Provides a shared, versioned, and local-first memory for multiple AI agents to read and write consistent facts.
Also known as make0-official/brain-oss, brain-oss, @make0-ai/brain
- Stars
- 15
- Tools
- 7
- Downloads, 30 days
- 3,208
- Latest version
- 0.3.3
- Last commit
- Nov 14, 2026
- License
- MIT
What is Make0 Brain MCP?
Make0 Brain provides a shared, versioned, and local-first memory for multiple AI agents to read and write consistent facts. It exposes 7 tools, such as list_brains, search_brain, get_memory.
Summary generated from the project's README
About Make0 Brain MCP server
Make0 Brain provides a local-first, versioned memory system designed to synchronize facts across multiple AI agents. Instead of each tool maintaining isolated instructions or memory files, this server allows different clients like Claude Code, Cursor, Windsurf, and Gemini CLI to read and write to a single source of truth. It operates using a local SQLite file on your machine, ensuring your data remains private and under your control.
Users can set up the system using the npx command, which handles model downloads and configures various agents. The server functions offline without requiring API keys after an initial setup. It includes specialized tools for searching and adding memories, and it features a web-based viewer to monitor activity and memory counts. Developers can also import existing session histories from dozens of coding agents to populate their shared memory immediately.
What you can do with it
- 1Synchronize facts across different AI toolsA developer can save a preference in Cursor and have it immediately available when using Claude Code in a separate session.
- 2Maintain a versioned history of decisionsYou can track every change made to your shared memory to see which agent edited a specific fact and when.
- 3Consolidate existing agent session dataYou can migrate historical context from many different coding agents into your new unified memory system.
- 4Monitor memory usage and activityUse a local web interface to see how many memories your apps are retrieving and adding each week.
Written from the project's README. Every use case is checked against a quote from it.
How to install Make0 Brain MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Make0 Brain MCP in Claude Code
$ claude mcp add --env 'OPENAI_API_KEY=<YOUR_OPENAI_API_KEY>' brain-oss -- npx -y @make0-ai/brainInstall Make0 Brain MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"brain-oss": {
"command": "npx",
"args": [
"-y",
"@make0-ai/brain"
],
"env": {
"OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>"
}
}
}
}Install Make0 Brain MCP in VS Code
.vscode/mcp.json
{
"servers": {
"brain-oss": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@make0-ai/brain"
],
"env": {
"OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>"
}
}
}
}Install Make0 Brain MCP in VS Code CLI
$ code --add-mcp '{"name":"brain-oss","type":"stdio","command":"npx","args":["-y","@make0-ai/brain"],"env":{"OPENAI_API_KEY":"<YOUR_OPENAI_API_KEY>"}}'Install Make0 Brain MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"brain-oss": {
"command": "npx",
"args": [
"-y",
"@make0-ai/brain"
],
"env": {
"OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>"
}
}
}
}Install Make0 Brain MCP in Codex
$ codex mcp add brain-oss --env 'OPENAI_API_KEY=<YOUR_OPENAI_API_KEY>' -- npx -y @make0-ai/brainInstall Make0 Brain MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.brain-oss] command = "npx" args = ["-y", "@make0-ai/brain"] [mcp_servers.brain-oss.env] OPENAI_API_KEY = "<YOUR_OPENAI_API_KEY>"
Install Make0 Brain MCP in Gemini CLI
$ gemini mcp add -s user -e 'OPENAI_API_KEY=<YOUR_OPENAI_API_KEY>' brain-oss npx -- -y @make0-ai/brainInstall Make0 Brain MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"brain-oss": {
"command": "npx",
"args": [
"-y",
"@make0-ai/brain"
],
"env": {
"OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>"
}
}
}
}Started by HostedMCP on 16 Nov 2026
We ran this command for @make0-ai/brain 0.3.3 in an isolated container with no network and no keys. It answered and listed 7 tools.
