TrueMemory — Watchlist

MCP100 Assessment

Watchlist / Tracking

Why we’re tracking it

Monitor this implementation for changes in adoption, MCP interface, maintenance and permission boundary.

Reviewed Oct 10, 2026 · Documentation review; complete setup workflow not independently tested

Best fit

Store and recall AI assistant context locally

What we know

The memory your AI should have had from the start. Automatic capture, automatic recall, 100% local. One SQLite file, zero cloud. Works with Claude Code, Claude CLI, Cursor, Codex CLI, Gemini CLI. Store and recall AI assistant context locally.

Maintenance / activity evidence

GitHub REST pushed_at 2026-10-09T20:21:59Z

Tracking evidence observed Oct 10, 2026. These dated signals do not establish current maintenance. Reviewed enrichment confidence: medium.

Verification gaps / watch-outs

Installation and comprehensive security have not been independently audited.
Scoped by connected account, local OS, and configuration; verify exact permissions before installation. Reported action classes: persist memories; delete memories (not verified). Complete write authority is not verified.
Local storage path and MCP client
Local memories and workspace text

Local-first privacy claim is project-reported, not verified via network audit. Persistent memory may contain secrets.

Full authority, access and evidence limits are available in Review context and Access & risk.

Popularity

380 repository stars

Stars observed Oct 9, 2026.

Repository total for buildingjoshbetter/TrueMemory.

All limitations / Review context

Has TrueMemory changed its specific MCP integration, install method or privilege scope, and does it justify shortlist promotion?

High-impact permissions explicitly documented; no known blocker to an accurately caveated public Radar listing in limited first-party review.

Local-first privacy claim is project-reported, not verified via network audit. Persistent memory may contain secrets.
Scoped by connected account, local OS, and configuration; verify exact permissions before installation.
Local storage path and MCP client
Local memories and workspace text
Reviewed write actions: persist memories; delete memories (not verified)
Complete write authority is not verified.
Installation, client compatibility and comprehensive security have not been independently audited. Authentication and access depend on the configured services.
No exhaustive advisory or runtime review performed; never infer installation safety.
Write actions/tool inventory not confirmed against exact tool documentation; listed action classes remain illustrative or context-dependent. Empty inventory does not establish read-only.
Setup and runtime permissions are implementation- and account-specific; follow linked upstream documentation.
Repository pushed_at explicitly observed

Original activity observations

GitHub REST pushed_at 2026-10-09T20:21:59Z

Technical identity

github.com/buildingjoshbetter/TrueMemory

Exact implementation source: https://github.com/buildingjoshbetter/TrueMemory ↗
Reviewed resource type: MCP Server
Repository identity: buildingjoshbetter/TrueMemory

Evidence & Sources

Evidence basis: Recorded source evidence
Setup runtime verification: Not independently runtime-tested by MCP100 for this setup workflow.

Reviewed Oct 10, 2026 · Latest source observation Oct 10, 2026

GitHub repository ↗
buildingjoshbetter/truememory
Recorded repository material and project history.

Setup · Watchlist

Install & Agents

Publisher instructions.

Source evidence observed Oct 12, 2026.

Additional setup details required — see the specific gaps below.

Warning

The publisher install.sh pipeline should not be pasted as an unchecked default.
Publisher-specific exact credential-revocation procedure not established; use the issuing provider controls only if credentials actually exist.
Credential revocation is external-provider-specific or not documented in examined official project Setup/README; do not assert exact revocation CLI.
No unique structured client config confirmed for this mode; may be inapplicable to Host/SDK/Framework.
Only if installed using the exact matching package manager and installation scope; may leave user data/configuration intact.
TrueMemory provides a local agent integration installer that downloads roughly 1.5 GB of AI models.
Review the publisher install.sh or install.ps1 source before execution
Remote script must be inspected before running.

