# Aki

> Use this tool when you need to enable AI coding assistants to retain project context and memory across sessions. Aki solves problems of lost progress and duplicated efforts by allowing AI agents to recall prior decisions and notes. It takes in coding project data as input and provides durable project memory as output, ideal for use cases where continuity and context are crucial.

Canonical page: https://skillsregistry.net/skills/akicoders-aki  
JSON: https://api.skillsregistry.net/v1/skills/akicoders-aki

## Description

Aki is a local stdio MCP server that gives AI coding assistants durable project memory, allowing them to remember decisions, search prior notes, and save context across sessions.

## Trust

- **Trust score (0–1):** 0.58
- **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/kwv0y70bha)
- **Repository:** <https://github.com/Akicoders/aki>

## 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": "akicoders-aki"
    }
  }
}
```

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