21 packages found
[knowledge-rag] - Drop docs, search instantly from Claude Code — 12 MCP tools, 20 format parsers, hybrid search + rerank
Persistent memory system for AI coding assistants. Captures decisions, learnings, and context from coding sessions. Feat
On-device memory layer for AI agents. Claude Code, Hermes and OpenClaw. Hooks + MCP server + hybrid RAG search.
Persistent memory MCP server for AI agents — Rust, 19 tools, knowledge graph, Hebbian learning, episodic memory, contrad
A Multi Agent Memory MCP That Connect Agents Across Systems and Machines
Local-first persistent agentic memory powered by Recursive Memory Harness (RMH). Open source must win.
Persistent memory for AI coding agents. Semantic knowledge + searchable archives in SQLite, served as an MCP server. HES
Make every AI agent you use smarter. Persistent memory with SQLite FTS5, MCP server, Obsidian sync, and self-learning in
Local-first AI memory system in Rust with SQLite storage, semantic search, knowledge graph, MCP server, and CLI.
DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agents for fast
Korean persona dataset (NVIDIA Nemotron-Personas-Korea) → SQLite + FTS5 + MCP server for AI agents
Persistent, searchable context storage across Claude Code sessions using SQLite + FTS5
Nornicdb is a distributed low-latency, Graph+Vector, Temporal MVCC with all sub-ms HNSW search, graph traversal, and wri
Hivemind turns your traces into reusable skills across agents
This is a TypeScript-based MCP server that provides database interaction capabilities through ArangoDB.
MCP server for Obsidian vaults — plugin-free search, memory, and full vault access for any AI agent
MCP server for semantic search using local Qdrant vector database and OpenAI embeddings
@zilliztech✓ OfficialAgent skill that teaches LLMs to operate Milvus vector database using pymilvus — connection, collections, vector CRU
Memory engine for AI agents — time axis (3-layer decay/promotion) + space axis (self-organizing topic tree). Hybrid sear
Palaia — Local, crash-safe memory for AI agents. Semantic vector search (fastembed/OpenAI/Ollama). SQLite + sqlite-vec o