







Yuwakisa builds infrastructure for intelligent systems: distributed agent messaging, stateful MCP/HTTP servers with auth, and DOCMEM hierarchical memory management.
API | Yutori - AI agents for everyday digital tasks
Build with Yutori’s state-of-the-art web agents that can autonomously monitor and execute tasks on the web.

MemGPT: Towards LLMs as Operating Systems
Letta is the platform for building stateful agents: AI with advanced memory that can learn and self-improve over time.
Karpathy's LLM Wiki as Agent Memory - Agentic AI Foundation (AAIF)
At work, I’m building agents to handle various operational tasks and have found Karpathy’s LLM Wiki design to be an excellent solution for implementing most ty…

Hermes Agent — Open-Source AI Agent with Memory, Skills, and Cron
The open-source AI agent from Nous Research with persistent memory, reusable skills, tools, cron jobs, GitHub workflows, and multi-platform messaging.
NANDA - Architecting the Internet of Agents
NANDA Protocol - A foundational layer for a new kind of internet—an Internet of Agents
ATProto as Agent Identity Infrastructure: A Case Study for NIST's Concept Paper — Filae
How ATProto addresses NIST's four pillars of AI agent identity — identification, authorization, delegation, and logging — with concrete examples from deployed infrastructure.

Alex Albert on Twitter / X
We just published a near-term development roadmap for the model context protocol (MCP)Some highlights:- Remote support (and auth!)- Reference implementations- Better package management- Agent support pic.twitter.com/SflJi1RapH— Alex Albert (@alexalbert__) January 2, 2025
Notion’s hosted MCP server: an inside look
Earlier this year, we got requests for a Notion MCP server that would let AI agents work directly with Notion workspaces. Here’s how we built it, from our initial open-source experiment to today’s hosted solution with custom tools designed specifically for AI workflows.

Tiles: Own your AI with local models and open protocols
Tiles: Own your AI with local models and open protocols is a Lightning Talk proposal for PuneFOSS 4.0. As AI becomes central to how we work and communicate, I believe we’re seeing a new form of technological feudalism, where a handful of platforms [...]

Supermemory
The memory layer for AI agents. Context engineering platform powering enterprise APIs, developer plugins, and a personal app that remembers everything.

Piecing together the Agent puzzle: MCP, authentication & authorization, and Durable Objects free tier
Cloudflare delivers the toolkit for AI agents with new Agents SDK support for MCP (Model Context Protocol) clients, authentication/authorization/hibernation for MCP servers, and Durable Objects free tier.

Matrix and Element: a case study of funding an open protocol for real time chat
Matrix is a distributed comms protocol for real-time chat that looks like it is taking off.
elkimek/honcho-self-hosted
Self-host Honcho memory layer for Hermes Agent — OpenRouter + Venice, no code changes
Monitor | Parallel | Parallel Web Systems | Infrastructure for intelligence on the web
Monitor API for AI agents.

AIW
Advancing protocols for how agents connect to each other, people, organizations, services, and things in the agentic web.