Dear Agent
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Dear Agent Remember that I started my new job today, feeling excited."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Dear Agent
Your AI agent keeps your diary for you. You never open an app or write a word.
You already talk to an AI agent all day. Dear Agent lets that agent quietly keep your personal life journal — filing what you tell it, the photos you send, and the voice notes you record, neatly by date. No app to open. No blank page to face. No habit to build. You just live your life and mention what matters; your agent does the writing.
It is a single, local-first MCP server plus a skill, so it drops into any agent that speaks MCP: Claude Code, Claude Desktop, Cursor, OpenClaw, and more.
Why it is different
You do not write it. Your agent does. Every other journal — Day One, Obsidian, Notion, a paper notebook — needs you to open it and type. Dear Agent flips that: you talk, it records.
Cross-agent. One diary, readable and writable by whatever agent you use.
Text, photos, and voice. Send a picture or a voice note and it is filed under that day.
Local-first and yours. Plain markdown on your own disk. No account, no cloud, no lock-in. Delete the folder and it is gone.
It remembers with you. "On this day" resurfaces past entries; a weekly digest lets your agent write you a short reflection.
Related MCP server: MCP Session Memory Bridge
Install
npm install -g dear-agentOr run it straight from npx (no install):
npx dear-agentClaude Code / Claude Desktop
claude mcp add dear-agent -- npx -y dear-agentOr add to your MCP config:
{
"mcpServers": {
"dear-agent": {
"command": "npx",
"args": ["-y", "dear-agent"]
}
}
}Cursor / OpenClaw / other MCP clients
Point the client at the dear-agent command (stdio transport). Set DEAR_AGENT_DIR if you want the diary somewhere other than ~/.dear-agent.
Then drop SKILL.md into your agent's skills so it knows to keep your diary proactively.
How you use it
You never call tools yourself. You just talk to your agent:
"Remember that I closed the apartment lease today, felt huge relief." "Save this photo for today — first dinner in the new place." (send the photo) "What was I doing a year ago today?" "Give me a recap of this week."
Your agent calls the right tool and keeps the diary current.
It remembers you, and it talks back
Dear Agent is not just storage. Two capabilities turn it into a living memory of your life:
recall— your agent can ask the diary "what do you know about this person — their people, patterns, open commitments?" and get a synthesized portrait. Your agent finally remembers your life, so every conversation is grounded in who you actually are.reflect— a proactive loop that surfaces patterns, progress, open loops, and on this day memories, so your diary reflects your life back to you instead of sitting in a folder.
Obsidian stores your notes. Dear Agent remembers your life and talks back. And because it never leaves your machine, it's the one place you can be completely honest.
Works with any agent, harness, or interface
Interface | How |
MCP tools | 11 tools (below) over stdio. |
MCP prompts |
|
MCP resources |
|
Skill |
|
CLI |
|
CLI examples:
dear-agent add "Closed the interview, felt good." --mood hopeful --tags job,win
dear-agent recall Sarah
dear-agent reflect week
dear-agent on-this-dayTools
Tool | What it does |
| Save a text moment (optional mood, tags) for a day. |
| Save a photo for a day (local path or base64), with a caption. |
| Save a voice note for a day, with an optional transcript. |
| Read one day's full entry. |
| Read entries between two dates. |
| Find days matching a word or phrase. |
| What the diary knows about a person/topic, or a whole-life profile digest. |
| Patterns, progress, open loops, and on-this-day, for a proactive check-in. |
| Resurface this same calendar date from past years. |
| Pull the last 7 days for a reflection. |
| List every day on record. |
Dates accept today, yesterday, or YYYY-MM-DD.
Where your diary lives
~/.dear-agent/
entries/
2026-06-29.md
media/
2026-06-29/
first-dinner.jpg
morning-thought.oggSet DEAR_AGENT_DIR to choose a different location.
Contributing
Issues and pull requests are welcome. Dear Agent is intentionally small and dependency-light — keep changes focused, keep storage as plain files the user owns, and keep everything local-first and private. See ROADMAP.md for where it is headed.
License
MIT © BitmapAsset. Free for anyone, anywhere, in any agent.
Available Tools
11 toolsadd_entryA
Record a text moment in the user's diary. Capture whenever they share something worth remembering — an event, feeling, win, or decision. The user never types into an app; you keep the diary for them.
Inputs: text (required), date, mood, tags.
add_photoB
Save a photo into the user's diary for a day (local path or base64), with an optional caption.
Inputs: data, date, path, caption, +1 more.
add_voice_noteB
Save a voice note into the user's diary for a day (local path or base64), with an optional transcript.
Inputs: data, date, path, filename, +1 more.
get_dayA
Read back one day's full diary entry, including any photos and voice notes filed that day.
Inputs: date.
get_rangeA
Read diary entries between two dates (inclusive).
Inputs: end (required), start (required).
list_daysA
List every day that has a diary entry, oldest to newest.
Inputs: no named parameters.
on_this_dayB
Resurface entries from this same calendar date in past years (true anniversaries). The memory people fall in love with.
Inputs: date.
recallB
Turn the diary into living memory of the person. With about, returns everything the diary knows about a person/place/topic across time. Without it, returns a profile digest (recurring people, themes, mood pattern, open commitments) for you to synthesize into who this person is. This is what makes Dear Agent a memory, not just a notebook.
Inputs: about, limit.
reflectA
Get reflection material so you can proactively talk back to the user: patterns, progress, open loops, and on-this-day memories over the last week or month. Use for a daily check-in or weekly recap so the diary feels alive.
Inputs: end, period.
searchB
Search the whole diary for a word or phrase; returns matching days with snippets.
Inputs: query (required), limit.
weekly_digestB
Pull the last 7 days of entries so you can write the user a short weekly reflection.
Inputs: end.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 11 tools
Each tool has a distinct purpose: adding different types of entries, reading entries in various ways, searching, and generating reflections. No two tools have overlapping functionality.
All tool names follow a consistent verb_noun pattern with lowercase and underscores (e.g., add_entry, get_day, list_days). The naming is predictable and uniform.
11 tools is a well-scoped set for a diary/memory application, covering entry addition, retrieval, search, and insight generation without being excessive or sparse.
The tool set covers core diary operations (add, read, search, reflect) but lacks update/delete capabilities. However, the domain may be append-only, so this is a minor gap.
Maintenance
Related MCP Connectors
Markdown notes and whiteboards your AI agent can read and write.
Portable AI memory shared across models and harnesses - plain markdown you own.
Memory, reflection and safety for AI agents. Hosted or local, no vector database.
Persistent memory and knowledge management for AI agents with semantic search and 50+ tools.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceProvides tools for AI agents to manage long-term memories, daily notes, and TODO lists through a structured markdown file system. It enables context awareness by allowing agents to read, write, and search entries for persistent information storage.17 npmMIT
- FlicenseNot gradedqualityNot gradedmaintenanceProvides cross-session memory for AI agents by maintaining a rolling 24-hour event stream and searchable daily archives to prevent context loss. It enables agents to record, query, and retrieve historical events and decisions through a structured markdown-based workspace.1 npm-
- AlicenseNot gradedqualityDmaintenancePersistent activity journal for AI agents - enables logging and querying decisions, changes, errors, and observations across sessions.3 npm1MIT
- AlicenseAqualityDmaintenanceEnables AI agents to maintain a persistent, queryable memory stored as user-owned Markdown files, with dual-channel retrieval (FTS5 and optional semantic search) and an audited write pipeline.11MIT