AGNTCon + MCPCon Japan 2026

A working agent ends up talking to a lot of things: a handful of MCP servers, two or three LLM providers, maybe another agent. Each one is a separate integration you wired in yourself, with its own auth and its own logging, or its own lack of it. Nothing sees all of it at once.

agentgateway is trying to be the thing that does. It's an open-source Rust proxy, an Agentic AI Foundation project as of this year, that sits in front of MCP, LLM, and A2A traffic together. The talk is mostly the gateway running on screen.

Four separate MCP servers go behind one endpoint and show up to the agent as a single list of tools. Claude Code connects to that one address and never finds out the tools live in four different places. One short rule, and a tool you don't want exposed stops showing up at all: not blocked, just never offered. Point the model traffic through the same gateway and a provider can drop mid-demo without the agent noticing, the whole thing readable as one trace.

Underneath the protocols, the idea is simple: an agent reaching into the world should go through one door someone is watching, not a hundred that nobody is. Building that door is what the talk is about.

The next leap in agent engineering is not bigger models. It's reusable skills.

Today, many agents repeatedly spend tokens rediscovering the same workflow every time a task appears. Whether it's code reviews, incident analysis, documentation generation, or research tasks, the agent often re-plans work it has already solved before.

This talk explores how agent skills are emerging as reusable workflow primitives that package expertise, decision-making patterns, and execution steps into portable capabilities. Instead of relying on increasingly large prompts, teams can teach agents repeatable workflows once and reuse them across tasks, products, and environments.


Key Takeaways

- Why prompts don't scale for repetitive work
- Skills as reusable workflow contracts
- Reducing token consumption through workflow reuse
- How skills and MCP work together
- Building self-improving agent systems

Most agent memory is a chat log with extra steps. Dump turns into a vector store, retrieve the top-k by cosine similarity, and hope the right context shows up. It usually doesn't, and the agent pays for it three turns later.

agentmemory MCP Server began as a fix for that. It combines BM25, dense vector search, and a knowledge graph, fuses them with reciprocal rank fusion, and ages stored memories on an Ebbinghaus forgetting curve so old context decays instead of drowning new signal. On LongMemEval-S it reaches 95.2% recall
at 5. The repo trended on GitHub, ranked on Product Hunt, got picked up by AlphaSignal, and was recognized by the Agentic AI Foundation, none of it paid for.

This talk covers how it was built and where the easy version breaks. Single-method retrieval looks fine in a demo and falls apart on long histories. I'll show why each method earns its place, how the pieces compose with one engine an agent can query over MCP, and which design decisions held up once real workloads hit them.

You'll leave with a memory model that beats top-k vector search and a clear picture of how to expose it to agents through MCP.

AI coding assistants are becoming part of everyday development, but many enterprises cannot send source code, internal APIs, or project context to external services. They need the productivity of coding agents while keeping models, repositories, prompts, and actions under their control.

In this session, we’ll show how to build an open-source, Claude Code-like assistant using local or privately hosted LLMs, Models as a Service, OpenCode, and AI guardrails. Developers will be able to explore a codebase, generate changes, review explanations, and trigger controlled actions without exposing sensitive data.

We’ll also cover the guardrails needed for real use: secrets protection, data leakage checks, unsafe command blocking, insecure code detection, and policy-based action control.

You’ll leave with a practical blueprint for building a private, secure coding assistant that improves developer productivity without compromising trust, privacy, or compliance.

Coding-agent harnesses such as Claude Code, Codex, and OpenCode are widely used as general-purpose agent platforms, customized with Skills and Tools and run inside sandboxes. But these agents are stateless by design: when a session ends or a sandbox is torn down, context and artifacts disappear. Running them in production for many users over months turns memory and artifact management into hard problems.

This session shares how we run multiple harness-based agents in sandboxes, and introduces two open-source tools we built to externalize agent state. mem9 (github.com/mem9-ai/mem9) records sessions through harness hooks and, at the next session, runs hybrid retrieval over past sessions from the user's instruction, injecting only relevant history—persisting sessions while compressing context and cutting token usage. drive9 (github.com/mem9-ai/drive9) is a cloud filesystem FUSE-mounted into each sandbox, persisting artifacts beyond sandbox lifetimes, auto-attaching metadata, and enabling semantic search over outputs.

Attendees will leave with a vendor-neutral, open-source architecture for agent memory and storage that works across any harness, plus lessons from real operation.