memco
agent?Log inSign up for free

Quick start

Get Spark working in one real project.

Connect Spark over MCP to the agent you already use, search shared memory before you code, and save what worked for the next agent.

/plugin marketplace add memcoai/marketplace /plugin install shared-memory@memco

About three minutes to connect · No repository upload · Personal and team workspaces

Your code stays local. Only query text, lessons you explicitly share and feedback cross the boundary.

Step 1 of 4Account

1. Create your Memco account.

The one prerequisite. Everything after this is a connection, not a code change — most people never install anything.

Two ways to start. Both are private, and both connect the same way
  • Just you — a private workspace only you can see
  • Your team — the same workspace, with people invited into it

2. Connect your agent.

Install the marketplace plugin, or point any MCP-compatible client at the endpoint. Pick the client you actually use.

Plugin marketplace — recommended
/plugin marketplace add memcoai/marketplace
/plugin install shared-memory@memco

Run both inside Claude Code.

Or add the MCP server directly
claude mcp add memco-shared-memory --transport streamable-http https://spark.memco.ai/mcp

shared-memory@memco connects Memco Shared Memory. Personal Memory is a separate plugin, personal-memory@memco, or the MCP server at https://spark.memco.ai/mcp-personal.

Endpoint and auth
https://spark.memco.ai/mcp

Authentication uses OAuth — you sign in with your Memco dashboard account when the client first connects. API keys are available as an alternative.

Using a client that isn’t listed?

In ChatGPT, install the Memco Shared Memory plugin from the plugin directory.

Anything that speaks MCP can use the same endpoint. Add it as a streamable-HTTP server in whatever config that client uses, then restart it — most clients only scan MCP configuration at launch. See the marketplace repo.

3. Check the connection.

Ask the agent directly. A live connection lists the domains your account can reach.

What Memco domains do I have access to?
Expected response
codingknowledge

Two domains, kept as separate stores — a repository fix never surfaces in a client-reporting search.

4. Search, then contribute.

Two things the agent can do now that it could not before. The second one is what makes the first one better next week.

Search
Search Memco for best practices on error handling in this codebase
Contribute
Save this as a memory in Memco — the payments service requires
idempotency keys on all POST requests

Share the lesson and the reasoning. Do not paste source code, secrets, credentials or private repository details.

The loop

The first run solves the task. The next run inherits the lesson.

Stays on the device
RepositorySource filesEnvironment & secretsGit history
The repository never crosses this line
Crosses only through an explicit action
Query textLesson title, content & tagsFeedback on a recommendation
Personal workspaceYour private memory
Private teamYour team’s private memory

Separate scopes with separate boundaries — never the same store.

Hands-on

Try the loop in a safe project.

The Spark tutorial is a small Python project with a deliberate piece of tribal knowledge. Use it to watch one agent inherit a solution another agent had to discover.

git clone https://github.com/memcoai/spark-tutorial.git
Open the tutorial on GitHub
Four moves
  1. 01Open the project and task.py in the coding agent.
  2. 02Ask the agent to implement solve_task.
  3. 03Let Spark search for the missing lesson.
  4. 04Confirm the result and allow feedback to close the loop.

Privacy

Your repository is not the payload.

Stays local
  • Source files and codebase
  • File paths and directory structure
  • Environment variables and secrets
  • Git history and diffs
  • Configuration and lock files
Sent only through an explicit action
  • Query text
  • Lesson title, content and tags
  • Feedback on a recommendation

Spark does not read the filesystem automatically. Text you paste into a query or lesson is transmitted, so do not paste secrets or sensitive repository details.

Every workspace has its own memory boundary, and a personal one works exactly like a team one. Nothing you write leaves it.

Read the full privacy model

One agent learns. The next starts ahead.

the loop

benchmarks · product · research

A short dispatch on shared memory for AI agents — the numbers behind the product, what we're shipping, and the research we're reading. No filler.

Unsubscribe anytime · no spam