Skip to content
Alternatives
Software like MEMANTO
What else does this job. Matched on what each project does, not on who links to whom.
Closest first
- memantogithub.commemanto is an open-source companion memory agent designed to help AI agents focus and improve by managing and retaining knowledge. It supports retrieval-augmented generation (RAG) and semantic memory, giving users ownership over learned information.
- 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.
- memanto-mcpmemanto.aiMemanto is a memory agent for AI systems that keeps information available across sessions. It is described as persistent memory for Claude Code, Cursor, Codex, and 14+ other agents, and as a companion memory agent that helps agents focus while the user keeps ownership of what they learn. The product is built on what it calls an information-theoretic search engine. Its core functions include instant ingestion, conflict resolution, verifiable sources, deterministic search, temporal queries, freshness prioritization, and semantic categorization into 13 types. The page says memories become searchable immediately after they are written and reports under 90 ms recall latency. It also says the system supports built-in RAG, confidence scoring, local embeddings, autonomous categorization, and daily summaries. A comparison section states that it supports remember, recall, and answer, and that it returns relevant results rather than dumping everything into context. Memanto is presented as working with agents and frameworks across a broad stack. Named integrations include Claude Code, Cursor, Codex, GitHub Copilot, Gemini, OpenAI Codex CLI, Cline, Windsurf, Continue, opencode, Goose, Roo Code, Augment Code, Hermes Agent, CrewAI, LangChain, LangGraph, LlamaIndex, and n8n. The page also mentions REST and MCP, and it shows a CLI with commands such as memanto connect claude-code and memanto ui. A local interactive dashboard is available for managing agents and memories, viewing conflicts and connections, and migrating from Mem0, Letta, and more. The product is 100% free, open source, and runs entirely on the user’s machine. Installation is shown through pip install memanto, with an on-prem backend using Docker and localhost:8080, and a cloud option that uses an API key. The page also says embeddings and answers can run via local Ollama models, and that no API keys, vector database, or backend service are required for the on-machine setup.
- supermempypi.orgsupermem is an open-source command-line tool that provides persistent AI memory using a four-tier retrieval system, integrating SQLite FTS5, graph, vector, and LLM agent layers. It is designed for AI developers and researchers seeking advanced memory and retrieval capabilities for language models.
- memnodememnode.devmemnode provides persistent memory infrastructure for AI agents through a hosted API and local MCP server. It supports typed recall, provenance and lineage inspection, scoped tokens, shared tenants, and correction workflows for coding, support, and research agents.
- mementogithub.ioMemento is a shared memory system for multiple AI agents that stores durable knowledge outside individual conversations. It addresses the need for persistent information about people, projects, machines, services, decisions and their relationships to remain available across agents while keeping transient data such as chats, reminders, credentials and machine-specific state with the owning agent. Knowledge is stored as Markdown files with stable IDs, metadata and links. Git manages those files and their version history. A control.sqlite database holds proposals, idempotency records, write journals, leases and scheduler state. Separate full-text search, graph and optional vector indexes are derived from the Markdown content and can be rebuilt from source. A fine-tuned local Needle model classifies natural-language requests into a small set of read operations to reduce ambiguity. The system supports MCP access so any authenticated client can search, read and propose changes. Curators review all writes before they are committed to the shared repository. Visual tools include a memory graph overview that displays concepts, services, links, clusters and diagnostics, a memory inspector showing selected concept metadata, links, assets, proposals and embedding state, and a large-graph stress view capable of rendering a 2,000-node graph with level-of-detail and runtime diagnostics. The project was originally built for several piclaw instances but is designed for broader use by any compatible MCP client. Memento is an open-source project hosted on GitHub under the rcarmo account. No pricing information is stated.
- 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.
- Claude-memcmem.aiClaude-mem and cmem provide an open-source memory layer for AI agents, enabling persistent, structured recall of agent actions and decisions across sessions, machines, and development environments. This system addresses the challenge of AI agents losing context between sessions by capturing every decision, bugfix, and dead end as structured observations in a temporal database, allowing agents to resume work with full historical context regardless of where or when they last operated. The core offering consists of the claude-mem open-source engine, which can be installed with a single command and requires no configuration or account to begin. This engine writes observations automatically as agents work, storing them in a database that supports both full-text and recency-based hybrid search. The system is designed for compatibility with a wide range of agent frameworks, IDEs, and Model Context Protocol (MCP) clients, including named integrations such as Claude Code, Cursor, Windsurf, OpenCode, Codex CLI, and Gemini CLI. Developers can run claude-mem locally or use CMEM Cloud, which provides a cloud sync layer that mirrors the local database and offers a private MCP endpoint for access from any machine or agent. CMEM Cloud is available in early access and is free during this period. 0 license. The platform emphasizes privacy and flexibility, supporting offline-first operation and end-to-end private access via personal MCP links. Teams can share a single memory across multiple agents and editors, facilitating collaborative development and long-term traceability of project decisions and changes. The system's hybrid search enables agents to recall relevant information in milliseconds, even from projects that have not been touched in months. By integrating directly with agent frameworks and development tools, claude-mem and cmem streamline the process of building and maintaining persistent AI agent memory, reducing the need for manual context management and enabling agents to maintain continuity across diverse workflows.
