- Giljo HQ @giljo/hqContext engineering for AI coding agents: product context, project missions, and 360 memory.20% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Memory Pulse @t-crew/memory-pulseCorrections that outlive the session. A guard blocks the edit that writes the old value back.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Agent Recall Trail @fantasyce/agent-recall-trailPrivate Agent memory and governed shared knowledge.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- Tugra @tugra-ai/tugraProvenance-aware memory format for AI agents: every claim carries its source, age and boundary.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- KMP @underpass-ai/kmpLocal-first agent memory that preserves what happened, when and why5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- Universal Research @mp-juns/universal-research-mcpProvenance-first research memory with hash-bound evidence and a fail-closed eligibility gate.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- MCP Light Memory @peterpirog/mcp-light-memoryLocal-first persistent memory for coding agents and MCP clients.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- Trail @usetrail/trailIssue tracker and durable project memory for your coding agent, scoped to the folder you open.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Oneda @freeelatech/onedaPersistent, governed institutional memory for Claude Code — specs, decisions, learnings.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- RCLL @rcll/fleet-memorySelf-hosted shared memory for a team of AI agents. Rooms, L0-L3 depth, no LLM on the read path.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- OMEM @troybrandonc-bit/omemMemory for AI agents that tracks beliefs over time and surfaces contradictions5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- SoluCortex @soluai-spa/solucortex-mcpLiving technical memory for AI agents: recall approved project context, record what was learned.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Cap Shield @robinlidberg-dot/cap-shieldContext selection and compression for AI agents - recall measured, not claimed.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Loreweave @lets-order-some-fries/loreweaveDurable agent memory over a markdown vault: bitemporal facts, timelines, hybrid graph search.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- metabrain @ariaxhan/metabrainMCP server giving AI agents persistent SQLite memory that proves which lessons hold.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- BanditDB @banditdb/mcpPersistent decision memory for agents — learns which action works in which context3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Traveler.md @traveler/mcpA traveler's portable travel profile and trip plans. It remembers, it does not search or book.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- kbdb @diko316/kbdbA searchable second brain for AI agents: ranked keyword and semantic search over your Markdown.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Mnemosyne @tripnet/mnemosyneKnowledge commons for agent lessons, questions, and direct long-form peer discussions.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Khwan @khwan/khwan-mcpDurable AI memory: recall distilled facts in a later session or subagent, and remember new ones.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Aura @rohnelt/auraEmail address, webhook, durable memory and zero-token waiting for agents. Paid in USDC via x402.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- UseMyContext.ai @usemycontext/usemycontextPersonal context for AI, written by you and never scraped: your profile and files, any MCP client.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- CogMemory @skylarng89/cogmemory-mcpCogMemory MCP Server — Unified context subsystems for AI coding agents5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Polypack Memory @imattau/polypack-mcpMCP server exposing Polypack as persistent adaptive memory5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
