# Project-AMBER

> Project-AMBER — jjhbrams-project-amber. Use this tool when you need to provide AI agents with a persistent memory and identity layer, solving issues of data retention and continuity across interactions. It integrates with MCP servers for popular AI models like Claude, Copilot, Gemini, and Ollama, accepting input from these models and outputting stored data for seamless conversation flows. Ideal for applications requiring contextual understanding and personalized responses, Project-AMBER streamlines AI agent interactions through its git-based capabilities.

Canonical page: https://skillsregistry.net/skills/jjhbrams-project-amber  
JSON: https://api.skillsregistry.net/v1/skills/jjhbrams-project-amber

## Description

Local-first project memory for AI coding tools on Windows. Connect Claude Code, Codex and Copilot through MCP, with an Obsidian knowledge graph and desktop companion.

## Trust

- **Trust score (0–1):** 0.15
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** ai-ml
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/JJHbrams/Project-AMBER)

## 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": "jjhbrams-project-amber"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/jjhbrams-project-amber` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/jjhbrams-project-amber/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