Alternatives to VoiceMem

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

Cognee is open-source agent memory that turns scattered company data into a cited knowledge graph agents can recall.

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

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

Open-source Postgres memory engine for AI agents that sends memory conflicts to a human instead of overwriting them.

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

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

Open-source AI agent memory runtime that runs on your own Postgres and issues a signed receipt for every answer.

Long-term memory for AI agents: one process_turn call stores each turn and returns the memories your next prompt needs.

Own your AI context in four plain Markdown files — the open-source AI agent memory system

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

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

Open-source, local-first memory palace that gives AI assistants verbatim recall across sessions, stored entirely on your own machine.

Open-source background agents that run in credential-less sandboxes to review PRs, triage bugs, and ship verified fixes on GitHub.

A persistent, file-based memory layer for coding agents that lives as a brain/ Markdown folder in your repo.

Unbody is an open-source AI-native backend with a self-evolving memory layer for agentic RAG apps.

Screenpipe records your screen and audio locally, turning your computer history into AI memory your agents can search.

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

UltraContext: an open-source context SDK that syncs AI agent sessions into one mountable filesystem over MCP.

Agent memory that learns from failed tool calls, so your AI agents stop repeating mistakes across sessions

Zep is the enterprise context layer that gives AI agents governed memory built on temporal context graphs.

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

DataGrout is an operating layer for production AI agents: persistent memory, real-time cost control, and cryptographic receipts for every action.

Cavemem gives MCP coding agents persistent memory on local SQLite — recall across sessions without re-reading files.

Outcome-weighted persistent memory for AI agents that keeps what actually worked, not what merely sounds related.

Persistent local memory for coding agents: Claude Code, Cursor and Codex share one searchable store.

Hosted MCP and REST memory that keeps AI agent context consistent across ChatGPT, Claude, Codex, and your own agents.

Carrier-native AI memory that turns every SIM into a persistent, billable AI agent

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

Persistent memory for Python AI agents, with versioning, shared memory across agent teams, and loop detection that pauses runaway agents before the token bill