PathruleAIコーディングの
現場ノート。
AIコーディングアシスタント、チームのメモリ、コンテキストエンジニアリング、トークンコスト、セキュリティについての実践ノート。エージェントのワークフローを一貫させるための、実用的なパターンを紹介します。
- エンジニアリング
Running the model locally was the easy part英語のみ
Pathrule runs a 4B model on your machine to understand your team's knowledge. Getting it to run was a weekend. Getting its output safe to act on took fifty numbered experiments, a frozen evaluation with veto power, and a deterministic compiler that has the final say.
- エンジニアリング
Introducing Pathrule Intelligence英語のみ
A local intelligence layer that learns how your workspace works, how you work, and carries that knowledge across coding agents. Why memory alone is not enough, why retrieval alone is not enough, and what we built instead.
- エンジニアリング
Persistent Memory for AI Coding Agents: Six Decisions英語のみ
Persistent memory for a coding agent is not one product choice. It is six: instruction file or layer, what a memory attaches to, how it is found, where it lives, when it arrives, and how you measure whether any of it worked.
- エンジニアリング
Memory MCP Servers for AI Coding Agents: What Each One Stores英語のみ
The protocol's reference server, Mem0, Zep through Graphiti, Supermemory, Basic Memory and what happened to OpenMemory. What each one calls a memory, where it runs, how to wire it into Claude Code, Codex, Cursor and OpenCode, and the one thing MCP does not settle.
- エンジニアリング
AI Agent Memory: What It Is and How It Works英語のみ
AI agent memory is the knowledge an agent can use in a session it did not learn it in. Here is the write path, the read path, the four kinds of memory and the blind spot every retrieval-only system has.
- エンジニアリング
Best AI Agent Memory Tools for Coding in 2026英語のみ
Most memory tools are not competing with each other. They store different units for different jobs, and picking the wrong category gives you a tool that works perfectly and still does not help.
- エンジニアリング
How to Give Codex Persistent Project Memory英語のみ
Codex supports local memories as well as AGENTS.md. Here is what persists, what teams can share, and where a cross-agent knowledge layer helps.
- エンジニアリング
Vector RAG vs Path-Scoped Context for AI Coding英語のみ
RAG is the right tool for a corpus you search. A codebase is not a corpus you search; it is a tree you are standing somewhere in, and the position you are standing in already tells you what matters.
- エンジニアリング
How Do You Know the Fix Actually Worked?英語のみ
Merging is a claim, not evidence. The runtime that reported the problem is the only thing that can say whether it stopped happening, and the honest answer has more than two states.
- エンジニアリング
Pathrule vs Supermemory: A Memory API Answers When Asked英語のみ
Supermemory is a good memory API and Pathrule is not competing to be one. The difference is delivery: retrieval waits for an agent to think of asking, and path-scoped context arrives before the first tool call.
- エンジニアリング
What a Pathrule Pattern Is, and Why It Is Not a Skill英語のみ
A pattern is not a single skill or rule. It is a small, opinionated bundle of memories, rules, and skills for one topic, each piece pre-scoped to the path it belongs to. Here is what that buys you and why the unit is bigger than a file.
- セキュリティ
Secure-by-Default Scaffolding for AI Coding Agents英語のみ
A coding agent writes the first draft now, and the easy default is almost always the insecure one. Here is how a security pattern puts the secure default in front of the agent before it writes a single line.
- エンジニアリング
One Import Token, Scoped Across Your Tree英語のみ
Sharing conventions usually means pasting a long file at the root. A pattern is imported with one token that expands into scoped pieces, each placed at the path it applies to. Here is why that difference matters.
- エンジニアリング
Why a Context Layer Should Have an Open Core英語のみ
A local knowledge store, readable integrations and an honest source boundary. What Pathrule keeps open, and where the proprietary Intelligence Engine and Cloud begin.
- セキュリティ
Where Your AI Context Layer Should Be Allowed to Run英語のみ
For regulated and security-reviewed teams, the hard question about a context layer is not only what it stores. It is where it runs and who controls the data. Here is how to think about that line.
- エンジニアリング
Context Engineering vs Prompt Engineering: What Actually Changed英語のみ
Prompt engineering tunes the question. Context engineering decides what the model sees before it answers. Here is the difference, why it matters for coding agents, and how teams put it into practice.
- エンジニアリング
What Is the Model Context Protocol (MCP) and Why Teams Use It英語のみ
MCP is the open standard that lets AI assistants talk to external tools and data sources. Here is what it is, how clients and servers fit together, and where a team context layer plugs in.
- エンジニアリング
Managing AI Coding Context in a Monorepo英語のみ
A monorepo holds many projects under one root, which is exactly where a single AI instruction file breaks. Here is how to scope context per package so the assistant gets the right rules for the folder it is in.
- エンジニアリング
GitHub Copilot Custom Instructions: What They Cover and Where They Stop英語のみ
What Copilot’s repository and path-specific instructions handle, and where a shared knowledge layer adds versioned authoring and cross-agent delivery.
