Memtrust alternatives

1

LLM Sandbox

by vndee

A

Securely run LLM-generated code in isolated containers across 7 languages and 3 container backends.

2

Basic Memory

by basicmachines-co

C

Local-first knowledge management with bi-directional LLM sync via Markdown files.

3

IWE

by iwe-org

A

Markdown knowledge base as agent memory. Runs against the notes directory it is started in.

4

ContextStream MCP Server

by contextstream

A

Project memory, semantic code search, and grounded agent context.

5

Mnemoverse Memory

by mnemoverse

A

Hosted AI agent memory that learns from outcomes, with shared rooms, in Claude, Cursor and ChatGPT.

6

Agent Comms

by ExaDev

A

Cross-harness communication mesh for LLM agents — rooms, DMs, presence, and visibility over TCP

7

Total Agent Memory

by vbcherepanov

A

Persistent local memory for coding agents: temporal knowledge graph, procedural and episodic recall

8

Fidelis Memory

by hermes-labs-ai

B

Recall locally stored agent memories through an MCP-compatible host.

9

Projectmem

by riponcm

A

Coding agent memory — one local MCP server for every project. Warns before repeating failed fixes.

10

coldstart

by AkashGoenka

A

Codebase memory for AI agents: an AST index plus agent-written notes that self-stale.

11

adrkit decision memory

by adrkit.dev

A

Deterministic, offline, read-only ADR decision memory for coding agents. No model or network calls.

12

rag-rat

by cq27-dev

B

Repository intelligence, code graph, history, papertrail, and cross-agent memory for coding agents.

13

GrayMatter

by angelnicolasc

B

Persistent agent memory as a single Go binary: knowledge graph, TUI observability, zero infra.

A harness for driving a Godot 4 project from an agent: addons, runtime bridge, MCP server, CLI.