- M3 Memory @skynetcmd/m3-memoryLocal-first memory — 100+ tools, 99.2% LongMemEval-S retrieval@8, hybrid search, GDPR, no cloud.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.26 GitHub stars.
- Audrey @evilander/audreyLocal-first biological memory for coding agents: recall, consolidation, and pre-action Guard checks.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.26 GitHub stars.
- Fidelis Memory @hermes-labs-ai/fidelis-memoryRecall locally stored agent memories through an MCP-compatible host.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.24 GitHub stars.
- Infimium @aryankumar06/infimiumPrivate AI context layer for semantic code search, dependency graphs, memory, and workspaces.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.24 GitHub stars.
- hmem — Humanlike Memory for AI Agents @bumblebiber/hmem-mcpPersistent 5-level hierarchical memory for AI agents. SQLite-backed, lazy-loaded.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.24 GitHub stars.
- Yantrikdb @yantrikos/yantrikdb-mcpCognitive memory for AI agents — semantic recall, knowledge graph, and contradiction detection5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.24 GitHub stars.
- Selvedge @masondelan/selvedgePersistent decision memory for AI coding agents: rationale, rejected approaches, and entity history.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.24 GitHub stars.
- Delimit — Keep the state. Change the model. @delimit-ai/delimit-mcp-serverKeep the state. Change the model. Shared context and a multi-model panel across coding assistants.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.24 GitHub stars.
- Memento @runmemento/mementoLocal-first, LLM-agnostic memory layer for AI assistants.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.24 GitHub stars.
- SAME - Stateless Agent Memory Engine @sgx-labs/samePersistent memory for AI coding agents. Local-first SQLite + vector search. 17 MCP tools.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.23 GitHub stars.
- World Model @saravananjaichandar/world-model-mcpTemporal knowledge graph for codebases with constraint enforcement at the edit boundary.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.23 GitHub stars.
- Claude FAF @faf/claude-faf-mcpPersistent project context for Claude. IANA-registered .faf format.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.23 GitHub stars.
- Clude @sebbsssss/cludePortable agent memory anchored on Solana. Local SQLite + vector recall, open export.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.22 GitHub stars.
- Engram @jamjet-labs/engram-serverDurable memory for AI agents: fact extraction, hybrid retrieval, temporal graph. SQLite/Postgres.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.22 GitHub stars.
- Yggdrasil @vondervuflya/yggdrasilOne shared, durable memory for your AI coding agents — local-first, zero-dependency.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.22 GitHub stars.
- memo @jagoff/memoMemory for AI agents — MLX (Apple Silicon) or CPU (Linux), sqlite-vec + BM25, zero cloud.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.21 GitHub stars.
- Connapse @destrayon/connapseSelf-hosted knowledge backend for AI agents with hybrid search and MCP tools5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.21 GitHub stars.
- Memory Journal @neverinfamous/memory-journal-mcpDeveloper journal with knowledge graphs, relationships, Git context, and semantic search4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.20 GitHub stars.
- Neurodivergent Memory @jmeyer1980/neurodivergent-memoryPersistent knowledge graph MCP server for neurodivergent thinking. BM25 search, no cloud LLM.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.20 GitHub stars.
- GoodMemory @hjqcan/goodmemoryDurable user/project memory for MCP clients: recall context and remember selected facts.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.19 GitHub stars.
- Context Mem @jubakitiashvili/context-memPersistent memory for AI agents — 98%+ retrieval recall, 99% token savings, 44 tools5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.19 GitHub stars.
- Grok FAF @faf/grok-faf-mcpPersistent project context for xAI Grok. IANA-registered .faf format.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.19 GitHub stars.
- Mnemosyne OS @mnemosyne-os/mcpMemory the human governs, on their own machine, plus what other coding agents here wrote.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.18 GitHub stars.
- mcp-me @paladini/mcp-meExpose your personal, professional, educational, and social profile to any AI assistant via MCP.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.18 GitHub stars.
