AI context management
myAI is a self-owned, git-versioned brain for AI context management. Plug any agent — Claude, Cursor, Gemini, Codex, opencode — into your own portable memory so it boots already knowing your projects, your decisions, and where you left off. Local-first, MCP-native, and built to run autonomously.
The problem
Every frontier coding agent is a brilliant amnesiac. Out of the box it has no memory of last week's decisions, no handoff between machines, no idea what it did on your other laptop yesterday. Everyone re-invents this by hand as a pile of markdown and rituals — and pays a re-teach tax in tokens and time at the start of every single session.
myAI's thesis: this layer — context, memory, sessions, handoff, retrieval, scheduling, and a control dashboard — should be portable, user-owned, and model-agnostic. Any agent plugs in and is bootstrapped with your context at session start.
The Brain
The hardest problem in agentic work is continuity — every session traditionally starts amnesiac. The brain fixes that by treating memory the way you already treat code.
How it works
You set direction from the CLI, your phone, or Telegram. A local gateway coordinates specialist agents and an autonomous runner. The brain remembers across all of it.
What you get
Git-versioned agent memory that lives in your own repo. Sessions are commits, wrap-up is a merge, catching up is a diff. Push it, clone it, back it up like any other code — no SaaS account, no lock-in.
A returning agent gets a few-hundred-token catch-up of exactly what changed since it last looked — instead of re-reading everything. Continuity across sessions, machines, and even different models.
Thirteen core specialists (frontend, API, database, security, QA, architecture…) plus 60+ skill playbooks, auto-dispatched to the right lane in parallel — not one generalist chat window.
A scheduled runner picks tasks off a queue and works them in headless sessions overnight, behind hard safety rails: never pushes to main, never commits secrets, stops and explains after three strikes.
One local gateway serves your context to every agent over the Model Context Protocol — plus a REST API, WebSocket updates, model routing, and an audit log.
Plans, task queue, repo directory, and analytics in one operator view — with a phone- and Telegram-driveable control surface for approvals on the go.
Progress
myAI is production-grade and used every day across a fleet of real repositories. A few recent milestones:
Private vulnerability reporting wired end-to-end; hardened public surface and a documented disclosure policy.
Health/readiness probes, graceful drain, OpenTelemetry tracing, per-tenant webhook receiver, and a Helm chart for self-hosting.
Git-versioned memory becomes the source of truth every session boots from, with RAG semantic recall and a composite brain health score.
A scheduled runner works the queue overnight across a fleet of repos, driven from one morning console — coffee, review, redirect.
Deeper reading
The architecture of myAI — a git-versioned memory layer, a specialist agent fleet, an autonomous off-hours runner, and an MCP gateway that ties them together. How it works, why it's shaped this way, and where it could go.
AgentFlow turns an idea typed into a text box into a repository you can actually run — the architecture that gets from prompt to working project.
The architecture of Connect — an installable support hub where a bug report becomes an AI-triaged, human-approved, autonomously-built fix with a live public timeline. The triage→fix loop, the safety model, and how a year of plans reshaped the ambition.
FAQ
One portable brain that you own, served to every agent. Bring your own credentials, run it on your own machine, take your context anywhere.