Skip to content

Central Brainby NeuroAIgent

Stop re-explaining your projects to AI.

Keep project files, saved decisions and next steps ready for your connected AI tools. Central Brain prepares and searches files locally, so you can start a new session or switch supported assistants with project context ready to recall.

Start your 14-day free trial See plans from $12/month

14-day free trial. No credit card required.

Project files and memory stay on storage you choose by default. Keygen receives licensing and device data, not documents. Connected AI tools receive the context they retrieve; optional cloud connections send selected data when enabled. Security and data boundaries.

  • Windows (Microsoft Store) and Apple silicon Mac
  • Prepare files locally
  • Flat per-license pricing
  • Readable saved decisions
memory/brief.mdcheckpoint · 2 min ago
## Decisions
- Weekly client updates stay in scope.      09-15
- Use the approved Q3 forecast. 09-14

## Facts
- Meridian renews 2026-11-01. 30 day notice.
- Sarah owns the security questionnaire.

## Open questions
- Who owns the final client handoff?

## Todos
- [x] Send revised SOW to Meridian
- [ ] Re-index /contracts after Q3 changes

> memory_recall  new Claude Desktop session
>   2 decisions, 2 facts, 1 question,
>   1 todo recalled into this session.
  • Works with Claude Desktop
  • Claude Code
  • GitHub Copilot
  • GPT Desktop: standard MCP
  • Hermes and OpenClaw
  • Over MCP, source files read-only

01The problem

The work continues. Your project context should too.

You already use AI for real work. The friction comes when the next session needs the same source files, the last decision and the next step. Central Brain keeps a project record your connected tools can search and update through explicit memory tools.

  1. Save the decision before you leave.

    Ask your connected assistant to checkpoint the agreed scope, deadline or next step. Saved notes remain available after the chat ends. Only saved notes become project memory; Central Brain does not capture every conversation automatically.

  2. Pick up in another supported tool.

    Connect the next assistant to the same project and ask it to recall the saved notes. Your working record stays in readable files on storage you control.

  3. Check the original source.

    Search prepared project files and inspect the source path, page and chunk where available. The connected assistant writes the answer; you can review the retrieved evidence.

  4. Keep client work organized.

    Use a focused project for each engagement. Choose the files and saved notes the connected assistant can access, then refresh changed material as the work moves forward.

02What it remembers

Five kinds of notes and a project brief. One place for every connected tool.

Central Brain keeps a per-project memory that connected AI tools can read before they answer and add to as they work. It is deliberately simple, because memory you cannot audit is memory you cannot trust.

  • Decisions. What you chose and when, so nothing gets re-argued next week.
  • Facts. Dates, names, numbers and constraints that should carry into later sessions.
  • Open questions. The things still unresolved, so the next session starts there.
  • Todos. Carried forward until they are done.
  • Summaries. Short recaps of where the work stands, saved like any other note.
  • Project brief. The compact context a new session can start from. Compaction replaces it with an updated summary.

What an AI memory layer is, and why files beat vector-only stores

MCPTools exposed to your AI

central_brain_pingstatus

Confirms the server is running and reports the project root folder.

memory_recallmemory

Searches decisions, facts, open questions, todos and the brief before the model answers.

memory_checkpointmemory

Appends one note at a time (a decision, fact, question, todo or summary) as the work happens.

memory_compactmemory

Replaces the project brief with an updated summary and marks older notes as compacted, without deleting them.

semantic_searchsearch

Vector search over prepared files with the local MiniLM model. Results carry path, page and chunk where available.

search_textsearch

Exact text search when you know the phrase and want zero guessing.

read_filefiles

Reads a file under the project root, read-only.

list_filesfiles

Lists what the project contains so the model can navigate instead of guessing.

03How it works

Five steps. Then the memory compounds.

Point Central Brain at a folder. It prepares and indexes the files locally, opens a project-specific MCP server, and connected tools get search plus memory. Refresh only touches what changed.

  1. Choose

    Pick the source folders and where prepared output should live. Those project files stay on storage you choose in the default workflow.

  2. Prepare

    PDF, DOCX, TXT, Markdown, CSV and XLSX become AI-ready text. Optional OCR, where the build includes it, recovers scans and photos.

  3. Index

    Chunks are embedded with the bundled 384-dimension MiniLM model into a local vector index. No cloud call required.

  4. Connect

    Add the project's MCP server to Claude Desktop, Claude Code, GitHub Copilot or GPT Desktop. Memory and search appear as tools.

  5. Refresh

    New, changed, removed and failed files are processed on their own. Interrupted work resumes.

The full walkthrough MCP memory server guide

04Files you can open

Local-first is a design choice, not a slogan.

In the default workflow, your source files, prepared output, project state, local vectors and memory stay on storage you choose. Keygen receives licensing and device data, not documents. Cloud embeddings, Pinecone, Postgres and Redis are optional connections you turn on, and they send selected data only when enabled.

  • Local credential storage for optional connections; protection depends on the operating system and installed release.
  • Read-only file tools: MCP tools can read and search your files, not rewrite them. Memory tools append notes and update the project brief.
  • Project-by-project organization and permissions.
  • Share Brain: pair trusted computers and choose which projects each may access.
  • Runs air-gapped: preparing files, indexing, search and memory need no network connection. The license is re-checked every 14 days, and Team and Enterprise can get a build with no online check. Cloud-hosted AI clients and optional cloud connections need internet.

