- lean-memory @wuesteon/lean-memoryEmbedded, local-first agent memory: one SQLite file per namespace, no server, no cloud.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.43 GitHub stars.
- Callimachus @betabots-llc/callimachusMCP server for Callimachus: local index and search of your AI coding-agent threads4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.43 GitHub stars.
- Perenna @scarletkc/perennaA lightweight, Git-backed permanent memory for AI agents.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.42 GitHub stars.
- Agent Memory MCP @ipiton/agent-memory-mcpMemory, docs, and repo context layer for engineering agents.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.42 GitHub stars.
- Inite Brain @inite-ai/inite-brain-serviceOpen-source bitemporal memory layer for LLM agents — knowledge graph with conflict resolution.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.41 GitHub stars.
- Kage @kage-core/kageVerified memory for coding agents: claims cited against code, stale withheld, savings receipts.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.40 GitHub stars.
- Cartographer @beppetemp/cartographerGovernance MCP server for agent-maintained knowledge bases (OKF): git-backed writes, search, lint.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.37 GitHub stars.
- Mnemex @simplemindedbot/mnemexTemporal memory for AI with decay and reinforcement. Two-layer storage (JSONL + Markdown).4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.36 GitHub stars.
- RemembrallMCP @cdnsteve/remembrallmcpPersistent knowledge memory for AI agents. Hybrid search, code graph, pgvector.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.35 GitHub stars.
- Cortex Memory Engine @gambletan/cortexLocal-first AI memory engine — 4-tier memory, people graph, Bayesian beliefs. Encrypted, 62µs.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.35 GitHub stars.
- A Mem @diaaaj/a-mem-mcpSelf-evolving memory system for AI agents5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.35 GitHub stars.
- Kindex @wandercom-io/kindexPersistent knowledge graph and MCP server for AI workflows with git-tracked project context.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.34 GitHub stars.
- Enquire @oomkapwn/enquire-mcpLong-term memory for AI agents — your Obsidian vault as searchable persistent memory.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.34 GitHub stars.
- Tokenmizer @shweta-mishra-ai/tokenmizerGraph-backed session memory for LLMs: checkpoint, resume, file analysis, token-savings stats.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.33 GitHub stars.
- Graqle @graqle/graqleDev intelligence layer: 7 MCP tools for graph-powered codebase reasoning.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.32 GitHub stars.
- Genesys Memory @astrix-labs/genesys-memoryOpen-source causal memory for AI agents: persistent, explainable, MCP-native memory (13 tools).4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.31 GitHub stars.
- Remem @majiayu000/rememLocal-first automatic memory for Claude Code and Codex: capture, distill, recall from SQLite.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.31 GitHub stars.
- MemoryIndustry @leandropg19/memory-industryMemoryIndustry persistent memory MCP server: BM25+MMR retrieval and audit.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.29 GitHub stars.
- Cuba Memorys @leandropg19/cuba-memorysPersistent memory MCP server. 28 tools, BM25+MMR+OOD retrieval, tamper-evident audit, code graph.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.29 GitHub stars.
- MemoCat — Shared AI Memory @montygovernance/memocat-mcpOne shared, persistent memory across AI agents and systems, with semantic recall and live updates.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.28 GitHub stars.
- Magpie Search @xfloukiex-lab/magpie-searchFederated local-first search across transcripts, files, KG, vectors and the web for AI agents.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.28 GitHub stars.
- Engram @kael-bit/engramHierarchical memory for AI agents. Three-layer (buffer/working/core) with decay and promotion.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.28 GitHub stars.
- Montycat MCP - Shared Memory for AI Agents @montygovernance/montycat-mcpShared, persistent memory for AI agents, with semantic recall and live updates.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.27 GitHub stars.
- ZenBrain Memory @zensation/zenbrainSeven-layer agent memory: episodic, semantic, procedural and core. Local SQLite, no account.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.27 GitHub stars.
