- Factum @factum-project/factumAuditable memory for AI agents: provenance, cascade retraction, conflict refusal4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from cargo.3 GitHub stars.
- OpenReflex @vishnu-77/openreflexOptional diagnostics MCP server for OpenReflex's ambient project muscle memory.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.3 GitHub stars.
- MCP Context Card @wolfe-jam/mcp-context-cardMCP server for a project's context (AGENTS.md), memory, and identity — base or drop-in extension.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- Facthouse @gordonkjlee/facthouseLocal AI memory: neuroscience-inspired Data→Information→Knowledge in SQLite you own.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- FactMem @gordonkjlee/factmemA local memory engine. You own the SQLite file. Not Mem0's hosted OpenMemory MCP.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- Th Memory @worakorn-prince/th-memory-mcpLocal long-term memory MCP server (SQLite) for AI coding agents — OpenCode, Claude Code, Cursor4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- Pathmark @hacksurvivor/pathmarkLocal-first intent and provenance for Codex, Claude Code, Cursor, Gemini CLI, and MCP agents.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- GRAFOMEM CGR Capture @grafomem/cgr-captureRecord agent judgments and their real outcomes on GRAFOMEM Cloud. Capture now, score later.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.3 GitHub stars.
- Aifp @wjabanjj/aifp-mcpPersistent memory MCP server for AI coding assistants. Chinese-first and fully local.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- Firekeep @kapella-hub/firekeepSelf-hosted operating layer for AI agents: knowledge, continuity, coordination, and governance.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.3 GitHub stars.
- Marrow @aryawidjaja/marrowShared memory for parallel AI coding agents. Local, free, with rooms and file claims.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.3 GitHub stars.
- Weasley DeepMind @potatohoney-p/weasley-deepmindSecure, fragment-based long-term memory for MCP-compatible AI agents.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- Aiko @masa-san-jp/aikoA portable persona for MCP clients — the same agent in Claude Code, Codex, Cursor and VS Code6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- soulSketch @bytewizard42i/soulsketchPortable, user-owned AI memory packs: read, validate, fingerprint, diff, and observe5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- mneme Record @onourimpram/mnemeVault-native, accountable memory for Claude Code and MCP clients. Markdown is ground truth.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- misMEM @lucasmella-stack/mismemCooperative persistent memory for LLMs: episodes, memories and traits over SQLite (FTS5, Hebbian)5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- Talamus @ampres-ai/talamusLocal-first, source-grounded memory that survives AI agent sessions.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.3 GitHub stars.
- Memex @evan-moon/memexLocal-first second brain with semantic search. Markdown notes indexed by a local ML model.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- Nahuali @arakiss/nahualiTrust-aware agent memory with evidence-backed recall, self-inspection, and audit history.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.3 GitHub stars.
- Ariadne @mclaut/ariadneLocal-first multilingual, auditable memory for Codex, Claude Code, and MCP clients.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.3 GitHub stars.
- Memkeeper @teflon07/memkeeperLocal-first memory for AI agents: on-device hybrid retrieval over a single SQLite file.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.3 GitHub stars.
- Cosmos @teampolarity/cosmos-mcpPersonal knowledge graph every MCP client reads from and writes to. Portable across agents.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- Forkmind @medhovarsh/forkmindBranchable LLM history DAG + encrypted context capsules agents can save, restore, and crypto-shred.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- SMRITI Memory @shivamtyagi18/smriti-memoryNeuro-inspired long-term memory for AI agents with semantic graph and consolidation.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.3 GitHub stars.
