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

Truememory

TrueMemory is a local memory tool for AI coding assistants and Python applications. It automatically captures useful conversation context and recalls relevant details in later sessions, storing memory in a SQLite file on the user's machine.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Truememory — 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

Use TrueMemory when recurring coding-assistant sessions need to retain selected conversation context, or when a Python project needs a documented add-and-search memory interface.

Who it is for

  • Developers using Claude Code, Claude CLI, Cursor, Codex CLI or Gemini CLI who want context carried between sessions.
  • Python developers who need to add and search memory records through a library interface.
  • Users choosing between CPU-only, fully offline and API-key-dependent memory tiers.

Documented uses

  • Carry project decisions, preferences and other useful conversation details into later assistant sessions.
  • Let a supported assistant capture and recall memories automatically rather than relying on manual tagging and lookup.
  • Add a memory record for a user and search for it from Python.
Before you choose

Requirements & limits

The repository is public and lists an AGPL-3.0 license. The documented assistant setup uses a command-line installer and downloads about 1.5 GB of models.

  • Listed assistant environments are Claude Code, Claude CLI, Cursor, Codex CLI and Gemini CLI; the README does not provide integration steps for each one.
  • Edge is described as CPU-only, Base as requiring 4 GB or more of RAM, and Pro as requiring 4 GB or more of RAM plus an LLM API key for HyDE search.
  • Base is described as fully offline, while the README separately notes anonymous usage telemetry that can be disabled through an environment variable.
  • The Python example demonstrates adding and searching a memory with a user identifier.
  • The repository's AGPL-3.0 license is relevant to developers incorporating or modifying the project.

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 TrueMemory for a supported coding assistant

Set up TrueMemory for automatic memory capture and recall in a listed coding assistant.

Before you start

  • A terminal on macOS, Linux or Windows PowerShell.
  • Claude Code, Claude CLI, Cursor, Codex CLI or Gemini CLI.
  • About 1.5 GB of model downloads, according to the README.

Steps

  1. Run the documented installer for your platform: the shell installer on macOS or Linux, or the PowerShell installer on Windows.

  2. Wait for the model downloads to finish.

  3. Quit and reopen the coding assistant.

  4. Type “Set up TrueMemory” in the assistant and choose a tier.

Expected outcome

The README says TrueMemory then automatically remembers conversations for the configured assistant.

Guide limitations

  • The installer downloads about 1.5 GB of models.
  • Tier requirements vary: Edge is CPU-only, Base needs at least 4 GB RAM, and Pro needs at least 4 GB RAM plus an LLM API key.
  • The instructions describe installation but do not provide integration test results.
Documentation 1 ↗
Source-based practical guide

Add and search a memory with the Python library

Use the documented Python interface to store a memory and retrieve it by a query.

Before you start

  • Python package installation using pip.
  • A Python environment in which to import the truememory package.

Steps

  1. Install the package with the command below.

    Documented command
    pip install truememory

  2. Import Memory from truememory and create a Memory instance.

  3. Call add with a memory string and a user_id.

  4. Call search with a query and the same user_id.

Expected outcome

The example adds a preference as a memory and searches for preferences associated with that user identifier.

Guide limitations

  • The README example does not document further configuration or storage-location settings for this library usage.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for AI coding assistance

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
TruememoryCarry project decisions, preferences and other useful conversation details into later assistant sessions.CLI, Self-hostedThe repository is public and lists an AGPL-3.0 license. The documented assistant setup uses a command-line installer and downloads about 1.5 GB of models.
Continuum — pouyahasanamrejiStore project lessons so coding agents can retrieve them across conversations.CLI, Self-hosted, ServerThe repository documents local Docker Compose and bare-metal development setups. Bare-metal startup requires Node 22.12.0 or later and pnpm 10.33 or later; the Compose path skips these host prerequisites.
HaftRecord the problem a project is solving and the options considered.CLI, Self-hosted
Evidence and transparency

Sources & review

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