- 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.
- Mnemoversemnemoverse.comMnemoverse is a persistent memory API for AI agents. It is built to let a preference, decision, or lesson be written once and recalled across tools, with a single API key connecting Claude Code, Claude Desktop, Cursor, VS Code, Windsurf, ChatGPT, Python, and REST. The service describes itself as memory for AI agents rather than a vector database. Its memory system uses Hebbian associations and Rescorla-Wagner-style outcome feedback, with HDBSCAN consolidation and Von Restorff-based forgetting. The page also describes a write-learn-recall loop: write stores a preference, decision, or lesson; learn updates valence from reported outcomes; and recall uses natural-language queries, learned associations, and valence-boosted ranking to surface what mattered before. It says an importance gate filters noise, look-alike memories can be merged, and memories that lead to good outcomes rank higher over time. For integration, Mnemoverse offers an MCP server through the @mnemoverse/mcp-memory-server npm package. That server exposes six tools: memory_write, memory_read, memory_feedback, memory_stats, memory_delete, and memory_delete_domain. The page lists support for MCP-compatible clients including Claude Code, Claude Desktop, Cursor, VS Code + Copilot, and Windsurf, and also mentions a VS Code Marketplace listing, a PyPI package, and the official MCP Registry. Pricing is public on the site. A free tier costs $0 and includes 1,000 queries per day, 10,000 atoms, and 60 requests per minute, with full API access and the MCP server and no credit card required. Paid plans shown are Pro at $29 per month and Team at $149 per month, and an Enterprise option is offered with custom terms, including SSO/SAML, audit logs, SLA, data residency, and BAA/SOC 2 on request. The page also says early-stage startups can start on Team free on signup, with six months if approved.
- mymem0rypypi.orgmymem0ry is an open-source personal memory system for AI coding agents, providing offline semantic search, cross-agent handoffs, and zero API key requirements. It is designed for developers building autonomous AI agents that need persistent, shareable memory.
- 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.
- 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.
- MEMMmemm.devMEMM is an open-source, AI-native application designed to serve as a persistent, structured memory system for AI tools. It addresses the challenge of AI "amnesia," where large language models and AI assistants repeatedly lose context between sessions, requiring users to re-explain information and maintain redundant knowledge across different tools. MEMM captures and organizes reasoning, conventions, and project knowledge in plain text Markdown files with YAML frontmatter, making the memory transparent, editable, and versionable by the user. The platform employs a scoring engine based on six signals—BM25, semantic similarity, graph relationships, recency, importance, and frequency—to rank and tier memories for each query. This approach aims to deliver high retrieval precision and context accuracy, while reducing token usage and latency. MEMM's engine operates with sub-millisecond query latency, and its tiered memory system ensures that only the most relevant information is injected into AI queries, avoiding overstuffed or irrelevant context. A governance layer tracks the health of the memory, surfacing stale entries, contradictions, and redundancies, and providing suggestions for consolidation and improvement over time. MEMM is designed for engineers and users who work with AI tools such as ChatGPT, Claude, Cursor, Codex, and local LLMs, allowing them to connect their AI assistants to a single source of structured knowledge via an MCP server. This eliminates the need to manually synchronize knowledge across multiple platforms and provides a unified, evolving memory accessible to all connected AI tools. The system supports categorizing knowledge as entities, concepts, sources, or syntheses, enabling AIs to reason over structured ontologies rather than flat text. The application is available for Mac, Windows, and Linux, and is built to be local and portable, ensuring that all knowledge remains owned and controlled by the user. MEMM does not rely on databases, embeddings, or black-box retrieval, instead prioritizing transparency and user ownership. Its open-source nature and focus on context engineering position it as a tool built specifically for the needs of the AI era.
