Give your AI agent a memory of every video you own.
MnemoVi runs a small server on your own machine. Point Claude Desktop, Claude Code, Codex — any AI agent that speaks MCP — at it, and it can search, quote and jump around your entire video library. Grounded in what was actually said and shown. Nothing leaves your device.
Runs on your own Mac or PC · localhost only · no cloud
One local server. Any agent. Your videos.
MCP is the open standard that lets AI agents plug into tools. MnemoVi ships an MCP server that runs beside the app — so your agent treats your video library like a database it can query.
It lives on your machine.
The server binds to localhost only (127.0.0.1:5005). Your agent connects to it directly — no account, no upload, no relay in the middle.
Answers you can trust.
Every reply is grounded in real moments — the exact line that was spoken or the frame that was shown — each with a timecode you can open.
Works with the agent you already use.
Claude Desktop, Claude Code, Codex, Gemini CLI — anything that supports MCP tool connections. No lock-in, no new app to learn.
You stay in control.
Search and read are on. Anything with a side-effect — adding videos, opening the app — is a switch you flip yourself, off by default.
Point your agent at it — one line.
Copy your token from Settings → MCP in the app, then connect however your agent likes. That is the whole setup.
claude mcp add --transport http mnemovi \ http://127.0.0.1:5005/mcp \ --header "Authorization: Bearer <token>"One command in your terminal registers MnemoVi with Claude Code.
The server is bound to localhost and protected by a bearer token — a stray browser tab or another device on your network can’t reach it.
Then just ask — in plain words.
Your agent searches your library, reads around the hits to get the context right, and answers with citations you can jump to.
Every citation is a real moment from your own library — click it and MnemoVi jumps the player to that second.
What your agent can actually do
MnemoVi hands your agent a focused set of tools and a few ready-made workflows. The everyday ones are on; the ones that change your library are opt-in.
Search & discover
Find where something was said or shown, scope the search to a collection, or pull up “more moments like this one”.
Read the content
Read the transcript and on-screen text around a hit, pull a whole talk to summarize, or grab a single frame to look at.
Map the library
List every video with its source and length, and check whether a fresh import has finished indexing yet.
Add videosOpt-in
Let the agent import a link or a file for you, then track it until it is searchable — off until you allow it.
Jump in the appOpt-in
Have the agent open MnemoVi and seek the player straight to the moment it found — off until you allow it.
Why this is the part people don’t forget.
AI agents are brilliant — but they have never seen the videos you have collected. This is how they finally do.
Long-term memory for your agent.
Three hundred talks, courses and clips become something your agent can recall on demand — not a folder it can’t open.
Private by construction.
Localhost-only, bearer-token auth, a strict origin guard. Your videos, transcripts and searches never touch a server — there is no server.
Grounded, never guessed.
The agent quotes real moments with timecodes instead of hallucinating. If it wasn’t said or shown, it isn’t in the answer.
Yours, and it stays that way.
Pay once. Works offline. The index is an open format on your disk — it keeps working even if we don’t.
Your agent is one line away from your whole library.
Free for your first 5 videos · Lifetime from €100 · Nothing leaves your machine