Local semantic memory with PGlite + pgvector - budget Qdrant for AI agents
TypeScript client for Hindsight - Semantic memory system with personality-driven thinking
Persistent and semantic memory services for Smithers
EngramMCP — local-first semantic memory layer for AI agents
Semantic memory search for AI agents
Semantic memory storage and retrieval system for agent-relay with multiple backend support
Control plane for Hindsight - Semantic memory system
Tembory Memory node for n8n AI Agents with profile, tools, timeline, graph and semantic memory
Local-first semantic memory MCP server for Obsidian vaults
YuiHub Core - Semantic Memory Types and Utilities
memsearch plugin for OpenCode — semantic memory search across sessions
Mnemo core — persistent semantic memory engine (ONNX embeddings + HNSW + sql.js)
OpenClaw memory plugin for Flair — agent identity and semantic memory
Storage layer implementations (Working/Episodic/Semantic Memory) for Memo cognitive system
YuiHub Server - Semantic Memory API for Agentic AI
YuiHub MCP Server - Protocol Adapter for Semantic Memory
AtomicMemory plugin for Claude Code — persistent semantic memory across sessions.
Repository intelligence substrate — a persistent, queryable semantic memory layer for codebases, exposed via the Model Context Protocol (MCP).
Local-first semantic memory for Pi coding agent. Powered by LogosDB MCP server — vector search, zero cloud, stdio-only.
Long-term semantic memory for AI agents (TypeScript)
Semantic memory MCP server for Claude Code. Local knowledge graph with vector search — powered by Neo4j.
Evolving semantic memory and intent router — CST tokenizer + HDC algebra
Agent Memory OS — semantic memory for AI agents
AtomicMemory plugin for OpenClaw — persistent semantic memory and deterministic session snapshots across channels.
Hybrid semantic search with SQLite, FTS5, and HNSW — built for AI agents
Transform Forge export envelopes into projection import batches for semantic-memory
Forge verification truth: evidence bundles, export envelopes, and causal estimation substrate
Shared identity, scope, and trace primitives for the local-first AI systems stack
Production-grade AI Agent framework for Rust — ReAct engine, multi-agent, memory, streaming, MCP, IM channels, workflows
Multi-channel agentic AI runtime with tool-calling, memory, and scheduling
Blazen - A Rust-native AI workflow engine with event-driven orchestration
AI memory systems with hyperdimensional vectors and chaotic reservoirs
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.
LEX agentic memory domain: episodic, semantic, and working memory
Hierarchical persistent memory with semantic search for SwarmSDK AI agents
Official Ruby SDK for Supermemory. Add persistent memory to AI applications with document management, semantic search, user profiling, and integrations with ruby-openai, graph-agent, and langchainrb.
Agentf is a Ruby-native multi-agent workflow engine with an ORCHESTRATOR, role-specialized agents, provider adapters (OpenCode/Copilot), and Redis-backed semantic, episodic, and graph-style memory. It includes a unified CLI, MCP server tools, and install/update workflows for generated agent/command manifests.
RobotLab is a Ruby framework for building and orchestrating multi-robot LLM workflows. Built on ruby_llm, it provides robots with template-based prompts, tools, and shared memory; networks for coordinating multiple robots with intelligent routing; MCP (Model Context Protocol) integration for external tool servers; and a memory system with Redis backend and semantic caching. Optional gems add Rails integration (robot_lab-rails), durable learning (robot_lab-durable), Ractor concurrency (robot_lab-ractor), and document storage (robot_lab-document_store).
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.
A simple, but feature-complete Ruby binding for OpenLDAP's libldap. This binding is intended as an alternative for [ruby-ldap][] for libraries or applications which require a more complete implementation of the LDAP protocol (according to [RFC4511][]) than it provides. Additions or changes: * Referrals for add, modify, delete, modrdn, compare * Controls for add, modify, delete, modrdn, compare * Asynchronous and synchronous APIs * Detailed exception class hierarchy for results instead of just one class for all non-success results. * Complete [RFC4511][] support: - extended operations and results - unsolicited notifications - continuation references - intermediate responses - alias deferencing - etc. * Cleanly abandon terminated operations where supported * Memory-handling cleanup to avoid leaks, corruption, and other problems experienced in the wild. * Drop deprecated non-_ext variants of operations which have a modern equivalent. * M17n for Ruby 1.9.x. * Improved test coverage **NOTE:** This library is still under development, and should not be considered to be feature-complete or production-ready. This project's versions follow the [Semantic Versioning Specification][semver].
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.