Security and data boundaries

How Central Brain connects your files to your AI tools Your folders feed Central Brain, which prepares, indexes and keeps memory locally, then serves search and memory tools over MCP to Claude Desktop, Claude Code, GitHub Copilot and GPT Desktop. YOUR FOLDERS /contracts/*.pdf /notes/*.md /finance/*.xlsx /scans/*.png (OCR) CENTRAL BRAIN runs on your machine preparetext, OCR, chunks indexMiniLM, local vectors memory/five note typesplus a project brief MCP serverfile tools read-only trail where available:path · page · chunk Claude Desktop GitHub Copilot GPT Desktopstandard MCP Hermes / OpenClaw read memory, search,checkpoint, then answer

05Ongoing project work

One client project. More than one AI session.

Built for people who already use AI daily and want the project record to carry forward.

Prepare the client update

Retrieve the relevant proposal or notes, recall the saved scope decision and ask your assistant to draft the next update from that context.

Continue in another assistant

Use the same project's prepared files and saved notes through another supported connection. The assistant needs to call the memory and search tools.

Bring a collaborator in

Share selected projects with trusted computers through Share Brain. Reading shared notes and contributing notes have separate permissions; sharing needs setup.

Central Brain for consultantsSee the setup steps

06Pricing

Choose the computers you need.

Pay monthly, or once a year for 15% off. Every plan includes the local-first workflow, project memory over MCP, semantic and exact search, and the desktop app for Windows and Apple silicon Mac.

Solo

$12/ month

One Central Brain license. $12 per license.

  • Local-first memory and files
  • Project memory over MCP
  • Semantic and exact search
  • Windows and Apple silicon Mac
Get Solo

Pair

$20/ month

Two licenses. $10 each.

  • Everything in Solo
  • Two separate one-computer keys
  • Built for a working pair
Get Pair
Lowest per license

Power Pack

$35/ month

Four licenses. $8.75 each.

  • Everything in Solo
  • Four separate one-computer keys
  • Best value for a small team
Get Power Pack

Each license activates one computer. Standard plans can be purchased online without a sales call. For custom deployment, infrastructure or support, discuss Team and Enterprise options.

Annual plans are billed once per year at 15% below twelve monthly payments. Taxes may apply. See the refund and cancellation policy.

07AEO Presence

Knowledge in. Knowledge found.

Central Brain helps your AI tools remember what you know. AEO Presence makes sure the answer engines remember you exist. It scores any site across technical SEO, on-page SEO, content quality, answer engine readiness and social sharing with 25+ deterministic checks, then ranks the fixes by impact.

Explore AEO Presence Learn AEO
26%of the score is answer engine readiness: structured data, question headings, author signals, llms.txt
25+deterministic checks on live HTML. Same input, same score, every time
1:1head-to-head comparison against a competitor's site

08Straight answers

Frequently asked questions.

More answers on the FAQ page, and every term defined in the glossary.

Does Central Brain offer a free trial?

Yes. Central Brain offers a 14-day free trial. No credit card is required. Paid plan prices remain the same.

What is Central Brain?

Central Brain is a local-first AI memory layer by NeuroAIgent: a Windows and Apple silicon Mac desktop app that indexes project files locally and gives supported AI tools, such as Claude Desktop and GitHub Copilot, persistent project memory and source-traceable search over MCP (Model Context Protocol). It prepares PDF, DOCX, TXT, Markdown, CSV and XLSX files and searches them with a bundled embedding model. Claude Desktop, Claude Code, GitHub Copilot and GPT Desktop connect on Windows and Apple silicon Macs. Preparing files, indexing, search and memory run without a cloud AI provider, and licensing uses Keygen. See the Central Brain AI product page.

Is Central Brain a second brain?

Yes, in the practical sense: it is a store of your files and project notes that you and your AI assistants can both read. The MCP server keeps a per-project memory of five note types (decisions, facts, questions, todos and summaries) plus a project brief, saved as local files. Your assistants can read it at the start of a session and add to it as work happens. Unlike a notes app, the store is searchable by meaning and reachable from Claude Desktop, Claude Code, GitHub Copilot and GPT Desktop. Unlike built-in chat memory, it lives on storage you choose. Read more at second brain for AI.

Does Central Brain replace ChatGPT or Claude?

No. Central Brain does not include a chat model and does not answer questions itself. It sits beside the assistants you already use and gives them memory and file search. Claude Desktop, Claude Code, GitHub Copilot and GPT Desktop connect to it over MCP (Model Context Protocol), call its tools, and do the reasoning and writing. You keep your existing subscriptions. Central Brain adds the part those tools lack: a local, inspectable, shared memory and a source-traceable index of your files.

What stays on my machine?

Your project content stays local by default: original files, prepared text, the local JSONL vector store, and memory notes remain on storage you choose. The bundled embedding model runs on your device, so the core preparation and search workflow does not require sending document content to a cloud embedding provider. Central Brain contacts Keygen for license activation and a check every 14 days, and runs air-gapped in between; Keygen receives licensing and device data, not documents. Connected AI tools receive the context they retrieve. If you configure an optional cloud connection, selected data for that connection goes to that provider. See the security page.

The AI doesn't own the memory. You do.

Central Brain runs on Windows 10 or later and macOS (Apple silicon M1 or newer). In the default workflow, files, prepared output, vectors and memory stay on storage you choose.

14-day free trial. No credit card required.

Get Central Brain Read the setup guide

AlsoFrom NeuroAIgent