DEV Community: ura-tools

Your AI Agent Forgets Everything Between Sessions. I Fixed That.

ura-tools — Sun, 29 Mar 2026 23:29:57 +0000

Every time you start a new session with Claude Code, Cursor, or any AI coding agent, it starts from scratch. It does not remember:

Who you are or what you prefer
What decisions were made yesterday
What corrections you already gave it
Where external resources live

I built memorybank to fix this.

What is memorybank?

An MCP server that gives any AI agent persistent, cross-session memory. Zero dependencies, file-based, works with Claude Code, Cursor, Windsurf, and any MCP-compatible tool.

npx @ura-dev/memorybank --help

8 MCP Tools

Tool	What it does
`memory_store`	Save a memory (user, project, feedback, reference, custom)
`memory_recall`	Retrieve most relevant memories for a query
`memory_list`	List all memories, filter by type or tag
`memory_get`	Get a specific memory by ID
`memory_update`	Update an existing memory
`memory_delete`	Delete a memory
`memory_search`	Full-text search across all memories
`memory_stats`	Counts, types, storage size

How it works

Your agent encounters something worth remembering
It calls memory_store with a type, name, and content
memorybank saves it as a markdown file with YAML frontmatter
Next session, the agent calls memory_recall to load relevant context
The agent now knows what happened before

Memories are stored locally in ~/.memorybank/, organized by namespace (one per project). No cloud, no database, no API keys.

Setup in 30 seconds

Add to your Claude Code config (~/.claude/settings.json):

{
  "mcpServers": {
    "memorybank": {
      "command": "npx",
      "args": ["-y", "@ura-dev/memorybank", "memorybank-mcp"]
    }
  }
}

Or Cursor (.cursor/mcp.json):

{
  "mcpServers": {
    "memorybank": {
      "command": "npx",
      "args": ["-y", "@ura-dev/memorybank", "memorybank-mcp"]
    }
  }
}

That is it. Your agent now has persistent memory.

Five memory types

user — About you: role, preferences, expertise level
project — About the work: goals, architecture decisions, deadlines
feedback — Corrections you gave: what to avoid, what worked
reference — External pointers: URLs, docs locations, API endpoints
custom — Anything else

Why not just use CLAUDE.md?

CLAUDE.md is great for static project instructions. memorybank is for dynamic knowledge that evolves during work:

User corrections that should persist
Architecture decisions made mid-project
References discovered during research
Project status that changes daily

memorybank complements CLAUDE.md. One for rules, the other for learned knowledge.

CLI too

memorybank store user team-lead "User is the team lead for backend services"
memorybank search "TypeScript preferences"
memorybank list --type=feedback
memorybank store project api-rewrite "Migrating REST to GraphQL" --namespace=myproject

Also: agentrace

If you want to see what your AI agent is doing (not just what it remembers), check out agentrace. Structured observability for AI agents. Same philosophy: MCP server, zero deps, file-based.

Links:

npm: @ura-dev/memorybank
GitHub: ura-tools/memorybank
Landing page: ura-tools.github.io/memorybank

Built with zero dependencies. MIT licensed. Works today.

I built an observability tool for AI agents — trace what they do and why

ura-tools — Sat, 28 Mar 2026 22:14:34 +0000

Also from ura: changelogai — AI-powered changelog generation from any git repo

I built a changelog generator that works on any repo — no conventional commits needed

ura-tools — Sat, 28 Mar 2026 19:43:58 +0000

Every changelog tool I tried had the same problem: they only work if your team writes perfect conventional commits. Most teams don't.

So I built changelogai — a CLI that generates professional changelogs from any git history.

What makes it different

It works on messy repos. The parser detects commit types from 24 keyword patterns, not just type(scope): prefixes. Commits like "fixed the auth bug" or "Updated dashboard layout" get classified correctly.

Clickable commit links. Auto-detects your GitHub/GitLab remote and generates linked hashes. No config needed.

AI mode (optional). Pass --ai and it rewrites technical commit messages into user-facing release notes using Claude. Costs ~$0.001 per changelog.

MCP server included. Other AI agents can call changelogai_generate and changelogai_version_bump as tools. Add it to your Claude Code or Cursor config in one line.

Quick start

npm install -g @ura-dev/changelogai

# Grouped changelog since last tag
changelogai --group

# AI-enhanced
changelogai --ai --group --output CHANGELOG.md

# JSON for CI/CD
changelogai --format json

# Suggest next version
changelogai --version-bump

Use as a library

const { generateChangelog, getGitLog, getLatestTag } = require('changelogai');

const commits = getGitLog('.', 'v1.0.0', 'HEAD', 500);
const md = await generateChangelog(commits, {
  format: 'markdown',
  group: true
});

MCP server (for AI agents)

{
  "mcpServers": {
    "changelogai": { "command": "changelogai-mcp" }
  }
}

Any MCP client (Claude Code, Cursor, Dapr Agents) can now generate changelogs autonomously.

Sample output

## [v1.1.0](https://github.com/you/repo/compare/v1.0.0...v1.1.0) — 2026-03-28

### Features
- Add dark mode toggle (abc123)
- Support custom themes (def456)

### Bug Fixes
- Fix login redirect on mobile (789abc)

The boring details

Zero dependencies — pure Node.js
Works with Node 18+
Markdown, JSON, or plain text output
Prepend mode for existing CHANGELOG.md files
MIT license

Built by ura — developer tools that go deeper.

Also from ura: agentrace — structured observability for AI agents