Netcafe Memory alternatives

1

IWE

by iwe-org

A

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

2

Total Agent Memory

by vbcherepanov

A

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

3

Fidelis Memory

by hermes-labs-ai

B

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

4

coldstart

by AkashGoenka

A

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

5

rag-rat

by cq27-dev

B

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

6

agent-device

by callstack

A

MCP server for mobile app automation: verify, control, and debug iOS, Android, TV, and desktop apps

7

Basic Memory

by basicmachines-co

C

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

8

Agent-Native Clips

by BuilderIO

A

Screen recording, meeting notes, and voice dictation - all with AI

9

ContextStream MCP Server

by contextstream

A

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

10

Google Surf

by HarimxChoi

B

Web, academic and code search with graph RAG, data lineage, ontology and cross-project schema links.

11

Mnemoverse Memory

by mnemoverse

A

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

12

Agent Comms

by ExaDev

A

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

13

Agent Search

by lennney

B

Free-first Chinese and English web search MCP using zero-key sources and inspectable evidence.

14

Dvalincode

by arthurpanhku

A

Deterministic security scanning, no model or API key, plus offline-verifiable proof a fix worked.

15

Projectmem

by riponcm

A

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

16

adrkit decision memory

by adrkit.dev

A

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

17

Watch Skill

by oxbshw

B

Watch video and live sessions, keep timestamped evidence, and verify an agent's own work.

18

GrayMatter

by angelnicolasc

B

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