Make0 Brain MCP tools 7
Read from the server with tools/listlist_brainsRead-onlyList Make0 brains this connection can use. Call this first to get a brain id for search_brain. Does not list memories.
search_brainRead-onlySearch saved Brain memories. A memory may be a singular fact or a short Markdown mini-doc. Use a short, focused query with the key people, entities, preferences, or topics needed—not the full user message. Memories are retrieved with semantic + BM25 keyword search, reranked by a MiniLM cross-encoder, then expanded up to two hops along related_to graph links so connected memories surface with the seeds. Each memory includes addedBy (who first saved it) and versionCount (saved revisions). When versionCount is greater than 1, call get_memory_versions for the full history. Call get_memory whenever a result has truncated: true so you read the full note, not a clipped preview. Always pass brain from list_brains.
get_memoryRead-onlyFetch one Brain memory by id. Content is either a singular fact or a short Markdown mini-doc (up to about 800 words). The memory includes addedBy (who first saved it) and versionCount (saved revisions). When versionCount is greater than 1, call get_memory_versions to read every saved revision.
get_memory_versionsRead-onlyFetch every saved version of one Brain memory, newest first, including the current version. Use this when you need to see how a fact changed. Each version includes its full content. The version with current: true matches the memory returned by get_memory.
add_memoryActionSave a new Brain memory when the user explicitly asks to remember, save, or store something. Store either one singular fact or one short Markdown mini-doc (headings, lists, bold, links, code, and Mermaid diagrams) up to about 800 words. Use one memory for one coherent fact or note; do not paste a long document. A new memory that contradicts or restates an older one replaces it; the older one stays in version history.
update_memoryActionUpdate an existing Brain memory when the user asks to correct or change it. The new content can be a singular fact or a short Markdown mini-doc (headings, lists, bold, links, code, and Mermaid diagrams) up to about 800 words. New content replaces the old content, and the previous version is kept.
delete_memoryActionDelete a Brain memory when the user explicitly asks to remove a saved fact. The memory leaves search and reads, and every saved version is kept so the user can restore it with `npx @make0-ai/brain restore <id>`.
Configuration
OPENAI_API_KEYSecretOptional. Turns on LLM features; Make0 Brain runs fully offline without it
MAKE0_BRAIN_DBMAKE0_BRAIN_EMBEDDINGSMAKE0_BRAIN_HOMEData folder for the database, local models and .env (default ~/.make0)
MAKE0_BRAIN_LLM_BASE_URLMAKE0_BRAIN_LLM_MODELMAKE0_BRAIN_LLM_SEARCH
Automated checks
Ran Nov 16, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablemake0-official/brain-oss is public and reachablegithub.com/make0-official/brain-oss ↗Pass
- Package names this repository as its source@make0-ai/brain names make0-official/brain-oss as sourcenpmjs.com/package/@make0-ai/brain ↗Pass
- Build provenance (Sigstore attestation)Sigstore attestation for @make0-ai/brainnpmjs.com/package/@make0-ai/brain/v/0.3.3#provenance ↗Pass
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-14github.com/make0-official/brain-oss ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from @make0-ai/brainPass
- No critical advisory in the package or its dependenciesthe package checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model7 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledDestructive tools carry destructiveHintPass
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubMake0 Brain: shared AI memory for every agent
One AI memory for every agent you use. Claude Code, Claude Desktop, Cursor, Codex, Windsurf, VS Code, Gemini CLI, Hermes Agent, and OpenClaw all read and write the same memory, and every change is versioned.
A local-first, open-source AI memory server for MCP. After a one-time model download it runs offline with no API key, keeps everything in one SQLite file on your machine, and speaks the same 7 tools as the hosted Make0 Brain. It can also start full: one command imports the sessions 41 coding agents already keep on disk.
Make0 · SWE-ContextBench results · LongMemEval results
npx @make0-ai/brain init
Only using Cursor or VS Code? These buttons add the server to that one app. Run init too if you want it to download the models up front and write the custom instruction.
Why
Every agent keeps its own memory. Claude has CLAUDE.md, Cursor has rules, Codex has AGENTS.md, ChatGPT has its memory page. You end up explaining your stack, your preferences, and last week's decisions again in each one, and the copies drift apart.
