Local-first MCP memory server for multi-agent systems. Hybrid search (BM25 + semantic embeddings), SQLite-backed, zero-config.
No description provided.
Lightweight core CLI surface for Claude Flow — memory + hooks commands only. Designed to load fast on cold npx cache (<5s) so plugin skills don't race the 30s MCP-startup timeout. The full @claude-flow/cli metapackage lazy-loads everything else on top of
Codex CLI integration for Ruflo (claude-flow) - OpenAI Codex platform adapter
Create a new LangGraph project
Simple in-memory vinyl file store
Memory module - AgentDB unification, HNSW indexing, vector search, hybrid SQLite+AgentDB backend (ADR-009)
High Performance In-Memory Cache for Node.js
In memory chunk store that is abstract-chunk-store compliant
Apache Arrow columnar in-memory format
A simple CRUD based persistence abstraction for storing objects to any backend data store. eg. Memory, MongoDB, Redis, CouchDB, Postgres, Punch Card etc.
Azure AI Projects client library.
Local-first graph memory CLI for AI agents
Coding agent CLI with read, bash, edit, write tools and session management
Tomahawk plugin, implementing a Key Value Pair Store in Memory.
[](https://www.npmjs.com/package/@n1ru4l/in-memory-live-query-store) [](https://www.np
Node.js atomic and non-atomic counters, rate limiting tools, protection from DoS and brute-force attacks at scale
The Memory Layer For Your AI Apps
Clementine — Personal AI Assistant (TypeScript)
A really fast memory store for better-queue
Four-layer local memory system plugin for OpenClaw — auto-captures, structures, and profiles conversational knowledge using local LLM + SQLite vector search (L0→L1→L2→L3 pipeline)
Maps proxy protocols to `http.Agent` implementations
Turn a function into an `http.Agent` instance
An HTTP(s) proxy `http.Agent` implementation for HTTPS
Engram gives AI agents durable, long-term memory. It recalls relevant facts about a user and injects them into the prompt, so an agent appears to remember across sessions. Framework-agnostic core with a ports-and-adapters design; first-class Rails and RubyLLM integration. Your memories live in your own database — no external memory service.
Provides RobotLab::DocumentStore — a thread-safe, in-memory semantic search store backed by fastembed (BAAI/bge-small-en-v1.5). Store text documents by key and retrieve the closest matches to a natural-language query using cosine similarity. Works standalone or as a drop-in extension for robot_lab agents and networks.
Tulving semantic memory store for brain-modeled agentic AI — concept storage, taxonomic relations (is_a, has_a, part_of), spreading activation retrieval, and knowledge consolidation with confidence-based decay.
HeapPeriscopeUi is a Rails engine designed to help developers monitor, visualize, and diagnose memory-related issues within their Ruby applications. It functions by listening for UDP packets containing GC profiler reports and heap snapshots, typically transmitted by a companion agent (like `heap_periscope_agent`). The engine efficiently processes this data: GC reports are batched for optimized database insertion, while comprehensive heap snapshots, including detailed object counts by class, are stored transactionally. Furthermore, HeapPeriscopeUi can broadcast incoming metrics via ActionCable for real-time dashboard updates. Its integrated web interface allows users to browse, filter, and analyze the collected profiler reports, facilitating the identification of memory leaks, excessive object allocations, and opportunities for performance optimization.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.