About innernet
innernet provides shared, versioned project and personal memory for AI tools, along with skills for loading context, saving decisions, and handing work off between sessions. Its remote connector and skills are packaged for several AI tools and MCP clients.
Key features
- 01Shared, versioned project and personal memory
- 02Load relevant project context
- 03Save decisions and update task lists
- 04Create session handoff notes
- 05Connector and skills for multiple AI tools
Use cases
- 01Resume project work in a different AI tool
- 02Retrieve a past project decision
- 03Keep project tasks current
- 04Record progress for the next session
MCP support
The innernet connector is a remote MCP server at https://innernet.live/api/mcp. MCP clients can use it to read and write the memory in an innernet account.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://innernet.live/api/mcpclaude mcp add --transport http live-innernet-innernet https://innernet.live/api/mcp{"mcpServers":{"live-innernet-innernet":{"type":"http","url":"https://innernet.live/api/mcp"}}}Open in Cursor{"servers":{"live-innernet-innernet":{"type":"http","url":"https://innernet.live/api/mcp"}}}Open in VS Code{"mcpServers":{"live-innernet-innernet":{"type":"http","url":"https://innernet.live/api/mcp"}}}{"mcpServers":{"live-innernet-innernet":{"serverUrl":"https://innernet.live/api/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project README![]()
innernet
the memory your AI tools share. innernet keeps one versioned memory for every project you work on and for you — what you're building, what you decided and why, what's in motion — and every tool you connect (Claude, ChatGPT, Codex, Cursor, any MCP client) reads and writes that same memory. open a project in Claude and the conversation picks up where your other tools left off.
this plugin brings that memory into your AI tool: the innernet connector plus two skills that tell the assistant when and how to use it.
what's inside
- innernet connector — the remote MCP server at
https://innernet.live/api/mcp. you sign in once through innernet's own OAuth page in your browser. - innernet skill — find the project you're talking about, load it, answer from the part of the memory that matters, save decisions back, keep the project's task list current, and remember durable things about you that you choose to share.
- innernet-handoff skill — "where did I leave off?" at the start of a session, and a short handoff note at the end, so the next tool continues.
use it
one repo, every host. the same connector and the same two skills, packaged for each:
claude.ai · cowork — customize → plugins → add, then connect innernet from the plugin's connectors tab and sign in.
claude code
/plugin marketplace add your-innernet/innernet-mcp
/plugin install innernet@innernet
codex
codex plugin marketplace add your-innernet/innernet-mcp
codex plugin add innernet@innernet
cursor — install innernet from the cursor marketplace, or add this repo as a plugin.
gemini cli
gemini extensions install https://github.com/your-innernet/innernet-mcp
any other MCP client — add the remote server https://innernet.live/api/mcp.
it is listed in the official MCP registry as live.innernet/innernet.
you need a free account at innernet.live. never paste an api key into a chat — the sign-in handles it.
try:
- "load my innernet project context"
- "what did we decide about pricing? check innernet"
- "where did I leave off?"
- "hand off — save my progress"
what's in the repo
| file | read by |
|---|---|
.claude-plugin/ | Claude (directory, Claude Code marketplace) |
.codex-plugin/ · .agents/plugins/marketplace.json | Codex · ChatGPT plugins |
.cursor-plugin/ | Cursor marketplace |
gemini-extension.json · GEMINI.md | Gemini CLI extensions |
server.json | the official MCP registry |
.mcp.json · skills/ | shared by all of them |
data
- the plugin runs nothing on your machine: no scripts, hooks, or local servers. it is two markdown skills and one connector entry.
- the only destination is innernet.live. Claude sends the connector what a tool call carries — a project name, your question, or the text you ask it to save — and innernet returns what your memory holds. nothing is read from Claude's own memory, chat history, or files.
- inside innernet, a few model providers do work on what you saved: Anthropic writes and folds, DeepInfra makes the embeddings retrieval uses, and TypeSafe's decision model, reached through OpenRouter with zero data retention, picks which saved sections answer an ask and sorts captures. the privacy policy names each one and what it sees.
- saves are written to your innernet account, versioned, and visible on your dashboard; you can edit or delete any of it there. personal memory is gated by disclosure levels you set, and private facts are never returned to an AI.
- tools that change data ask before running, and the skills tell Claude to say what it saved.
privacy policy — https://innernet.live/privacy · terms — https://innernet.live/terms
releasing
every push to main is a new version for the plugin directories, so each one raises
version in all four plugin manifests (claude, codex, cursor, gemini) together.
python3 scripts/check.py runs on every push: the manifests parse, the versions agree,
every url is https://innernet.live/api/mcp, the listing fits each directory's caps,
and the skills name only tools the live server serves.
server.json is the official MCP registry entry. its version follows the server's
own serverInfo.version; when that moves, raise it here and run
./scripts/publish-registry.sh (it signs in with the innernet.live domain key).
support
docs — https://innernet.live/docs/connect · email — [email protected]
MIT licensed.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.