Make0 Brain is one memory that all of them share:
- Tell one agent, every agent knows. A fact saved from Cursor is found by Claude Code in the next session.
- Nothing is overwritten silently. Every edit, from any agent, is kept as a version with who wrote it and when.
- It stays yours. One SQLite file on your machine, MIT licensed, exportable to plain Markdown.
Quick start
1. Connect your agents.
npx @make0-ai/brain init
init finds Claude Code, Claude Desktop, Cursor, Windsurf, VS Code, Codex CLI, Gemini CLI, Hermes Agent, and OpenClaw. When more than one is installed, it shows a checklist of them, all ticked; untick any you want to leave out. Pass --clients to choose up front, or --yes to configure every detected agent without asking. It then shows what it will change, asks once, keeps a .make0-backup of each config file, and adds Make0 Brain to each chosen app. It downloads the two local models (about 50 MB, once) with a progress bar, so your first question to an agent doesn't wait on a download. Restart the apps afterwards.
Connecting the server is not enough. The agent also needs a custom instruction so it searches Brain before answering and saves lasting facts there. init writes this into the global rules file for Claude Code (~/.claude/CLAUDE.md), Codex (~/.codex/AGENTS.md), Gemini (~/.gemini/GEMINI.md), and Windsurf. Cursor, Claude Desktop, VS Code, Hermes Agent, and OpenClaw keep rules in settings or a persona file, so init prints the same text for you to paste:
Make0 Brain is my source of truth for durable memory. Always search it before answering about me, my work, people, preferences, or past decisions. Save lasting facts and decisions to Brain. Never guess or invent memories. Use Brain exclusively for durable memory.
| App | Where it goes |
|---|---|
| Claude Code | ~/.claude/CLAUDE.md, written by init |
| Codex CLI | ~/.codex/AGENTS.md, written by init |
| Gemini CLI | ~/.gemini/GEMINI.md, written by init |
| Windsurf | Global rules, written by init |
| Cursor | Settings → Rules → User Rules. Paste it. |
| Claude Desktop | Settings → Profile → personal preferences. Paste it. |
| VS Code | .github/copilot-instructions.md in the repo. Paste it. |
| Hermes Agent | ~/.hermes/SOUL.md. Paste it. |
| OpenClaw | ~/.openclaw/workspace/AGENTS.md. Paste it. |
Skip the rule with init --no-rules.
2. Bring in the context you already have.
npx @make0-ai/brain import --detect # CLAUDE.md, AGENTS.md, Cursor/Windsurf/Copilot rules
npx @make0-ai/brain import --sessions # past sessions from 41 coding agents, one digest each
npx @make0-ai/brain import ~/Documents/MyVault # an Obsidian vault or any Markdown folder
pbpaste | npx @make0-ai/brain import - # e.g. a memory dump copied from ChatGPT
import on its own asks what to import. The details are under Import and export.
3. Look at it.
npx @make0-ai/brain view
The viewer opens on 127.0.0.1 with every brain, how many memories each holds, and what your apps retrieved and added this week.
Models live in ~/.make0/models and data in ~/.make0/brain.db. If you skip init (or pass --no-models), the first save or search downloads the models instead.
Or run it without arguments
Typed in a terminal, npx @make0-ai/brain opens a menu: connect agents, import sessions or notes, open the viewer, create a brain, choose which brains an app can use, export, restore an archived memory, or show stats. Any command run without its arguments asks for them the same way, one step at a time, with arrow keys, checkboxes, and a default on Enter. Ctrl+C cancels without changing anything.
Scripts and MCP clients are unaffected. Passing the arguments, adding --yes, or running without a terminal skips every question, and MCP clients, which start the server without a terminal, get the server as before. make0-brain serve starts the server even in a terminal.
Verify it works
Restart the apps you connected, then check that a memory written by one agent reaches another:
- Save from one agent. In Cursor (or any connected app), say: "Remember that my test fruit is mango." It should call
add_memory. - Find it from another. In a new Claude Code session (or any other connected app), ask: "What is my test fruit?" It should call
search_brainand answer "mango" without being told. - Check who wrote it. Run
npx @make0-ai/brain view, open the personal brain, and click the memory. It shows Added by Cursor and a version timeline.