- memoriuspypi.orgmemorius is an open-source SDK and CLI tool that offers a self-contained memory vault for AI agents, featuring vector search, session diaries, and agent-agnostic hooks. It is designed for AI developers needing persistent, searchable memory for agent workflows.
- MemDatamemdata.aiMemData is a decentralized memory infrastructure designed for autonomous AI agents and developers seeking persistent, searchable storage of unstructured data. The platform enables agents and applications to ingest files—including PDFs, images, screenshots, audio, and text—automatically handling optical character recognition (OCR) for images and PDFs, as well as audio transcription. Uploaded content is chunked, embedded, and indexed without the need for manual configuration or tuning, allowing users to query their data in natural language and receive relevant context with source citations. MemData is accessible via a REST API and supports integration with AI tools such as Claude, ChatGPT, Gemini, Cursor, and automation platforms like n8n and Make. Developers can interact with the service using API calls or the MCP server, and file ingestion and querying are demonstrated through simple command-line examples. The platform supports a variety of file types, including PDFs, PNG, JPG, MP3, WAV, M4A, and text files, and provides persistent, account-isolated storage. 3 and at rest with AES-256. Data is stored on US-based infrastructure using SOC 2 compliant providers, and users retain ownership of their data, which is not used for model training or sold. Data can be deleted at any time through the API or dashboard, with purging completed within 24 hours. MemData offers a tiered pricing model. The Free plan includes 100 MB of storage, 250 queries per month, a 10 MB file size limit, and access to OCR, audio transcription, and both API and MCP interfaces. The Pro plan, at $29 per month, expands storage to 10 GB, allows 10,000 queries per month, and increases the file size limit to 100 MB, adding priority support. The Scale plan, at $99 per month, provides 100 GB of storage, 50,000 queries per month, a 500 MB file size limit, priority support, and custom integrations. No credit card is required to start, and users can upgrade as needed. Positioned as a complete memory pipeline rather than just a vector database, MemData is built for AI builders and agents requiring long-term, semantic memory and context retrieval capabilities.
- AutoMemautomem.aiAutoMem is a persistent memory layer designed for AI agents, enabling them to recall both facts and their context rather than starting each session without memory. The tool addresses the challenge of agents forgetting previous interactions by capturing and organizing relevant information as users work, allowing for more effective and context-aware recall in subsequent sessions. AutoMem integrates into agent workflows by providing a memory architecture that combines a knowledge graph for relationships and a vector index for semantic meaning. The platform stores every memory in a graph structure, mapping out entities, relationships, and temporal data using FalkorDB, while also leveraging Qdrant for vector-based semantic search. This hybrid approach allows agents to retrieve not only semantically similar information but also the specific threads or contexts to which that information belongs. AutoMem consolidates new memories in the background, clustering related ideas, strengthening frequently accessed connections, and allowing irrelevant data to decay over time, resulting in increasingly relevant and refined recall. AutoMem is compatible with a range of agent clients and platforms, including Claude, Cursor, ChatGPT, Codex, and any client supporting the Model Context Protocol (MCP). It can be deployed locally via Docker, as a managed cloud service through Railway, or self-hosted within a user's own infrastructure, including Kubernetes environments. All deployment options expose the same MCP endpoint, ensuring consistent integration regardless of setup. The tool supports macOS, Linux, Windows (WSL2), and is accessible from both desktop and mobile clients that are MCP-compatible. The software is open source and distributed under the MIT License. AutoMem has been benchmarked using the neutral Agent Memory Benchmark (BEAM), where it achieved a high accuracy rate and was ranked second among competitors. Its design is informed by research focused on enhancing recall for AI agents, ensuring that memory compounds and becomes more useful over time.
- mnemosmaking-minds.aiMnemos is a local-first memory framework designed specifically for coding agents, with a focus on reliable, scoped memory management. The tool addresses the challenge of agent memory drift and scope confusion by keeping project, workspace, and global memory partitions separate, ensuring that knowledge relevant to each context remains distinct and does not accumulate contradictions. Mnemos is intended for solo coding-agent workflows, where maintaining accurate and adaptive memory across projects and sessions is critical. The platform operates using a single local SQLite file for persistence, allowing memory to survive restarts while remaining compact and efficient. It features a guided user interface (mnemos ui) for setup and host configuration, making operational readiness and host integration more accessible. Mnemos integrates with Claude Code, Claude Desktop, generic Model Context Protocol (MCP) hosts, and provides documentation for Codex setups. Its architecture is inspired by neuroscience, employing modules such as a Surprisal Gate for predictive coding, Mutable RAG for dynamic memory reconsolidation, an Affective Router for state-dependent retrieval, a Sleep Daemon for episodic memory consolidation and pruning, and Spreading Activation for associative memory priming. These modules enable Mnemos to selectively encode only surprising or salient information, adapt stored knowledge as new context emerges, blend semantic and affective cues for retrieval, and keep memory stores clean by consolidating and pruning episodic traces. The system is designed to avoid the pitfalls of standard append-only memory layers, which can lead to bloated, contradictory, and operationally opaque memory pools. Mnemos is open source and can be installed via pip. It does not require extra services, as all retrieval and consolidation processes are handled locally. The framework includes built-in tools such as a graph edges doctor and a health check utility (mnemos_health) to help users inspect and maintain operational readiness. Its tier 1 host support includes Claude Code, Claude Desktop, and generic MCP hosts, with additional documentation for integrating with Codex.
