Get This Tool
Weave
Pricing
- Model
- Free
Summary
Most personal AI assistants forget everything the moment you close the tab — your open commitments, the email you still owe a reply, the calendar conflict you noticed Monday and ignored by Wednesday. Weave is a local-first macOS agent that builds a persistent private memory from what you actually see and do, then acts on it.
Weave watches your screen via OCR, pulls Gmail and Calendar data, and stores all of it locally in SQLite — so the context it works from is yours and stays on your machine. The morning brief surfaces to-dos, overdue commitments, and response debt before your day starts. When you need action rather than summary, a browser agent plans and executes steps toward a goal, and a separate macOS agent drives native apps by voice or intent. The ceiling appears early: this is a solo developer project at 72 commits with no hosted fallback, no API, and no documented path for teams or shared memory.
Bottom line: Pick Weave if you are a macOS power user who wants a local memory layer that actually tracks your commitments and can run browser tasks on your behalf — but plan to maintain it yourself the first time an Electron dependency breaks on an OS update.
Community Performance Report Card
No community ratings yet. Be the first to rate this tool!
Community Benchmarks Community
Sign in to submit a benchmarkNo community benchmarks yet. Be the first to share a real-world data point.
Pros
Sign in to edit- All captured data — screen OCR, email, calendar, contacts — is stored locally in SQLite, so you are not trading your personal context for a vendor's data pipeline.
- The browser agent accepts a goal and executes the steps to reach it without per-step instruction, so repetitive research or form-filling tasks run without you staying on the loop.
- Commitment and response-debt tracking surfaces what you said you would do and have not done yet, which means the morning brief catches the dropped thread before the other person follows up.
- Native macOS app control by voice or stated goal means automation extends beyond the browser to the full desktop environment, so you are not limited to web-only task execution.
- Fully free with no paid-only features and self-hosted by design, so there is no pricing gate on any capability and no subscription to cancel when the project goes dormant.
Cons
Sign in to edit- The setup requires cloning the repo and running npm dev commands — there is no packaged installer documented beyond electron-builder config. The first OS update that breaks an Electron or native dependency lands on you to debug, with no issue history and no maintainer response SLA.
- There is no API surface. Any workflow that needs Weave's memory or agents accessible from another tool, script, or service hits a dead end — teams who need that integration path switch to a self-hosted open-source alternative like Mem0 or a custom LangChain memory layer.
- The macOS agent and browser agent have no documented multi-user or profile separation. A household or small team that wants shared context or separate memory spaces finds no path forward in the current architecture — this is a single-user, single-machine design.
Community Reviews
Sign in to write a reviewNo reviews yet. Be the first to share your experience.
About
- Platforms
- macOS
- API Available
- No
- Self-Hosted
- Yes
- Last Updated
- 2026-06-18T04:44:05.185Z
Best For
Who it's for
- macOS users seeking local personal memory
- Relationship and productivity tracking
- Agentic browser and desktop automation
- Privacy-focused local AI assistance
What it does well
- Daily morning briefs with to-dos and notifications
- Chat over personal memory and calendar/email data
- Browser task automation with goal-based planning
- Native macOS app control by voice or goal
- Commitment and response-debt tracking
Integrations
Discussion Community
Sign in to commentNo discussion yet. Sign in to start the conversation.
Spotted incorrect or missing data? Join our community of contributors.
Sign Up to ContributeCommunity Notes & Tips Community
Sign in to contributeBe the first to contribute. General notes, observations, gotchas, and tips from people who use this tool day-to-day.
Frequently Asked Questions
- Is Weave free?
- Yes — Weave is fully free to use. There is no paid tier.
- Is Weave open source?
- Yes. Weave is open source.
- Can I self-host Weave?
- Yes. Weave supports self-hosting on your own infrastructure.
- What platforms does Weave support?
- Weave is available on: macOS.
Hours Saved & ROI Stories Community
Sign in to contributeBe the first to contribute. Concrete time/cost savings, with context. e.g. "Cut my code review backlog from 4h to 45m per week."
Curated lists that include this category
Weave describes itself as a ‘local-first relationship life intelligence engine’ for macOS. The core loop is: screen OCR captures what you see across apps, Gmail and Calendar integrations feed structured data, contacts fill in the relationship graph, and all of it lands in a local SQLite database. On top of that memory, Weave runs a daily morning brief — a digest of to-dos, notifications, and pending commitments — and answers natural-language questions against your own stored context.
The differentiating feature is the dual-agent layer. The browser agent accepts a goal, then plans and executes steps to reach it — navigating pages, filling forms, retrieving information — without you micromanaging each action. The macOS agent goes further, driving native desktop apps by voice or stated intent. Both agents run locally; cloud calls occur only for LLM inference or search features you configure yourself, so the decision about what leaves your machine is yours.
Where Weave fits cleanly: a solo macOS user who wants persistent personal context, commitment tracking across email and calendar, and occasional goal-driven automation without paying for a SaaS subscription. Where it breaks: the project carries no license in the documented file list, has a single-digit star count, no API surface, and no multi-user or shared-memory path. Teams, non-macOS users, and anyone who needs a stable integration contract rather than a local npm dev environment will hit a wall immediately. The vendor states no commercial tiers exist — this is free and open-source, which also means no support queue and no SLA.
Setup follows standard Electron app conventions: npm install and dev commands, with an electron-builder config for packaging. The OCR pipeline and native macOS agent live in separate directories alongside a Chrome extension for browser automation. Anyone evaluating this should audit the dependency chain before treating it as a production daily driver — the architecture is sound on paper, but community reports on stability at this maturity level are absent.