69 packages found
Persistent AI memory for Claude Code, OpenClaw, and any MCP-compatible agent. BM25F + vector hybrid, governance-aware, l
Redis Vector Library (RedisVL) -- the AI-native Python client for Redis.
Durable hybrid memory for AI agents: vector + BM25 + temporal + graph recall, exposed through MCP, HTTP, and Python.
A Python library powered by Language Models (LLMs) for conversational data discovery and analysis.
SQLite-backed MCP Memory Server with WAL concurrent safety, FTS5 search, session tracking, task management, and cross-ma
MCP server for semantic code search — AST-aware chunking, hybrid dense+sparse search, 160+ languages
CPersona — Persistent AI memory server with 3-layer hybrid search, confidence scoring, and 29 tools. MIT licensed.
A Retrieval-Augmented Generation (RAG) system that leverages Google's Agent Development Kit (ADK) and Qdrant vector data
Agent memory for LLMs: 30 runnable Jupyter notebooks covering conversation buffers, vector stores, knowledge graphs, epi
Long-term memory for LLMs. MCP server backed by hybrid search in a single SQLite file.
Production-grade persistent memory service for AI agents — FastAPI + pgvector + local ONNX embeddings
High-precision calculator MCP server — goes beyond arithmetic to calculus (derivatives, integrals) and equation solving,
Interactive LLM Powered NPCs, is an open-source project that completely transforms your interaction with non-player char
Self-improving memory for AI agents
A lightweight, rollbackable, and visual Long-Term Memory Server for MCP Agents. Say goodbye to Vector RAG and amnesia. E
AI Skill for OMG Payment Gateway (歐買尬金流) - Taiwan third-party payment API with credit card, ATM, CVS support | 台灣第三方金流串接
The best-benchmarked open-source memory system for AI coding assistants
AI-powered documentation RAG system with MCP server for Claude Code. Search and retrieve technical documentation on-dema
剧本分镜工具智能体（PenShot）：电影/动漫/短剧/小说/剧本→分镜→片段→prompt | 基于 LangGraph+LLM，自动解析任意格式剧本，生成 Sora/Veo/Runway 等模型可用的连贯text-to-video提示词
A deliberately lite personal brain: Obsidian to browse, Claude Code for everything else. No vector DB, no embeddings, no
Unreal Engine Vibe Coding tool
Self-evolving memory across Agent and platform. The one portable memory layer for every agent they use - Claude Code, Co
Parameterized multi-agent orchestration framework for Claude Code and Gemini
Self-hosted documentation RAG pipeline that serves semantic search to LLM agents over the Model Context Protocol.
Cognitive memory for AI agents. Pure Rust, <1ms recall, 2.7MB, zero cloud. Patent Pending.
Cognitive memory for AI agents. Pure Rust, <1ms recall, 2.7MB, zero cloud. Patent Pending.
Fast Python web crawler for RAG and AI ingestion. Extracts clean Markdown from any site for LLMs and vector stores.
Memory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents
Modular Python framework for AI agents and workflows with chain-of-thought reasoning, tools, and memory.
AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https://disco
历年ICLR论文和开源项目合集，包含ICLR2021、ICLR2022、ICLR2023、ICLR2024、ICLR2025.
Zero-config MCP server for searchable documentation (SQLite default, PostgreSQL optional)
Local-first, project-aware memory MCP server for Claude Code, Codex, and other AI agents, with Obsidian and an owner das
Personal Telegram knowledge base — forward anything, search via DM. Hybrid SQLite + FTS5 + vector + voice, MCP server fo
One memory. Every AI tool. Yours to keep. Local-first, MCP-compatible, Apache 2.0.
@Abhigyan-ShekharMCP server for external memory layer for AI agents + more . Download from pypi , and get started
Governed memory for long-lived coding agents. Trust, provenance, conflict detection. Local-first.
Always-on context for AI agents: screen capture, OCR, voice, MCP server. Local-first, AGPL-3.0.
Project-scoped Qdrant MCP server for workspace collections with scratchbook functionality. Python port of claude-qdrant-
Persistent semantic memory server for MCP - Give your AI long-term memory that survives across conversations. Lightweigh
The missing layer between AI and the web. Open-source escalating web unlocker + read/search/transcribe/grab across web,
Your AI agent finds the right files. Every time. Code graph context engine with 24 MCP tools — 170+ languages, triple se
Learn AI, ML, and NLP with interactive Jupyter Notebook tutorials.
Persistent memory and session intelligence for AI coding assistants. Auto-tracks mistakes, decisions, and context via ho
Universal memory layer for AI applications. Self-host in minutes. Open source.
Persistent engineering memory for coding agents over MCP.
A multi-step LangChain v1 sales-conversation agent that uses the Azure OpenAI Responses API, an MCP server with Postgres
pythonanywhere-mcp-server
Secure, local-first MCP server exposing ArcGIS Pro's ArcPy engine over stdio JSON-RPC.