OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Memory & RAG

Cortexadb

CortexaDB is a Rust-based embedded database for persistent AI-agent memory. It stores information in a single-file, no-server design and combines vector search, graph relationships and temporal indexing; its documented interfaces include Python and Rust.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Cortexadb — OpenViST project profile in Agent Memory & RAG.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Consider CortexaDB when an agent application needs persistent local memory and combined semantic, relationship-based and time-aware retrieval without operating a separate database server.

Who it is for

  • Developers building AI agents that need persistent, searchable memory.
  • Python or Rust application developers seeking embedded storage rather than a separate database server.

Documented uses

  • Store facts that an agent needs to retain beyond its current context.
  • Retrieve memories by semantic similarity, relationships or time-based recency.
  • Connect related memories and query those links alongside vector matches.
Before you choose

Requirements & limits

The repository is public and lists an Apache-2.0 license. The README describes the release as available under MIT and Apache-2.0, and documents installation through PyPI for Python and Cargo for Rust.

  • The design is embedded and single-file, rather than a separately running database service.
  • The README's example uses the Python package and OpenAIEmbedder; the repository also documents adding the library through Cargo for Rust.
  • The README describes HNSW (USearch) indexing, WAL-backed storage and optional Python extras for PDF and DOCX support.
  • Project-published benchmark measurements are specific to an M-series Mac and 10,000 embeddings at 384 dimensions.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install CortexaDB for Python

Add the documented Python package to an environment for an agent-memory project.

Before you start

  • A Python environment with pip.

Steps

  1. Install the package with the command below.

    Documented command
    pip install cortexadb

  2. For the optional PDF and DOCX support, install the command below.

    Documented command
    pip install cortexadb[docs,pdf]

Expected outcome

The README's Python package installation step is complete; using the database requires the application code and API steps described in the project documentation.

Guide limitations

  • The instructions do not specify Python versions or operating-system compatibility.
Documentation 1 ↗
Source-based practical guide

Add and query linked memories in Python

Follow the README example to create a local database, add two facts, link them and issue a graph-aware query.

Before you start

  • CortexaDB installed for Python.
  • The README example's OpenAIEmbedder provider.

Steps

  1. Open agent.mem with CortexaDB.open("agent.mem", embedder=OpenAIEmbedder()).

  2. Add two memory strings with db.add(...).

  3. Connect the returned memory IDs using db.connect(mid1, mid2, "relates_to").

  4. Build a query, set a result limit, call .use_graph(), and execute it.

Expected outcome

The example returns query hits from the linked memory records.

Guide limitations

  • The README example uses the OpenAI embedder; it does not establish the requirements or configuration for other embedding providers.
  • The sample's query outcome is illustrative documentation, not an independently verified execution.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Vector search

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
CortexadbStore facts that an agent needs to retain beyond its current context.Linux, macOS, Self-hosted, ServerThe repository is public and lists an Apache-2.0 license. The README describes the release as available under MIT and Apache-2.0, and documents installation through PyPI for Python and Cargo for Rust.
KektordbSave and retrieve semantic memories across agent sessions.Self-hosted, ServerThe README describes self-hosted use and displays an Apache 2.0 license badge.
LongbowStore and retrieve dense or sparse vectors with HNSW search.Server
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
16 October 2026
Original website title
anaslimem/CortexaDB · Official homepage title · retained in its source language
How we review sourcesSuggest a correction