alma-memory is an open-source Python library that provides persistent memory architecture for AI agents. Below are 10 rag, search & retrieval apps with similar functionality to alma-memory, matched by what each product actually does — not ranked or scored. Explore each to find the closest fit for your use case.
everalgo-agent-memory is an open-source Python library for managing agent memory, extracting agent skills, and detecting boundaries in AI agent workflows. It is designed for developers building advanced AI agent systems.
memorylaier is an open-source Python SDK that provides persistent memory infrastructure for AI agents. It enables developers to efficiently store, manage, and retrieve agent memory, supporting advanced AI workflows. The SDK is designed for integration into AI systems and is available under the Apache-2.0 license.
atlas-ai-memory is an open-source, local-first structured memory system for AI-assisted development. It enables persistent, cross-tool project memory, supports embeddings and RAG workflows, and integrates with Model Context Protocol (MCP) for advanced AI development.
yourmemory is an open source Python package that provides persistent memory capabilities for Claude-based and MCP-native AI agents. It features semantic deduplication, Ebbinghaus forgetting curve support, and integrates with SQLite and PostgreSQL. Designed for developers building advanced AI agent workflows.
aelfrice is an open-source library that offers persistent, deterministic memory for AI coding agents using local SQLite storage. It enables developers to store and retrieve matched beliefs in prompts, ensuring auditable and cloud-independent operation for agent applications.
memman is an open-source Python package that provides LLM-supervised persistent memory for AI agents, supporting intent-aware graph recall, retrieval-augmented generation (RAG), and pluggable embeddings. It is designed for developers building advanced agentic systems that require long-term memory and semantic search capabilities. The package integrates with Claude Code, OpenClaw, and NanoClaw.
auto-memory is an open-source CLI tool that provides progressive session recall for AI coding agents such as GitHub Copilot CLI. It helps developers maintain context across coding sessions for better AI assistance.
m3-memory is an open-source memory framework for AI agents, offering local-first storage, hybrid and vector search, and compatibility with the Model Context Protocol (MCP). It supports both offline and cloud operation, making it suitable for advanced AI agent development.
forgememo is an open-source library that provides persistent memory capabilities for AI agents, allowing them to retain context across sessions. It supports the MCP protocol and is designed for developers building autonomous agents or LLM-based workflows. The tool is distributed as a CLI and Python package under the Apache-2.0 license.
getmem-ai provides a persistent memory API designed to serve as the memory layer for AI agents. The platform addresses the challenge of maintaining and retrieving structured, contextual knowledge from conversational turns, enabling applications to deliver more accurate and personalized responses based on what is already known about each user. It processes conversation data by extracting structured knowledge, storing it in a typed graph and a hybrid vector index, and returning ranked, grounded context for every interaction, typically in under 300 milliseconds and with isolation per end user. The API operates through two main endpoints: one for ingesting conversation turns and another for retrieving context. When a conversation turn is ingested, the system extracts typed facts across a 12-category taxonomy, including tone and confidence, and resolves entities such as people, places, organizations, and topics with canonicalization and stable IDs. This information is written in parallel to a hybrid vector index—combining dense and sparse representations with 17-field payload filters—and a typed knowledge graph. Retrieval is handled on a fast, LLM-free path that includes heuristic decomposition, fuzzy entity matching (handling typos and variants), parallel hybrid search across multiple indexes, bounded graph expansion, and a ranking step. The result is a structured prompt block containing deduplicated, contextually relevant facts, along with meta information about latency and token counts for observability. getmem-ai is intended for developers building AI agents that require deep, accurate personalization, particularly in domains where response quality depends on prior user knowledge. Example use cases include healthcare agents that remember patient histories and legal research agents aware of case facts and client preferences. The system is designed with features such as per-patient or per-user isolation and audit logging for sensitive applications. The service is accessible via API, and integration is described as straightforward with a free credit available to start. Overall, getmem-ai is positioned as a specialized memory infrastructure for AI and conversational applications, enabling structured retrieval-augmented workflows for agents that benefit from persistent, contextual memory.
