# junto-memory

> junto-memory — tlemmons-junto-memory. Use this tool when you need to manage persistent shared memory and coordinate multiple AI agents in a workflow. It solves problems of data consistency and agent synchronization by providing a reliable server for storing and retrieving information. Ideal for multi-agent AI applications, it accepts various data inputs and outputs, and is particularly useful in production environments with multiple sessions and agents.

Canonical page: https://skillsregistry.net/skills/tlemmons-junto-memory  
JSON: https://api.skillsregistry.net/v1/skills/tlemmons-junto-memory

## Description

Persistent shared memory and coordination MCP server for multi-agent AI workflows. The memory component of the Junto system. MongoDB + ChromaDB. Production-tested with 6+ agents over 500+ sessions.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** database
- **Updated:** 2026-09-22

## Source

- **Source listing:** [GitHub](https://github.com/tlemmons/junto-memory)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "tlemmons-junto-memory"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/tlemmons-junto-memory` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/tlemmons-junto-memory/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt