Skip to content
Alternatives
Software like CoreMem
What else does this job. Matched on what each project does, not on who links to whom.
Closest first
- AgentMemagentmem.devAgentMem is a memory layer for AI agents. It is built for developers who want agents to keep context instead of starting from zero, and it describes its purpose as giving persistent, searchable memory that can sync across frameworks including LangChain, CrewAI, OpenAI, Claude, AutoGPT, and LlamaIndex. The product stores and retrieves memories through an API. Its listed capabilities include semantic search, which finds memories by meaning rather than keywords and is powered by vector embeddings, and cross-agent sync for sharing context between agents. The page also says memories are persistent and survive restarts, that the API is simple to use with an API key, and that memories are auto-embedded when stored. A short code example shows calls for storing a memory, searching memories, and syncing across multiple agents. AgentMem’s production-oriented features include fast API response times under 100 ms, edge caching, API key authentication, tenant isolation, encrypted-at-rest storage, usage analytics for memory usage, search patterns, and agent activity, and a global CDN setup. It is deployed on Railway with a Cloudflare proxy. The page also includes a worked example of registering an agent through a POST endpoint and then using POST endpoints to store memories and search them. Pricing is presented in three plans. A free plan costs $0 per month and includes 10,000 memories, semantic search, support for three agents, and community support. Pro costs $29 per month and adds unlimited memories, unlimited agents, cross-agent sync, priority support, and usage analytics. Enterprise costs $199 per month and adds a self-hosted option, custom integrations, an SLA guarantee, and dedicated support. The page identifies AgentMem as being built by Gritza and says it is in public beta.
- Mem0mem0.aiMem0 is an infrastructure platform that provides persistent memory for AI agents and applications. It enables context retention across sessions, making it easier for developers to build smarter, more personalized AI systems. Designed for integration via API and SDK.
- ClawMemclawmem.aiClawMem is an open-source framework that provides a shared memory layer for AI agents, enabling context and memory to persist across sessions and agent handoffs. It supports integration with multiple agent frameworks and the Model Context Protocol (MCP), making it valuable for developers building complex agent systems.
- Memobasememobase.aiMemobase is a persistent AI memory and context-continuity tool for agents and other AI tools. It is described as a synaptic layer for AI agents, intended to avoid the reset that happens when each new session loses earlier context, architecture, style, and progress. Its core architecture centers on passive context capture and a background Dream Phase that distills noisy session logs into durable, high-signal rules and project insights. Memobase also uses deterministic HTTP hooks for passive intelligence, hybrid graph retrieval that combines vector similarity with Knowledge Graph relationships, and an MCP-native protocol. The site says it works natively with Claude, ChatGPT, and Cursor. It also includes an insight dashboard for visualizing a knowledge graph and vector space, managing API keys, and monitoring usage in real time. The Quick Setup section says it can be added to an AI assistant with no code required, and the CLI supports a private local mode with SQLite as well as cloud sync for cross-device access. The CLI examples include installing memobase-cli, starting a local memory server, logging in to a cloud account, auto-configuring Claude Code hooks, scanning a repository for project IQ, and pushing local memories to the cloud. The page presents Memobase for developers and for everyone else. For developers, it offers the CLI and guidance for adding the Memobase MCP server to an AI configuration. For other users, it offers a one-click flow and drag-and-drop history import to build a knowledge graph. The setup instructions also show integrations with Claude and Claude Desktop, including connector setup, an API key workflow, and hooks for events such as UserPromptSubmit, Stop, TaskCompleted, and SessionEnd. Pricing is listed in monthly plans. Free is $0 forever and includes 500 credits per month, semantic vector search, per-user memory isolation, and community support. Pro is $9 per month and includes 5,000 credits, a monthly usage dashboard, email support, and priority response. Unlimited is $29 per month with unlimited credits, dedicated support, SLA availability, and custom onboarding. The page also states that PostgreSQL Row-Level Security is used for memory isolation and that self-custody options are on the roadmap.
- Memori Labsmemorilabs.aiMemori Labs provides an agent-native memory infrastructure designed for production AI systems. The platform offers a layer that is agnostic to large language models (LLMs), enabling agent execution and conversations to be transformed into structured, persistent state. This infrastructure is intended to help AI agents and their developers capture, organize, and recall information from interactions and documents efficiently, without the need for additional external services. A core feature of Memori is its ability to automatically capture each turn in a chat and classify the information into facts, preferences, rules, and summaries. Users retain control over what data is stored, its retention duration, and storage location. When context is needed for prompts, the system retrieves only the most relevant information across conversations and documents. Memori enhances search accuracy through selective semantic search, enriching queries with semantic context to improve results and reduce token costs. Every recall provides an explanation of why specific information was included, offering traceability by entity, time, and source. 95% accuracy rate on the LoCoMo benchmark and a 95% reduction in token usage compared to full-context retrieval. Developers can integrate Memori with a single line of code using its SDK, which manages model calls and callbacks with zero configuration. Memori Cloud allows instant storage and search of memories, requiring no additional setup. The tool also features an interactive memory graph to visualize relationships and analytics to monitor memory creation, recall usage, and cache performance. Memori is positioned to help enterprises reduce costs by over 95% through tokenless recall and structured memory, and aims to deliver fast responses by caching concise snippets. The platform supports secure memory for payments and sensitive information, with PCI and SOC 2 compliance. It is designed for developers and teams building AI agents, and has been noted for potential integration with ecosystems such as MongoDB. The service emphasizes explainable results, intelligent routing, and instant context from historical content, catering to the needs of production-scale AI applications.
- Supermemorysupermemory.aiSupermemory provides a hosted context and memory platform for AI agents, including persistent knowledge-graph memory, hybrid RAG retrieval, user profiles, connectors, extractors, and structured context. It offers APIs, developer plugins, MCP support, and a personal second-brain app.
- Memcode AImemcode.aiMemcode is a terminal-based coding agent that maintains a persistent, evolving model of your entire codebase across sessions. Unlike typical chat wrappers that start from scratch each time, it remembers architecture decisions, prior changes, and context, allowing it to continue work efficiently without re-analyzing the full repository. It runs as a fast, single-binary TUI with no browser or IDE dependency. It is aimed at developers who want an AI pair programmer that truly understands their project's history and grows more effective over time.
- MemMachinememmachine.aiMemMachine is an open-source memory layer built to enhance advanced AI agents by enabling them to learn, store, and recall data and user preferences across sessions. Its primary function is to transform AI-powered applications, such as chatbots and assistants, into context-aware and personalized agents capable of delivering more precise and meaningful interactions. By persisting memory across multiple sessions, agents, and large language models, MemMachine helps applications build evolving user profiles that inform future responses and actions. The platform is designed to support sophisticated personalization and context retention. It features two distinct types of memory: Episodic Memory, which captures conversational context, and Profile Memory, which stores long-term user facts and preferences. These memory types allow agents to recall relevant information, enabling them to provide tailored responses and manage complex, long-running workflows. For example, MemMachine can be used in healthcare AI assistants to remember patient preferences and history, or in team collaboration tools to deliver proactive, context-aware insights that improve with each interaction. MemMachine is accessed through a RESTful API, a Python SDK, or an MCP Server, providing flexibility in how developers integrate memory capabilities into their AI agents. The memory data is persisted to databases, supporting robust and reliable storage of user and interaction data. The platform is suitable for engineering teams and developers building AI agents that require persistent, context-rich memory to support personalized and intelligent behavior. As an open-source solution, MemMachine is available for integration into a variety of AI-powered applications. Its architecture and features are designed to abstract complexity while allowing flexibility for developers to use components independently. The tool is positioned within the class of memory infrastructure solutions for AI agents, focusing on enabling context-aware, personalized, and sophisticated automation in AI-driven systems.
- core-memorypypi.orgcore-memory is an open-source library that provides persistent, lossless memory with causal structure for agent-based frameworks. It is designed for developers building AI agents that require reliable memory storage and efficient compaction.
- ContextNestpromptowl.aiContextNest is a locally running context management tool designed to provide a persistent memory layer for AI applications. It addresses the challenge of AI models forgetting user context between sessions, enabling every AI tool on a user's machine to draw from the same up-to-date knowledge base without repeated re-briefing. The platform is intended for knowledge workers and organizations where accuracy and privacy are essential, and it is used in environments where regulatory compliance such as SOC 2, HIPAA, and GDPR is required. The core feature of ContextNest is its ability to maintain a local knowledge vault that integrates with AI tools including Claude, Cursor, Antigravity, and any MCP-compatible client. The tool supports Markdown and PDF files, allowing users to organize their expertise and ensure that every AI response is informed by the most relevant and current information. ContextNest operates entirely on the user's machine, with no cloud connectivity, ensuring that files never leave the device and are not transmitted or stored externally. This local-first architecture emphasizes privacy and security, as there is nothing to breach or intercept in transit. ContextNest is available as a free desktop application for macOS and Windows, requiring no account or subscription. Users can set it up in minutes, and it runs quietly in the background, providing a continuous context engine for all supported AI tools. For teams, a free, self-hosted Community Edition server can be deployed on local infrastructure or a VPS, supporting team roles, approval workflows, and shared, versioned knowledge vaults. The tool also provides a command-line interface for developers who prefer direct code interaction. PromptOwl, a related offering, adds governance features such as role-based access control, approval workflows, cryptographic audit trails, and enterprise-grade infrastructure. This allows organizations to manage context and knowledge sharing at scale, with deployment options that include embedded chat, standalone applications, API access, and white-label solutions. ContextNest thus serves as the foundational context artifact, while PromptOwl governs access and automation across teams and enterprises.
