Finally, every AI
knows you.
Persnally learns who you are from your AI history — your chats, your code, your decisions — so every tool you use stops treating you like a stranger. Your AIs read it, and can even ask it what you'd do. It lives on your machine, and it's yours.
Your profile
A builder shipping a local-first context engine — moves fast, decides from first principles, and guards user trust as non-negotiable.
Learned from your AI history
Imported 142 Claude conversations
source · ~/.claude
Interests · decay-weighted
- event sourcing0
- local-first software0
- go-to-market0
- rust0
Your context, learned once — read by every AI over MCP.
Works with the AI tools you already use
You explain yourself.
Again. And again.
ChatGPT doesn't know what you told Claude. Your coding agent relearns your stack every session, or stops to ask. So you paste the same context — your tools, your conventions, your taste — into tool after tool.
Each meets you as a stranger. And the model vendors can't fix it — their business is keeping you inside their walls, not sharing you across them.
“My stack: TypeScript, Next.js, Tailwind.”
More than memory. An engine.
Structured events, derived views, and a walkable provenance graph — explainable, decay-aware, and entirely your own.
One context, every tool reads it.
speaks MCP — adopted by every major AI
Every claim cites its evidence.
Guards user trust as non-negotiable.
- Imported 142 Claude conversations
- Vetoed telemetry without consent
- Chose local-first storage
Decide exactly what each AI can see.
Your context, in every tool you touch.
Import your history
One command finds your Claude & ChatGPT exports, your Claude Code sessions, and your git repos, and reads them.
$ persnally import
- Claude & ChatGPT exports
- Claude Code sessions
- git repos
It learns, on your machine
A local daemon turns that activity into a structured, evidence-linked model of who you are — kept on your machine, never our cloud.
building your model…
- ships the smallest design
- prefers SQLite
- guards user trust
Every AI reads it
Connected over MCP — the open protocol your AI tools already speak — Claude, Cursor, and your agents read your context the moment a session starts.
↳ loaded your context
persnally_context 2ms
The only context engine your AI can ask.
Other tools store facts about you. Persnally answers what you'd do — your agents ask it directly, get an answer with a confidence score, and it hands the question back to you when the evidence is thin. No confident guessing.
It answers, or it defers
“Would they want tests here?” “What tone for this email?” Your agent asks Persnally instead of interrupting you. Below its confidence bar it says so and sends the agent back to you — never a made-up answer.
persnally_ask “tests before I merge?”
↳ yes — you demand proof before merge; add e2e on the changed paths.
confidence 0.92 · 3 evidence events
Correct it once, it sticks
Tell it it's wrong about you and the correction becomes authoritative — it outranks everything the model inferred, and the wrong answer never comes back. The model gets sharper every time you push back.
persnally correct “I use pnpm, not npm”
↳ recorded — authoritative.
every future answer respects it
See the difference
Same prompt — “write a Slack message telling my team the deploy went out” — asked of a blank AI and an AI that read your Persnally:
Generic AI
🚀 Deploy is live! Just pushed the latest changes to production. Everything looks good so far — let me know if you spot anything unexpected.
AI + Persnally
deploy is out. watching sentry/logs for the next hour, will confirm clean or flag issues here.
Terse, lowercase, no emoji, and it knew to watch Sentry — because that's how you actually work. Not configured; learned.
Everyone remembers. Persnally answers.
The category is full of memory. What no one else does: answer what you'd do, learn when you correct it, and let you verify all of it on your own machine.
| Capability | Persnally | claude-mem | Mem0 · Supermemory | Unabyss · cloud vaults |
|---|---|---|---|---|
| Your AI can ask it — answer with a confidence score, defers when unsure | ||||
| Learns when you correct it — the correction outranks everything inferred | ||||
| Synthesizes a model of you — taste, voice, how you decide | ||||
| Local plaintext on your machine + source you can audit | ||||
| Reads your chat exports + git history |
has it · partial · no. Verified against each product's own docs and repos, July 2026. claude-mem is genuinely local and open-source too — our edge isn't custody alone, it's the answering loop and modeling you across every AI, not just your code.
A context engine you can actually trust.
Trust isn't a privacy policy here — it's the architecture. Not promises; properties you can check.
Local-first
Your context lives in ~/.persnally on your machine — not our cloud, not any vendor's silo. Serving it to an AI is a local read: instant, offline, free.
~/.persnally
- persnally.db
- config.json
stays on your machine, never our cloud
Truly deletable
Forget a topic and it erases the events and everything derived from them, then rebuilds. No tombstones, no residue.
$ persnally forget “rust”
- 18 events erased
- derived views rebuilt
no tombstones · no residue
Provenance-complete
Every claim links to the exact events behind it. “Why does it think this?” is a real lookup, never a guess.
↳ why “guards user trust”?
- #412vetoed telemetry
- #087chose local-first
- #203removed analytics
3 events · 0 guesses
Source-available
Read the engine, audit the claims, run it yourself. The event schema and MCP interface are an open spec.
Every AI knows you.
And it's yours.
Every other memory tool
“a place to store facts about you”
- A database of you — you save, you search, you retrieve
- Recalls facts; can't answer what you'd decide
- Correct it? Delete a memory, at best
- A black box — it can't tell you why
Persnally
your own context engine
- A model of you your AI can ask — with a confidence score
- Answers what you'd do; defers to you when unsure
- Correct it once and it sticks — outranks everything inferred
- Every claim cites its evidence — local, auditable, deletable
Everyone can remember facts about you. Persnally is the one your AI can ask — it answers what you'd do, defers when it's unsure, and learns the moment you correct it. All of it on your machine, and yours.
The engine is free. Forever.
Everything that touches your data runs on your machine and costs nothing. Pro adds cloud conveniences on top — and the cloud only ever carries ciphertext, never your plaintext.
Free
$0 forever
- The full engine — import, learn, synthesize your profile
- Serve your context to every AI over MCP
- The dashboard: inspect, audit provenance, delete
- Bring your own key, or run fully local with Ollama
Pro
Coming soon$6 / month · billed annually · founding price
- Encrypted backup & restore of your accumulated self
- Agent relay — your phone and cloud agents reach your context, end-to-end encrypted
- Zero-setup inference — no API key needed, inference included (fair-use)
- Reflection reports — what changed about you, over time
Privacy is never the paid tier. The local engine, the dashboard, and deletion stay free — Pro is convenience on top, not a wall around your own data.
Install, and see yourself.
One command finds your exports, reads your repos, synthesizes a profile, connects your AI clients, and opens the dashboard.
npm i -g persnally && persnally setupPaste in your terminal.
macOS · Linux · Windows · Node 20+ · background autostart on macOS & Linux · bring your own key, or run fully local with Ollama