16 skills found
MemTensor / MemOSSelf-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings
1jehuang / jcodeThe most RAM efficient harness
Beledarian / mcp-local-memoryA lightweight, powerful local memory server for AI agents supporting text, entities, and relations. Enables persistent codebase understanding and user preference management.
cedricvidal / memorious-mcpSemantic Memory for MCP. 100% Local & Private. Store, recall, and forget with vector search via ChromaDB
kapillamba4 / code-memoryMCP server with local vector search for your codebase. Smart indexing, semantic search, Git history — all offline.
zycaskevin / Vault-Agent-MemoryLocal-first memory governance for AI agents: shared, reviewable, auditable memory via SQLite and MCP.
remete618 / widemem-aiNext-gen AI memory layer with importance scoring, temporal decay, hierarchical memory, and YMYL prioritization
TheMasonX / MemorySmithSingle-host ASP.NET Core app for local structured memory management — Blazor UI, MCP endpoint, hybrid search, and chat/agent with Ollama and GitHub Copilot.
3ksoft / schema-popMemory-layout-first schemas for zero-copy cross-language data structures.
alioshr / memory-bank-mcpA Model Context Protocol (MCP) server implementation for remote memory bank management, inspired by Cline Memory Bank.
Dataojitori / nocturne_memoryA lightweight, rollbackable, and visual Long-Term Memory Server for MCP Agents. Say goodbye to Vector RAG and amnesia. Empower your AI with persistent, graph-like structured memory across any model, session, or tool. Drop-in replacement for OpenClaw.
cyanheads / filesystem-mcp-serverA Model Context Protocol (MCP) server for platform-agnostic file capabilities, including advanced search/replace and directory tree traversal
MemPalace / mempalaceThe best-benchmarked open-source AI memory system. And it's free.
LycheeMem / LycheeMemLightweight Long-Term Memory for LLM Agents.
LuiggiVal08 / toon-memoryMCP server giving AI coding agents offline, token-efficient persistent memory — recall decisions, patterns, and bugs across sessions with 68.5% fewer tokens than re-reading context. No LLM, no server; works with 15+ agents.
DeusData / codebase-memory-mcpHigh-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.
