Meridian is an open-source AI work journal that runs entirely on your device. It writes your work up in plain English as the day goes, so by the end of the day you have a summary of everything you did. Meridian automatically drafts your updates for your project management tools like Jira, ready to post once you approve them. Do the work. Let the remembering take care of itself. No cloud, no account. MIT-licensed, free.
Loading comments…
Project Info
Product Keywords
Meridian is an open-source AI work journal that runs entirely on your device. It quietly observes your work throughout the day—the apps you use, the tasks you touch, the time each one takes—and writes it all up in plain English. By the time you finish, you have a complete, searchable summary of everything you did, plus auto-drafted status updates ready for your project management tools. No cloud, no account, no setup ceremony. Just do the work, and let the remembering take care of itself.
Meridian captures every task, every switch, and every hour of your day. It shows the real shape of your work—focused time, tasks touched, things shipped—broken down by activity like coding, debugging, reviewing, and meetings. You get a clear picture of where your day actually went, without lifting a finger.
Beyond the surface, Meridian records not just what got done but why the day went the way it did. It tracks which estimates held and which didn't, and explains the reasoning—like noting that a task scoped at 2 hours took 2h 40m, and that overrun pushed the next task off the day.
Meridian drafts a clear update from your actual work, matched to the right task in your PM tool. You review it, approve it, and post it with one click. Zero typing required. It supports Jira, GitHub Projects, Linear, Azure DevOps, and Trello—with connections that are read-only until you approve a log.
Every day lives in your own searchable journal. Worklogs, decisions, proof of what happened—all available whenever you need them. It's a private, complete record of your time and your choices.
Privacy isn't a feature. It's the foundation.
Meridian is MIT-licensed and free, with every line of code auditable. Capture, analysis, and journaling all run on-device—nothing is uploaded, nothing phones home. The only thing that ever leaves your device is a worklog you explicitly approved, sent directly to your PM tool. You can exclude any app, pause anytime from the menu bar, and delete anything. Even with no integrations connected, Meridian stands alone as a private, searchable record of your work.
You're tired of manual timesheets, hate the idea of your work data sitting on someone else's server, or simply want to end each day with a clear, honest summary of what you accomplished. Meridian is free, open source, and runs entirely on your device—so there's no risk in trying it. If you want to see it in action, you can book a 20-minute call and watch it work on real tasks.
Other tools you might consider
Octopoda is an open source infrastructure layer that gives AI agents persistent memory, automatic loop detection, and full observability. Agents forget everything between sessions. Octopoda fixes that with a remember/recall API that survives restarts, crashes, and deployments. The loop detection system monitors 5 signals to catch agents stuck repeating themselves before they burn your API budget, with real-time cost estimation showing exactly how much each loop wastes. A built-in dashboard shows every agent's health score, memory explorer with version history, audit trail logging every decision with reasoning, and a timeline replay that lets you scrub through everything your agent did step by step. Works with LangChain, CrewAI, AutoGen, and OpenAI Agents SDK with one-line integrations. Runs locally with SQLite or connects to cloud with one environment variable. Free tier, MIT licensed. 177 signups, 120 GitHub stars, zero marketing spend.
You're running more coding agents than ever, but you can't keep up with them. That's where AgentPeek comes in. It pulls every session up into your Mac notch, live. Glance up, approve a prompt, watch token usage and manage the entire flow without pausing your YouTube video. All local, all yours.
AI agents can ship quickly, but without the right product context, they're often flying blind. Brief gives product teams a living source of truth that captures decisions, preserves product intent, and serves relevant context to humans and agents through chat, Slack, CLI, and MCP. It keeps strategy, decisions, and execution connected from vision to impact.
Harness Starter Kit helps teams turn fragile AI coding prompts into durable repository rules: AGENTS.md, drift checks, failure memory, adoption reports, and stack profiles for safer agent collaboration.
Maker
pixel_pilot
Compare with
Alternatives
Loading comments…