- Memerimemeri.aiMemeri is a workspace platform designed for developers who use AI coding agents like Claude, ChatGPT, and Codex. It enables multiple agents to collaborate on projects with a shared memory, visible work logs, and real-time updates. Users can connect different agents, track their activities, and steer their work in a unified environment.
- MemBrainmem-brain.ioMemBrain is a persistent memory infrastructure designed for AI agents, offering a self-evolving knowledge graph that enables long-term storage, traversal, and recall of reasoning paths and semantic relationships. The platform addresses the challenge of maintaining continuity and context for AI agents over extended periods, allowing them to recall information and reasoning across weeks or months without session resets. Rather than simply storing documents, MemBrain parses incoming events, calls, and state changes into a neural graph composed of semantic nodes, edges, and type definitions, supporting autonomous learning, linking, and pruning of context based on actual reasoning patterns. Key features include an event observation and parsing engine that transforms raw data and tool calls into typed nodes, a causal reasoning engine that identifies connections and traces causal paths between temporal events, and a graph traversal system for memory recall that returns logical paths through the memory graph. The platform supports interactive exploration of stored memories as a graph, with capabilities such as Graph Search and Regex Scoping for finding and highlighting nodes. MemBrain's architecture is engineered for agentic speed and reliability, with features like pre-cached logic for rapid response times, surgical retrieval to prevent context window bloat, and temporal accuracy that distinguishes structural shifts from temporary anomalies in agent behavior. MemBrain integrates natively via the Model Context Protocol (MCP), enabling compatibility with any large language model (LLM). Users can connect through exposed interfaces such as search_narrative, observe_state, and evolve_memory for querying, reading, and writing to the memory graph. The platform is accessible via API and command-line interface (CLI), and offers a read-only demo graph for interactive exploration without an API key. Pricing is provisioned in Indian Rupees (INR) and is structured into four tiers: a Free plan for individuals with 1,000 total memories and API/MCP access, a Pro plan for developers with 10,000 total memories, a Scale plan for high-volume users with unlimited total memories and increased weekly creation limits, and an Enterprise plan with custom limits, dedicated support, security audits, and white-labeling options. The product is developed by Alphanimble.
- rememorirememori.devrememori is an embedded memory engine designed for AI agents, implemented in pure TypeScript with zero dependencies, zero servers, and zero native bindings. It addresses the challenge of providing persistent, in-process memory for agents that would otherwise lose context, user preferences, and prior interactions at the end of each session. The tool offers a lightweight alternative to external vector databases and retrieval services, enabling agents to remember and recall information efficiently without additional infrastructure. The core API revolves around four main operations: remembering, recalling, forgetting, and reinforcing memories. Text can be stored along with its embedding, tags, and automatically extracted entities. Recall operations rank stored memories using a combination of similarity, shared entities, user feedback, importance, and time decay, while the forget function removes specific memories. The reinforce function strengthens memories only when there is verifiable evidence of their use, and demote provides a mechanism to reduce the prominence of incorrect memories. rememori automatically constructs a bipartite knowledge graph by linking memories to their mentioned entities, enhancing recall accuracy even when queries do not directly match stored text. Developers can use any embedding model, including local options like Ollama, OpenAI-compatible endpoints, or custom functions. Storage is handled locally: on Node and Bun, data is kept in a single append-only file; in browsers, IndexedDB is used; and on edge platforms, a key-value adapter is available. The tool operates wherever JavaScript runs, including Electron and edge workers, and it is suitable for a range of applications such as chatbots, coding agents, local-first apps with semantic search, compliance-sensitive assistants, home automation, and game NPCs. rememori is distributed as a single npm package, with a core size of approximately 8 kB gzipped, and is licensed under the MIT license. It is not intended as a multi-user server, cloud solution, or document-ingestion platform, but rather as a memory engine embedded directly within an agent's process for rapid deployment and minimal operational overhead.
- COREgetcore.meCORE is a personal AI operating system that helps users manage their memory, tasks, and toolkits through an AI-powered web interface. It integrates various productivity features, acting as a central hub for personal organization and automation. CORE is designed for individuals looking to enhance their productivity with AI-driven assistance.