Install / connect
Publisher instructions
For Claude Code, Cursor, Codex or Gemini CLI, publisher recommends `curl -LsSf https://raw.githubusercontent.com/buildingjoshbetter/TrueMemory/main/install.sh | sh` (review remote script before executing). `pip install truememory` is specifically Python library usage, not the recommended agent installer.
Advanced configuration · agent integration installer
agent integration installer · Review before use
curl -LsSf https://raw.githubusercontent.com/buildingjoshbetter/TrueMemory/main/install.sh | sh
pip install truememory
Configure / authenticate
Publisher instructions
After intentional install, completely restart the chosen agent and invoke publisher onboarding to select Edge, Base or Pro tier. Edge/Base operate offline; Pro HyDE mode can require an additional LLM API key. Do not treat a Python library install as an MCP server registration.
Check connection
Suggested check
Restart the agent and inspect TrueMemory integration/tools. If the only installed artifact was the Python library, consider MCP agent setup still incomplete; do not write synthetic memories to the real store just to test readiness.
Remove / uninstall / revoke
MCP100 setup guide
Remove the TrueMemory integration from your agent client and stop the runtime. `pip uninstall truememory` only removes library installations, not the integration installed by remote script; do not claim it is a full reversal.
python -m pip uninstall truememory

Official Documentation & Sources

What it does

The memory your AI should have had from the start. Automatic capture, automatic recall, 100% local. One SQLite file, zero cloud. Works with Claude Code, Claude CLI, Cursor, Codex CLI, Gemini CLI. Store and recall AI assistant context locally.

Capability: Files & Knowledge
Resource type: MCP Server
Best fit: Store and recall AI assistant context locally

Representative uses

Store useful agent project context
Recall prior notes and remembered facts
Organize local memory history
Store and recall AI assistant context locally

Limitations

Local-first privacy claim is project-reported, not verified via network audit. Persistent memory may contain secrets.
Setup and runtime permissions are implementation- and account-specific; follow linked upstream documentation.
Repository pushed_at explicitly observed

Reviewed access

Access & risk

Review the exact access boundary before connecting this MCP to accounts, credentials, or sensitive data.

Authentication: Local storage path and MCP client
Permissions: Scoped by connected account, local OS, and configuration; verify exact permissions before installation.
Data handling: Local memories and workspace text
Cost: may incur external API or infrastructure charges; unverified
Risk and cautions: Local-first privacy claim is project-reported, not verified via network audit. Persistent memory may contain secrets.

Access scope and cautions

Write actions: Not verified persist memories delete memories (not verified)
Risk level: moderate
Security notes: Local-first privacy claim is project-reported, not verified via network audit. Persistent memory may contain secrets.

The reviewed evidence does not establish the complete write authority of this MCP. Consult the unresolved evidence before granting write access.

FAQ

Based on reviewed evidence as of 2026-10-09. Watchlist tracking is not a recommendation or a security certification.

Which tasks are documented for this implementation?

The reviewed tasks include: Store useful agent project context; Recall prior notes and remembered facts; Organize local memory history; Store and recall AI assistant context locally.

What setup and authentication are documented?

A complete connection procedure is not verified. Client notes: Command provided only where first-party command or package existence is established; verify the client configuration against upstream documentation. Installation/authentication detail is incomplete; do not infer settings from package name. These facts do not supply missing installation commands, credentials or a verified authentication procedure. Authentication: Local storage path and MCP client

Can it modify data or perform write operations?

Not verified. The available evidence does not establish the complete write authority. The partial inventory lists: persist memories; delete memories (not verified). Recorded permission context: Scoped by connected account, local OS, and configuration; verify exact permissions before installation.

What data-handling boundary should I consider?

Local memories and workspace text

What limitations and risks should I check before use?

Local-first privacy claim is project-reported, not verified via network audit. Persistent memory may contain secrets. Setup and runtime permissions are implementation- and account-specific; follow linked upstream documentation. Repository pushed_at explicitly observed. No exhaustive advisory or runtime review performed; never infer installation safety.