- エンジニアリング
Why AI Coding Assistants Forget Your Codebase Between Sessions英語のみ
AI coding assistants are stateless. Each new session starts from zero. Here is what actually persists, what does not, and how teams keep context across sessions.
- エンジニアリング
How to Share Claude Code Memory Across a Team英語のみ
Claude Code stores memory per project and per user by default. Here is how teams actually share that knowledge: what CLAUDE.md covers, where it stops, and what fills the gap.
- セキュリティ
Claude Code Hooks vs CLAUDE.md: Where Enforcement Lives英語のみ
CLAUDE.md is advisory. Hooks are deterministic. Here is the practical split, why teams should use both, and where a path-scoped knowledge layer fits.
- エンジニアリング
Why Claude Code Skills Do Not Activate英語のみ
Skills look like they install cleanly and then quietly do nothing. Here is why SKILL.md often fails to activate and what a working delivery path looks like.
- エンジニアリング
Why Cursor Rules Get Silently Ignored英語のみ
Cursor rules look loaded and then quietly do nothing. Here is what breaks, what to check first, and how a path-scoped layer keeps rules visible at the moment they matter.
- エンジニアリング
Why Claude Code Ignores CLAUDE.md英語のみ
CLAUDE.md is guidance, not enforcement. Learn why AI coding assistants skip long instruction files and how hooks plus path-scoped rules close the gap.
- エンジニアリング
AGENTS.md vs Pathrule: When Each One Makes Sense英語のみ
AGENTS.md gives AI coding agents one predictable file. Pathrule keeps it short by routing the right team knowledge slice per session.
- エンジニアリング
Context Is a Team Interface, Not a Prompt File英語のみ
A practical argument for treating AI context as shared team infrastructure, not another prompt file to maintain by hand.
- セキュリティ
Why AI Coding Assistants Need Scoped Rules英語のみ
Learn why AI coding rules work best when they are attached to the files and folders where they apply, reducing noise while preserving precise constraints.
- トークンコスト
The Cost of Rediscovering Your Own Codebase英語のみ
AI coding sessions often waste time and tokens rebuilding knowledge the team already has. Scoped context changes the first move.
- エンジニアリング
From Tribal Knowledge to Reviewable Memory英語のみ
Learn how teams turn scattered project knowledge into visible, scoped and reviewable memory that AI coding agents can reuse across sessions and tools.
- セキュリティ
A Practical Model for Safer AI Coding Workflows英語のみ
Build safer AI coding workflows with explicit boundaries, scoped rules, reviewable memory, source-code privacy and clear human approval points for teams.
- エンジニアリング
Why Global AI Instructions Break Down at Team Scale英語のみ
Learn why global AI instruction files lose signal as teams add more paths and exceptions, and how scoped context keeps local constraints precise for teams.
- エンジニアリング
Just-in-Time Context for AI Coding Agents英語のみ
AI coding agents work better when relevant team knowledge arrives before the first useful action, not after a search loop.
- エンジニアリング
Memory, Rules, and Skills: Three Kinds of Team Knowledge英語のみ
Pathrule separates team knowledge into memories, rules, and skills so AI coding assistants receive the right kind of context.
- セキュリティ
How Stale Team Knowledge Creates AI Mistakes英語のみ
Learn how stale team knowledge creates repeat AI coding mistakes, then use review, repair and retirement workflows to keep shared context trustworthy.
- エンジニアリング
One Knowledge Layer Across AI Coding Agents英語のみ
Teams should not rewrite the same guidance for every AI coding agent. Pathrule gives shared product knowledge one home across supported coding agents.
- エンジニアリング
Design Rules Should Travel With the Work, Not the Tool英語のみ
Keep AI-generated interfaces consistent by attaching product and design rules to the work itself, so the same constraints follow every coding tool you use.
- エンジニアリング
Team Memory Should Not Change When AI Tools Do英語のみ
Keep team memory stable while engineers switch AI coding tools, so shared decisions and conventions remain portable across agents, sessions and editors.
- セキュリティ
Audit Trails for AI Coding: What Changed, Who, and Why英語のみ
An audit trail for AI coding shows who changed a rule, memory, or skill, when, and why. Here is why the context your assistants act on deserves the same review and history as code.
- セキュリティ
Pathrule Stores Team Knowledge, Not Source Code英語のみ
Pathrule is built around a narrow privacy boundary: store the knowledge teams choose to write down, not their repository source.
- エンジニアリング
Small Teams Should Build a Context Layer Early英語のみ
Small teams feel AI context problems early. Capturing knowledge before the team grows keeps onboarding, review, and AI work calmer.
- トークンコスト
More Context Is Not Always Better for AI Assistants英語のみ
AI assistants do not need every fact at once. They need the right context, at the right depth, for the task in front of them.
- 導入事例
A Real History Test: 30x-50x Lower Context Cost英語のみ
A real Pathrule history query showed how scoped prior work can avoid broad local search and reduce tool-output token cost.