- mnemonnpypi.orgmnemonn is an MIT-licensed Python package that gives AI coding agents persistent project memory and a knowledge graph. It stores project context in SQLite and supports MCP-based integration for developer workflows.
- 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.
- getmem-aigetmem.aigetmem.ai is a persistent memory API for AI agents. It is described as a memory layer for agent applications that need to keep track of prior conversation turns and return grounded context on each new turn, with isolated per-end-user memory and reduced context token use. The service works by taking conversation turns as input, extracting structured knowledge, and storing it in both a typed graph and a hybrid vector index. Its retrieval path is presented as LLM-free and includes heuristic decomposition, fuzzy entity matching, parallel hybrid search, bounded graph expansion, ranking, and assembly of a structured prompt block. The page also says that each response includes per-stage meta information such as latency and token count. Other named details include a 12-category taxonomy, typed facts with tone and confidence, entity canonicalization with aliases and stable IDs, and a hybrid vector index with dense and sparse search plus a 17-field payload index. getmem.ai is shown as a tool for developers building AI agents and apps that depend on persistent user context. The page names OpenAI, Anthropic ChatGPT apps, LangChain, and Vercel AI SDK in an integrations section, and it presents two endpoints as the full integration surface: POST /v1/memory/ingest and POST /v1/memory/get. Ingestion is asynchronous and returns 202, while retrieval is synchronous. The page also notes idempotent ingestion and says retrieval is under 300 ms, with examples of tenant filtering and per-end-user isolation. Pricing is represented by a free credit to start. The page also includes a GitHub link and login link. It refers to a no-training API and mentions audit logging and per-patient scoping in a healthcare example, but those details are presented in the context of example use cases rather than as a separate product specification.
- Memrausememra.comMemra is a developer API and CLI tool that offers persistent, privacy-first memory for AI agents and LLM applications. It provides long-term semantic recall, PII masking, and is EU-hosted for compliance. Memra is designed for developers building advanced agentic systems requiring reliable memory infrastructure.
- Memoir Aimemoir-ai.devMemoir is memory infrastructure for AI agents. It presents itself as Git for AI memory, with a local-first, taxonomy-structured, Git-versioned store that lets agents explain, rewind, and branch their memory. The product is framed around problems such as context contamination, token rent, and memory drift. Its core capabilities include recall by path rather than similarity, time travel to reproduce bugs, and branching to test risky strategies. The page also describes automated branch shadowing, where memory branches follow git branches automatically via Claude Code hooks, and a merge workflow that moves lessons from a feature branch into the main knowledge base. Memoir also supports semantic path retrieval with hierarchical paths such as api.v2.auth. The text says it ships as a Claude Code plugin with automatic skills and hooks that follow git workflow. Memoir is built for coding agents and custom runtimes. It is shown with plugins or integrations for Claude Code, Codex, OpenCode, Hermes, OpenClaw, and LangGraph, and it also offers a Python SDK, a CLI, and an MCP Server for any MCP host. The installation examples include pip install memoir-ai for Python, and the page says the Python install is for the SDK or CLI. It also describes slash commands and hooks for session memory capture, context injection on start, and explicit recall or onboarding actions. The page lists Apache 2.0 licensing and Python 3.10+ support. It also refers to open-source coding agent support in the plugin ecosystem and to community-maintained plugins for some runtimes.
- memento-brain-collectorgithub.commemento-brain-collector is an open-source agent that collects memory files from various AI coding tools and synchronizes them to a central server. It supports cross-platform operation and is designed for developers working with AI-powered coding environments.
- memoria-frameworkpypi.orgmemoria-framework is an MIT-licensed Python framework for adding memory capabilities to AI agents and LLM applications. It supports retrieval-augmented generation and extensible memory workflows for developers building agent systems.
