- Kybase @kyrzin/kybaseSelf-hosted Markdown memory for AI agents: notes you can read and edit, with hybrid search.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.5 GitHub stars.
- Cairn Remembers @cairnremembers/cairn-remembersLocal memory your AI tools share: decisions, notes and corrections that carry across sessions.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.5 GitHub stars.
- Mushroomdb @matthewsherlin/mushroomdbEmbedded graph database for agents: declare association rules once, edges maintain themselves.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from cargo.5 GitHub stars.
- Fireweed @starksood/fireweed-mcpAgent memory where every fact carries a receipt, and deletion is provable.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.5 GitHub stars.
- THOR @nworks3d/thorLocal memory for coding agents; a rule with a proof can refuse. Full install with hooks: the repo.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.5 GitHub stars.
- Dreamd @botzrdev/dreamdLocal-first, cross-harness memory for AI coding agents.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.5 GitHub stars.
- Pseudolife Memory @pseudogiant-xr/pseudolife-mcpPersistent memory for MCP-compatible agents: memory bank, fact cortex, dreams, graph.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.5 GitHub stars.
- Ctxfile @ctxfile/ctxfileLocal-first MCP server that snapshots your project's working state into one context object.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.5 GitHub stars.
- Mif Tools @varun29ankus/mif-toolsConvert, validate, and inspect AI agent memories across formats5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.5 GitHub stars.
- agentmem @oxgeneral/agentmemLightweight persistent memory for AI agents. Hybrid search. 16 tools. One SQLite file.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.5 GitHub stars.
- Iranti @nfemmanuel/irantiPersistent, shared memory for AI agents — facts, checkpoints, semantic search.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.5 GitHub stars.
- Memex @dioniipereyraa/memexOne searchable memory of your Claude.ai chats and Claude Code sessions, served over MCP.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.5 GitHub stars.
- Claude Code Conversation Search @tonysimonovsky/claude-code-conversation-search-mcpSearch Claude Code conversation history with natural language queries across all projects12% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.5 GitHub stars.
- Thronglets @shangri-la-0428/throngletsP2P shared memory substrate for AI agents — stigmergic knowledge network via libp2p39% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.5 GitHub stars.
- Rekindle @skitchy/rekindleMCP session continuity engine. Boot reports, orientation scoring, and end-session capture. SQLite.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.5 GitHub stars.
- AIppocampus @sapientropic/aippocampusLocal-first, source-backed continuity for AI agents via stdio MCP.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.5 GitHub stars.
- Nan Forget @nanmesh/nan-forgetAI that remembers. Local-first cross-session, cross-project long-term memory for coding tools.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.5 GitHub stars.
- Rememb @luizedupp/remembPersistent memory for AI agents — local JSON, zero config, no server required.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.5 GitHub stars.
- Contextful @inferensys/contextfulEfficient context management: code search, evidence packs, and memory for coding agents.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.5 GitHub stars.
- M1K3 @m1k3/m1k3Private memory, documents, voice and a local LLM for your agents, served by a Mac app on-device.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.4 GitHub stars.
- MemoryGuard @merakosiris/memoryguardLocal-first governed MCP memory backend for coding agents.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.4 GitHub stars.
- Gemdex @nikships/gemdexPersistent memory layer for AI coding agents: save, recall, update via Gemini plus LanceDB5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.4 GitHub stars.
- Graphiti Local @renezander030/graphiti-localLocal-first temporal knowledge graph with six read-only MCP tools and human-reviewed writes.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.4 GitHub stars.
- Mitos @dovahkiin-v/mitosArchitectural decision memory for LLM-native workflows — markdown for humans, a graph for agents.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.4 GitHub stars.
