text. Entities are deduplicated, and each fact is anchored to the artifact it came from and records when it was true.

**2. Query**

The query finds relevant entities, the surrounding subgraph is expanded by one hop, and an LLM answers using only that context. The response includes the evidence behind the answer.

**3. Store**

SQLite (a single file, the default) or PostgreSQL, plus an embedded or hosted vector store.

## Explore

> **[Temporal facts](https://gligabao.mintlify.site/concepts/temporal.md)**
>
> Bi-temporal edges keep history instead of deleting it.

> **[Datasets](https://gligabao.mintlify.site/concepts/datasets.md)**
>
> Isolated, per-user containers for memory.

> **[Sessions](https://gligabao.mintlify.site/concepts/sessions.md)**
>
> Trace every fact back to the run it came from.

> **[Images](https://gligabao.mintlify.site/guides/images.md)**
>
> Read text and themes from images.

> **[Timeseries](https://gligabao.mintlify.site/guides/timeseries.md)**
>
> Anchor values over time to entities and facts.

> **[Geo](https://gligabao.mintlify.site/guides/geo.md)**
>
> Coordinates for the entities that are places.

> **[Evals](https://gligabao.mintlify.site/evals/evals.md)**
>
> End-to-end checks recorded as ATIF trajectories.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.