Xuan-1998/kodo
Universal persistent memory for AI coding agents. Remember conventions, learn from mistakes, carry context across sessions. Works with Claude Code, Cursor, Kiro, Codex, and any MCP client.
Platform-specific configuration:
{
"mcpServers": {
"kodo": {
"command": "npx",
"args": [
"-y",
"kodo"
]
}
}
}Add the config above to .claude/settings.json under the mcpServers key.
Universal persistent memory for AI coding agents.
[](https://docs.anthropic.com/en/docs/claude-code) [](https://cursor.sh) [](https://kiro.dev) [](https://github.com/openai/codex) [](https://modelcontextprotocol.io) [](LICENSE)
> Your AI coding agent forgets everything between sessions. You tell it "use ESM imports" — next session, it's back to require(). You fix a bug caused by missing null checks — next session, same bug. kōdo fixes that.
An agent-agnostic memory layer that stores structured memories — conventions, mistakes, decisions, preferences, patterns — in a local SQLite database, and makes them available to every agent you use. One memory store. Every agent. Zero cloud.
kodo add -t convention -c "Always use ESM imports, never require()"
kodo add -t mistake -c "Never use process.exit() in library code — throw instead"
kodo learn # auto-learn from git history
kodo export # sync to .claude/ .cursor/ .kiro/ .codex/Every AI coding agent starts every session with a blank slate. This means:
| What happens | How it feels | |-------------|-------------| | You correct the agent's code style | It forgets next session | | You explain your architecture decisions | Gone. Every. Time. | | The agent makes a mistake you've seen before | Groundhog Day | | You switch from Cursor to Claude Code | Start over from scratch | | New team member onboards with an agent | Zero institutional knowledge |
**kōdo gives your AI agent a persistent, structured, searchabl
Loading reviews...