MemPalace/mempalace
MemPalace is an open-source, local-first AI memory system that stores and retrieves conversation history verbatim using semantic search, supporting pluggable backends like ChromaDB and integrating ...
Awesome MCP › Knowledge & Memory
ConechoAI/openai-websearch-mcp
OpenAI WebSearch MCP Server gives an assistant web search performed by an OpenAI reasoning model rather than by a raw search API. The distinction matters: the model runs the searches, reads the results and returns a reasoned answer, so the output is synthesis rather than a list of links. It supports the current reasoning models — gpt-5, gpt-5-mini, gpt-5-nano, o3 and o4-mini — and exposes reasoning_effort as a parameter with sensible defaults chosen per use case, which is the cost and latency dial: gpt-5-mini at low effort for quick lookups, gpt-5 at high effort for something closer to deep research. Localised results are supported through location parameters, so queries whose answers depend on country or region return appropriately scoped information. Configuration is available through environment variables for deployment, and the tool parameters are documented in full so a client can choose them deliberately. It is a Python project requiring 3.10 or newer, published on PyPI as openai-websearch-mcp and MIT licensed. An OpenAI API key is required and usage is billed per call, with effort level directly affecting cost. The audience is people who already pay for OpenAI API access and want search with reasoning attached rather than adding a separate search provider.
https://github.com/ConechoAI/openai-websearch-mcp
Also in Knowledge & Memory
siyuan-note/siyuan
SiYuan is a privacy-first, self-hosted personal knowledge management system featuring block-level referencing, Markdown WYSIWYG editing, and support for the Model Context Protocol (MCP).
topoteretes/cognee
Cognee is an open-source project that provides scalable and modular memory capabilities for AI agents using ECL pipelines, enabling efficient management and retrieval of past interactions and diverse data types.
vectorize-io/hindsight
Hindsight is an agent memory system designed to create smarter, learning AI agents by moving beyond simple conversation history recall to encompass a biomimetic storage architecture for long-term m...
screenpipe/screenpipe
Screenpipe is a local-first, AI-powered memory tool that records computer activity (screen, audio, accessibility tree) to provide a searchable, automated context for personal AI agents and users, i...
Olow304/memvid
Memvid is a video-based AI memory library that stores millions of text chunks in MP4 files with ultra-fast semantic search, eliminating the need for traditional databases and enabling portable, efficient AI memory management.
EverMind-AI/EverOS
EverOS is an open-source Python framework for self-evolving, portable, long-term memory for AI agents, supporting multimodal ingestion and local-first persistence with Markdown as the source of truth.
MemTensor/MemOS
MemOS is a Memory Operating System for LLMs and AI agents that unifies long-term memory management, offering a single API for structured, multi-modal memory with enterprise-grade optimizations, sig...