# ltm

> Use this tool when you need to seamlessly transfer the state of an AI coding session between agents, enabling continuous collaboration and minimizing duplicated efforts. The ltm protocol solves problems of session continuity and knowledge sharing, accepting inputs such as goal, decisions, attempts, and next steps, and producing outputs that can be pulled by other MCP-capable agents. Ideal for use in multi-agent environments where coding sessions require persistence and mobility.

Canonical page: https://skillsregistry.net/skills/dennisdevulder-ltm  
JSON: https://api.skillsregistry.net/v1/skills/dennisdevulder-ltm

## Description

Portable memory protocol for AI coding sessions. Push the state of a session (goal, decisions, attempts, next step) from one MCP-capable agent and pull it back from another.

## Trust

- **Trust score (0–1):** 0.60
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-05-12

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/h8mp33cmm9)
- **Repository:** <https://github.com/dennisdevulder/ltm>

## 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": "dennisdevulder-ltm"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/dennisdevulder-ltm` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/dennisdevulder-ltm/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