- MentisDBmentisdb.comMentisDB is a durable, self-hosted memory engine for AI agents. It is meant to keep memory persistent across sessions and shared across an entire fleet, while remaining owned by the user rather than an AI provider. The product describes itself as free, open source, and suitable for running on a laptop or server. Its memory model is append-only: each thought stores the hash of the thought before it. The site also says that agents bootstrap themselves over MCP, and that once connected, MentisDB teaches the agent how to use memory during the MCP handshake. It provides ranked search and grouped context in a dashboard, and the built-in skill system is presented as part of the memory workflow. Skills are immutable, versioned documents that can be uploaded, versioned, distributed, and revoked, and they are loaded at session start so agents use the same operating instructions. MentisDB includes a setup wizard that scans a machine and auto-detects Claude Code, OpenAI Codex, GitHub Copilot, Qwen Code, Cursor, VS Code, and more, then asks before applying changes. There is also a targeted setup command for configuring a single integration or all detected integrations, plus manual wiring instructions for individual tools such as Claude Code, OpenAI Codex, GitHub Copilot CLI, Qwen Code, Google Gemini CLI, OpenCode, VS Code + Copilot, and Claude for Desktop. The Claude for Desktop integration supports stdio, and the documentation says the stdio process can auto-detect a running daemon and proxy to it or launch one in the background. A web dashboard is included for browsing memory chains and inspecting individual thoughts. The project is released under the MIT License and is installed with a single command. The page states that Rust is required, and it links to GitHub, a cookbook, blog, docs, and Rust docs.
- memmangithub.commemman 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.
- Remnicremnic.aiRemnic is an open-source, local-first memory store that lets AI agents share context across sessions and tools. It stores memories as plain Markdown files on the user's machine, with recall and extraction workflows for Claude Code, Codex CLI, Cursor, ChatGPT, and MCP clients.
- memorpypi.orgMemor is a Python package that implements reproducible structured memory for large language models and autonomous agents. It enables consistent management of conversational history, context, and structured data across LLM interactions. Designed for developers building reliable AI agents, it is fully open source under the MIT license.
- yourmemoryyourmemory.aiyourmemory 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.
- mempalace-aipypi.orgmempalace-ai is an open-source CLI tool that adds memory and retrieval capabilities to AI agents. It mines projects and conversations into a searchable database, supporting vector-based retrieval without requiring an API key.
- 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.
- Memoryportmemoryport.aiMemoryport is permanent-memory software for AI conversations, built for persistent context across sessions with any LLM. It is local-first and open source, and its core promise is that each session can continue where the last one left off. Installation is described as a one-command setup for macOS and Linux, followed by an interactive wizard for configuring integrations. Once in use, conversations are indexed locally and context is injected only when relevant. The feature set includes a local LanceDB vector index with zero cloud dependency, optional Arweave storage for permanent backup, cross-device sync, and rebuilds from the chain. It also uses AES-256-GCM encryption with Argon2id key derivation. The tool includes what it calls intelligent retrieval, using a three-gate system with query expansion so the AI receives relevant context rather than everything at once. It also supports multi-tool memory across Claude Code, Cursor, Ollama, and OpenAI, and lists integrations for Claude Code MCP Server, Cursor MCP Server, Open WebUI, an Ollama proxy, an Ollama native API proxy, a ChatGPT OpenAI proxy, and any MCP client through a standard protocol. The page also reports benchmark results, including 97.9% session recall on LongMemEval, 500 million tokens tested, under 100 ms p95 retrieval, and 0.82 recall@10. Memoryport is licensed under Apache 2.0 and is presented with a full Rust codebase that can be read, self-hosted, or contributed to. The pricing section lists a free plan with unlimited local storage, Claude Code integration via MCP, Cursor integration, Ollama and Open WebUI support, knowledge graph visualization, session analytics, and encrypted-at-rest storage. A Pro plan is also offered at $9.99 per month and adds permanent memory backup, memories available forever after cancellation, about 250 million tokens per month, cross-device sync, and cold start rebuilds from the chain.
- memdpypi.orgmemd is a Python package that acts as an agent-driven project-memory curator. It helps maintain context, memory, and knowledge across AI agent sessions, particularly those using Claude and other LLMs. The tool is designed for developers building complex, long-running AI agent workflows that require persistent and intelligent memory management.
Ranked by how close each one sits to MEMANTO in the index, not by popularity. Back to MEMANTO →