- Contextiumcontextium.aiContextium is an open-source methodology and toolkit designed to provide structure and continuity for AI agent workflows, particularly in coding and development contexts. It addresses the common problem of AI sessions starting from scratch and losing context or memory over time, leading to repetitive explanations and a lack of persistent rules. By introducing an operating system-like approach, Contextium enables each AI session to build upon the last, preserving both decisions and reasoning. The tool organizes work into a loop of distinct phases: planning with a SPEC of success using the 'Think' verb, implementing from a clean context with 'Do', and journaling outcomes and reasoning with 'Wrap'. These phases are executed as commands, each with its own session and context. Additional commands include 'implement-audit' for adversarial review and 'explain' for deeper investigation, among others. Contextium enforces rules through mechanisms wired to hooks—such as a commit gate, a destructive-git guard, and a memory-write guard—ensuring that important practices are automatically enforced rather than merely advisory. The system maintains two layers of memory: the git log for tracking changes (what happened) and a daily journal for capturing the rationale behind decisions (why they happened), enabling users to reconstruct past choices and reasoning. Contextium is delivered as a terminal-based tool that can be installed via a shell command. Upon installation, it prompts users to select which AI tools they use (including Claude Code, Gemini, Codex, Cursor, and Copilot), their name, and the desired level of AI autonomy. It then generates native configuration files for each selected tool, ensuring model-agnostic compatibility and zero lock-in. All data and context are stored as plain markdown files within a git repository owned by the user, preserving portability and user control. The toolkit includes templates for integrating with external services such as GitHub, Google, and Todoist, which can be configured as needed. Contextium is released under the MIT License and is fully open source. Its design emphasizes portability, accountability, and a structured approach to managing AI agent sessions and memory in development workflows.
- Memorr.AImemorr.aiAI is a desktop application designed to address the challenge of context loss in extended AI conversations. Available for both Mac and Windows, the tool enables users to maintain continuity across multiple AI chat sessions by storing all conversations and contextual memories locally on their devices. 5, GPT-4, GPT-4 Turbo), Anthropic (Claude 3 Opus, Sonnet, Haiku), Google (Gemini Pro, Gemini Ultra), and Perplexity, and even use multiple models within the same session. A central feature of the application is its visual memory canvas, which occupies the majority of the split-screen interface (70% canvas, 30% chat). On this canvas, users can create, edit, and organize memory nodes, visually mapping out important information and context from their AI interactions. The branching functionality lets users explore different conversational paths without losing track of the original thread, supporting workflows that require tracking decisions, ideas, or project milestones over time. The application is positioned for a variety of users, including developers managing complex projects, writers and creators evolving content strategies, marketers analyzing campaign performance, entrepreneurs tracking startup pivots, students mastering academic subjects, and product managers overseeing feature development. AI emphasizes privacy and control, as all data—including conversations and memory structures—is stored locally, ensuring that content is not sent to external servers. Users bring their own API keys (BYOK) for the supported AI providers, which allows direct interaction with the AI services, full cost control, and access to the latest models as soon as they are released. The tool also offers export functionality, enabling users to save their chats and memories in JSON or markdown formats for external use or backup. The software is sold via a one-time purchase model for $89, which grants a lifetime license for use on up to two devices (with the ability to reassign devices as needed). The purchase includes free updates and support for one year, after which users retain indefinite access to their licensed version. AI.
- ContextVaultcontextvault.devContextVault is a shared memory layer designed for AI systems and teams, enabling persistent and centralized storage of context across agents and sessions. Its primary function is to prevent teams from repeatedly starting from scratch with each AI session by providing a single source of truth that AI clients can both read from and write to. ContextVault is scoped per user, agent, and tenant, ensuring durability of information across sessions and supporting long-term organizational learning. The platform is aimed at developers and organizations seeking to coordinate and reuse knowledge among multiple AI agents. It supports sharing memories across an organization, reducing the context load in AI requests, and eliminating the need to manage scattered Markdown files or outdated local projects. ContextVault is compatible with various AI clients and editors, allowing users to bring their own AI tools without vendor lock-in. It supports integration with AI systems such as Claude, Copilot, ChatGPT, and Ollama, and offers compatibility with OpenAI Codex and OpenAI Desktop/ChatGPT. Single sign-on is available through major authentication providers. Among its features, ContextVault offers centralized organizational storage, the ability to search historical solutions, and MCP compatibility. It is designed to facilitate long-term knowledge retention and skill development across teams, positioning itself as a tool not just for individual productivity but for organizational memory and collaboration. The platform is accessible through a dashboard and provides documentation for integration and use. The tool is classified as a shared memory infrastructure within the AI and machine learning domain, supporting persistent and reusable context for multi-agent workflows.
Ranked by how close each one sits to CoreMem in the index, not by popularity. Back to CoreMem →