What does Afterpaths do that my IDE doesn't?
Afterpaths gives a single view across Claude Code, Cursor, and Codex CLI—something no single IDE provides. It automatically extracts rules from sessions and surfaces comparative model performance.

@burnssa
基本情報
Make your AI coding agents smarter with every session
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"afterpaths": {
"command": "uvx",
"args": [
"--from",
"afterpaths[mcp]",
"afterpaths-mcp"
]
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。
Afterpaths captures sessions across AI coding tools (Claude Code, Cursor, Codex CLI), summarizes them, and automatically extracts rules—so your agents learn from every session and you retain rich context. It includes a Model Context Protocol (MCP) server that exposes session history, summaries, and rules as native tools for AI assistants.
Install with pip install afterpaths (or pip install afterpaths[mcp] for MCP support). Navigate to your project and run ap audit to see an overview. Recommended flow: ap log to browse sessions, ap summarize <ref> (requires ANTHROPIC_API_KEY), ap rules to extract rules into .claude/rules/, ap search <query> to find past discussions, and ap stats to track performance. For the MCP server, configure it with claude mcp add afterpaths -- afterpaths-mcp or run python -m afterpaths.mcp_server. Both afterpaths and ap work identically.
.claude/rules/ and .cursor/rules/ap search) with optional deep searchAfterpaths gives a single view across Claude Code, Cursor, and Codex CLI—something no single IDE provides. It automatically extracts rules from sessions and surfaces comparative model performance.
Audit, log, and search commands work without any API key. Summarization requires an `ANTHROPIC_API_KEY`. The MCP server uses local files only.
Summaries are stored in `.afterpaths/` (gitignored). Rules are written to `.claude/rules/` and `.cursor/rules/` (these should be committed). Everything stays in your project; no data leaves your machine except when sending session text to the LLM for summarization.
Cursor support is partial—the adapter reads several known formats from `state.vscdb`, but Cursor changes its storage schema often. Some sessions may show `Entries: 0`. In that case, `ap show <ref> --raw` emits a warning; you can still access the raw file directly with `sqlite3`. Tool provenance features only cover sessions whose entries the adapter can read.
Each rule file has `<!-- afterpaths:manual:start -->` and `<!-- afterpaths:manual:end -->` markers. Content between those markers survives every `ap rules` run. Auto-generated content is regenerated. Content outside markers (other than boilerplate) blocks the run unless `--force` is used.
Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.

Agent-Native Terminal

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools

Query your team's drift, vulnerability, and migration data from any AI assistant. Vibgrate MCP connects Cursor, Claude, ChatGPT, Windsurf, or VS Code to Vibgrate Cloud: 51 tools for DriftScores, CVEs and EOL runtimes, up
コメント