Delete the test memory in the viewer when you are done. If step 1 or 2 doesn't call a Brain tool, the app is missing the custom instruction above (Cursor, Claude Desktop, and VS Code need it pasted) or wasn't restarted. Run npx @make0-ai/brain agents to confirm the app can use the personal brain.
Import directly from
Your coding agents already keep every session on disk. One command reads that history from 41 agents and saves each session as a memory, filed under its project, so the next agent can find what was asked, decided, changed, and broken last time. No API key and no model are needed.
npx @make0-ai/brain import --sessions # pick agents and a brain step by step
npx @make0-ai/brain import --sessions --agent cursor,codex # only these agents
npx @make0-ai/brain import --list-agents # agent ids and names
In a terminal it asks three things: which of the agents it found to import, which brain to save into (or a new one), and whether the summary is right. Each memory is a digest of one session: what you asked, your corrections, the files that changed, the commands that failed, and how it ended. Credentials are redacted before anything is saved. Coding-agent sessions covers the time window, the session cap, scripting flags, and the stores that cannot be read.
One context across all agents
Same tools in every app
After init, every connected agent gets the same 7 tools:
| Tool | What the agent uses it for |
|---|---|
list_brains |
Get the brain ids this app can use. personal is always there until you allocate others. |
search_brain |
Find memories for a focused query before answering. |
get_memory |
Read one memory in full. |
get_memory_versions |
Read every saved version of a memory, newest first. |
add_memory |
Save a fact or a short Markdown note when you ask it to. |
update_memory |
Change a memory. The previous text is kept as a version. |
delete_memory |
Archive a memory. Its versions are kept and you can restore it. |
The names and schemas match the hosted Make0 Brain, so a prompt or agent setup works against either one.
More than one brain
The personal brain is created with the database and cannot be deleted. Add others when a project should not share those memories:
npx @make0-ai/brain brains create "Work" --description "Client work" --agents cursor,claude-code
npx @make0-ai/brain brains # list brains
npx @make0-ai/brain agents # which app can use which brain
npx @make0-ai/brain import ~/Notes --brain Work
npx @make0-ai/brain view --brain Work
An app with no allocation sees only personal. agents grant and agents revoke change that, and so does the Connect dialog in view. Revoking every brain leaves the app with none: list_brains comes back empty until you grant one again. The viewer and the CLI can open every brain. Agents only see brains you give them, and list_brains is how they learn the id to pass to the other tools.
Open a brain to see its memories as a board, one column per category, with the app that wrote each one.
Every memory knows who wrote it
Make0 Brain reads the client name each app sends when it connects and records it as the writer: claude, chatgpt, or cursor. Any other app is recorded as mcp, with its own client name kept too. Search results show addedBy for each memory, and every version records who wrote it. You can see which agent learned what.
See what each app reads and writes
Every memory an app retrieves or writes is counted per app and per brain, with a rough token count. The home page shows this week at a glance; Details opens the full chart, filterable by brain, range, and app, in memories, tokens, or average tokens per call. The counters stay in the local database.
Make0 Brain MCP questions
How do I add Make0 Brain MCP to Claude Code?
Run claude mcp add --env 'OPENAI_API_KEY=<YOUR_OPENAI_API_KEY>' brain-oss -- npx -y @make0-ai/brain in your terminal. Add --scope user to make it available in every project.
How do I add Make0 Brain MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does Make0 Brain MCP provide?
It exposes 7 tools, including list_brains, search_brain, get_memory, get_memory_versions, add_memory.
Does Make0 Brain require an API key?
No, it runs offline with no API key after a one-time model download.
How is the memory stored?
Everything is kept in a single SQLite file on your local machine.
Can I import existing agent sessions?
Yes, you can import sessions from 41 different coding agents to bring existing context into the Brain.
Is the memory shared between different AI tools?
Yes, tools like Claude Code, Cursor, and Windsurf can all read and write to the same shared memory.