# bernard

> Use this tool when you need to leverage AI memory for coding agents, enabling them to learn from past decisions and record new ones. Bernard provides a project-scoped memory solution, storing data as plain text in the repository, eliminating the need for external APIs or services. It is ideal for use cases requiring transparent, self-contained, and reproducible AI decision-making.

Canonical page: https://skillsregistry.net/skills/yeneryigitcelik-debug-bernard  
JSON: https://api.skillsregistry.net/v1/skills/yeneryigitcelik-debug-bernard

## Description

Bernard is an MCP server that provides repo-committed, project-scoped AI memory for coding agents. It enables agents to search past decisions and record new ones, all stored as plain text in the repo without external APIs or services.

## Trust

- **Trust score (0–1):** 0.43
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** search
- **Updated:** 2026-09-03

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/ae8sqz93id)
- **Repository:** <https://github.com/yeneryigitcelik-debug/bernard>

## 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": "yeneryigitcelik-debug-bernard"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/yeneryigitcelik-debug-bernard` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/yeneryigitcelik-debug-bernard/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