Memory for AI MCP
Local codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Memory, knowledge bases and documentation search. Includes retrieval services that store what your agent learns between sessions.
Local codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Review-gated declarative long-term memory with bounded read-only MCP access.
Local-first memory and knowledge graph for coding agents. Compact retrieval, no network.
MemoryIndustry persistent memory MCP server: BM25+MMR retrieval and audit.
Persistent memory MCP server. 28 tools, BM25+MMR+OOD retrieval, tamper-evident audit, code graph.
Zero-model recall over your docs: the section that answers a question, in about a millisecond.
Persistent semantic memory for AI agents using local ChromaDB vector search. No cloud required.
Story continuity, novel memory, and series bible for fiction writers, shared with AI assistants
Verifiable agent memory with signed ledger receipts — verify every write offline.
Spanish dialect localization MCP server: 25 regional variants, glossary, adversarial QA gates.
AI-verified knowledge base with trust scoring, temporal facts, and skill cards.
Local-first personal knowledge base. Cited answers from your vault via vector + graph retrieval.
Permanent on-chain memory for AI agents on Lightchain via a one-time unlock.
Persistent semantic memory for AI agents with knowledge graphs and Intelligence Packs.
Persistent semantic memory for AI agents with knowledge graphs and Intelligence Packs.
UNBLOCK org-brain — shared memory and comms for human + agent teams. By Kaeva Labs.
Persistent memory for AI agents — 98%+ retrieval recall, 99% token savings, 44 tools
Read, write and scan process memory, Cheat Engine style, on Windows, Linux and macOS.
28-layer cognitive substrate with cross-session ToT evolutionary memory and self-telemetry tools
Public working memory for AI agents: messages, shared pages, and resumable tasks.
Local-first personal memory and model server for trusted MCP agents on macOS.
Per-app CPU, efficiency-core and memory control for Apple Silicon Macs, with suggestions and undo.
Computer use for Hyprland: semantic desktop state over IPC, plus vision and native input
Pre-action gates that block AI agents from repeating known mistakes.