Alternatives to Mnemosyne

Mem0 is an AI memory layer that gives agents persistent context across sessions, users and apps

Local-first memory layer that gives your AI coding agent a SQLite file it can recall from between sessions.

TrueMemory gives CLI coding agents persistent, local-first memory recall in about 55ms — one file, zero cloud.

Cavemem: local-first MCP memory that compresses coding-agent context into recoverable handles

Local-first persistent memory for AI agents with a forgetting curve, open source and MCP-compatible.

MemOS gives AI agents persistent long-term memory through a cloud API or a fully local runtime.

Jumbo.Cli gives AI coding agents persistent project memory from a local-first CLI, so you stop re-onboarding Claude Code every session.

Local-first agent memory and secrets layer that gives Claude Code, Codex, and OpenCode one shared context on your own machine.

Local-first coding agent memory that records issues, failed attempts and fixes inside your repo and feeds them back to Claude Code, Cursor or Codex at session

CogniMemo is an API-first persistent memory layer that gives your AI agents structured long-term recall across sessions.

Cognee gives AI agents persistent knowledge-graph memory with cited recall across sessions, teams, and tools.

Hebbrix is outcome-weighted persistent memory for AI agents — it recalls what actually worked, not what merely sounds related.

Agentmemory gives coding agents shared, local memory across Claude Code, Cursor, Codex and 22 other agents.

Local-first memory layer for Claude Code and OpenCode that scores memories by whether they actually worked.

Open-source MCP memory layer that gives AI agents a graph plus vector store so recall carries relationships, not just similar text.

memU gives Codex, Claude, Cursor and other agents one shared, inspectable memory layer with source-linked recall.

Memori is an LLM-agnostic agent memory gateway that turns every execution trace into persistent, governed memory and procedural recall.

Microsandbox runs untrusted AI agent and user code in local-first microVMs with a dedicated Linux kernel per sandbox.

Run AI coding agents in isolated cloud sandboxes — locally on your Mac or delegated from Slack, Linear, and GitHub.

Memoryport is a local-first memory layer that gives Claude Code, Cursor, Ollama and OpenAI persistent context across every session.

Open-source local-first AI memory that stores every conversation verbatim in a method-of-loci palace on your machine.

Open-source graph memory engine for sentence-level AI agent recall across sessions

Governed shared memory for AI agent fleets — scoped writes, keystone policies and a per-recall audit trail.

Open-source, self-hosted memory layer that gives AI agents persistent recall via hybrid retrieval.

Unabyss gives every AI agent one live MCP memory built from Slack, Gmail, Notion and GitHub — so you stop re-explaining yourself.

Letta builds stateful AI agents with persistent memory that survives sessions, model swaps, and machines.

Agent memory that learns from failed tool calls and user corrections, not just stores facts

Build governed AI agent memory with Zep's temporal context graph and dated, traceable facts

Omnara is a stateful, open-source agent API for deploying durable AI agents on any model, machine, or cloud.

MemoryLake is portable AI memory for ChatGPT, Claude, Codex and Gemini — encrypted, exportable, and shared across every agent you run.