Korely

Coding agents

Antigravity

Give Antigravity memory that survives the session. Add the Korely MCP server to your MCP config with your API key in a header.

Connect Korely's MCP server and Antigravity can ask Korely for the current facts and the relevant memories before it answers, and save new ones as you work. Korely does the heavy part on its own servers: it reads each memory, writes the facts, closes an older fact when a newer one contradicts it, and keeps both dates of a fact (bi-temporal). Antigravity only calls the tools.

Prerequisites

  • A Korely API key (kor_live_...) without the admin permission. Make it on the dashboard's API keys page, which ticks memories:read and memories:write and leaves admin off. A key from agent signup has admin until you connect it to a dashboard login, and with it a tool can manage the account's projects and close the account; connecting takes admin away, and the key keeps working. The hobby plan is free; Pricing lists its limits.
  • Antigravity installed, with MCP support (Manage MCP Servers in the IDE).
  • For the fallback bridge only: Node.js with npx on your PATH, the bridge runs as a Node process.

Add the Korely MCP server

Korely's agent memory is a remote MCP server at https://api.korely.ai/agent/mcp, authenticated with your key in an Authorization: Bearer header. Register it in the global config at ~/.gemini/config/mcp_config.json (or .agents/mcp_config.json in the workspace). In the IDE you can open the live file via Manage MCP Servers → View raw config. These paths and the serverUrl and headers fields are the ones in Antigravity's MCP docs.

{
"mcpServers": {
"korely": {
"serverUrl": "https://api.korely.ai/agent/mcp",
"headers": {
"Authorization": "Bearer kor_live_..."
}
}
}
}

Replace kor_live_... with your real key. Restart Antigravity (or reload MCP servers) and korely should show as connected.

Fallback, the mcp-remote bridge

If your build does not send the header to a remote server (one report, on version 1.0.0, is antigravity-cli #25), register Korely as a local command server that runs mcp-remote instead:

{
"mcpServers": {
"korely": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://api.korely.ai/agent/mcp",
"--header",
"Authorization:${KORELY_AUTH}"
],
"env": {
"KORELY_AUTH": "Bearer kor_live_..."
}
}
}
}

mcp-remote speaks stdio to Antigravity and forwards each call to https://api.korely.ai/agent/mcp over Streamable HTTP, injecting the Authorization header.

About the bridge. mcp-remote is a third-party, open-source npm proxy (punkpeye/mcp-remote, MIT licence), not published or maintained by Korely or Google. It needs Node.js on your machine and runs locally as a command server. Your key reaches it through the KORELY_AUTH environment variable, and it forwards the key to Korely in the header.

If a server doesn't load

  • Use the IDE's View raw config to open whichever file is actually live, and check that korely is in it.
  • With the bridge, confirm npx resolves in the environment Antigravity launches from, the bridge is a Node process.

Korely MCP also supports OAuth, so Antigravity can sign you in instead of using a key. The Antigravity documentation describes OAuth for remote MCP servers. Korely has not tested OAuth with Antigravity. See Connect with OAuth.

What Antigravity can do

The Korely server offers six memory tools:

ToolWhat it does
korely_get_contextThe recall call: returns the current facts plus the most relevant memories as one block of text, ready to put in a prompt (the context block). It does not call a language model.
korely_addStore a memory. Korely writes facts from it on its servers, each as (subject, predicate, object), and closes an earlier fact, with its end date, when a model decides a new one replaces it.
korely_searchSearch by meaning over the stored memories, best match first.
korely_get_factsThe facts known about an end user, with point-in-time queries: as_of (what was true then) and known_as_of (what the store knew then).
korely_correct_factFix or end one fact by its id. Give a new subject, predicate or object and the old fact is closed and a corrected one is written, both kept in history. With close=true the fact is only closed, which is how you forget a fact. Needs a key with the memories:write permission.
korely_forget_memoryForget one memory by its id. It drops out of every read and the facts only it stated are closed; with erase=true it is removed for good. Needs memories:write.

Use it

Korely MCP sends its client short instructions: call korely_get_context before answering, and korely_add once a decision or preference is settled. If Antigravity follows them, a session looks like this (an example, not a recording):

You › Remember that this repo deploys to Hetzner, not Render.
→ korely_add("This repo deploys to Hetzner, not Render")
# next session, days later
You › How do we deploy this?
→ korely_get_context("deploy") → "This repo deploys to Hetzner..."
Antigravity › This repo deploys to Hetzner (you told me earlier), not Render. ...

Scoping

The four tools korely_get_context, korely_add, korely_search and korely_get_facts accept an optional user_id so one key can serve many end users: a read that names "user-b" never returns a memory written for "user-a". Omit it on a write and the memory belongs to no end user (a key confined to one end user writes to that one). Omit it on a read and the read covers every end user the key can see. korely_add and the three read tools also accept an optional agent_id. korely_correct_fact and korely_forget_memory take the id of a fact or a memory instead, and treat an id from another project (or, for a confined key, from another end user) as not found. The Korely MCP page lists every argument.

Why this is more than a notepad. Korely keeps each memory's text as written and also extracts typed facts with bi-temporal validity from it. When something changes ("this repo now deploys to Hetzner, not Render"), Korely closes the old fact with its end date instead of overwriting it, so korely_get_context returns what's true now, and as_of can still replay what was true before. The Cloud runs on servers in Helsinki; Data and governance says where text is processed.

Related