AGNTCon + MCPCon Japan 2026

Autonomous assistants are easy to demo and hard to make reliable. The problem is usually not tool access. It is memory.

Most assistant architectures still treat memory as a chat log plus vector retrieval. That is fine for document question answering, but it breaks down when the assistant must connect conversations, people, tools, and decisions across multiple tool iterations. For an AI engineer, a single request can depend on a Slack thread, a GitHub PR, a failed CI run, a calendar event, and prior operating preferences or constraints. These are not isolated pieces of context. They form a connected state that changes as work progresses and context grows.

In this talk, I’ll show why knowledge graphs, context graphs, and GraphRAG provide a better foundation for OpenClaw-style assistants. Knowledge graphs capture durable entities and relationships. Context graphs capture the operational layer assistants usually lose, including actions, decision traces, provenance, and recency. GraphRAG turns that structure into task-time context by combining graph traversal, semantic retrieval, and tool use.

Attendees will leave with practical patterns for schema design, retrieval routing, and evaluation, plus a concrete blueprint for assistants that remember more than the last prompt and retrieve more than the nearest chunk.

___________________________
Presentation Language: English

Captioning will be available for attendees in 50+ languages through Wordly. See instructions in each room to utilize captioning.

From a green software perspective, waste in agentic AI comes not only from model choice, but also from workflow design. Agent workflows combine planning, retrieval, retries, memory, tools, and model calls. Poor controls can lead to large models for simple tasks, long histories, repeated retrieval, or needless tool calls, increasing compute, cost, and latency.

This talk presents a design-review approach for reducing unnecessary computation in agent workflows. As a case study, it uses Lean Agentic AI (https://github.com/navveenb/lean-agentic-ai) as an open-source workflow example. For each workflow step, it asks: Is an LLM needed? Is the model appropriate? Is context bounded? Could code, rules, or a smaller model replace a large-model call?

The goal is not precise carbon accounting. Instead, it identifies avoidable inference, oversized context, and needless tool calls before estimating CO2 emissions.

Takeaways:
* See how agent workflow design affects compute, cost, and latency.
* Understand how reducing unnecessary computation supports green software goals.
* Ask simple review questions to reduce unnecessary LLM calls, retrieval, memory, and tool use.

___________________________
Presentation Language: English
Captioning will be available for attendees in 50+ languages through Wordly. See instructions in each room to utilize captioning.

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.

___________________________
Presentation Language: English

AI coding agents are useful in isolated demos; the hard problem is making them controlled enough to ship production code. At Delphi, we built an agentic software factory that turns product specs and engineering tickets into scoped pull requests, then routes those PRs through reviewer agents, CI, browser verification, and merge gates.

This session breaks down the operating system around the agents: how we package repo context, encode architectural rules, isolate attempts in worktrees, make agents cite source-of-truth patterns, prevent drift from legacy code, and decide what should stay human-controlled. I will also cover failure modes we hit in production: stale context, over-broad diffs, flaky tests, review spam, false confidence, and agents copying the wrong pattern.

Attendees will leave with a practical blueprint for moving from “agent writes code” to a controlled delivery pipeline for agent-generated software.

___________________________
Presentation Language: English

Captioning will be available for attendees in 50+ languages through Wordly. See instructions in each room to utilize captioning.

Technical debt lives in code. Cognitive debt lives in your head. Intent debt, Addy Osmani's term for the goals, constraints, and rationale behind a decision that never got written down, lives nowhere. It's the one debt agents can't pay down: an agent drafting a spec fills the gap with a confident guess, and the guess is usually wrong.

This talk covers building context graphs that capture the why: connecting decisions to the document threads and ticket discussions where humans actually made them, then exposing that structure to agents alongside code and data. I'll draw on an open-source toolkit that bootstraps context graphs from existing work artifacts (workspace threads, ticket histories) and the modeling questions that turned out hard: what separates a decision from a discussion, and when capture should run as a background process versus an explicit act.

Vendors now race to pitch "context layers for agents." I'll argue the differentiator isn't collection but connection: rationale linked to the entities, people, and prior choices it affects: queryable, not just retrievable.

You'll leave with patterns for making the why available to every agent that touches your work.

___________________________
Presentation Language: English

Captioning will be available for attendees in 50+ languages through Wordly. See instructions in each room to utilize captioning.