Show HN: Share sessions between Codex and Claude Code (and more)

An MCP server that makes sessions from Claude Code, OpenAI Codex, Gemini CLI and opencode available to any MCP compatible client.

Mostly written using Claude Code.

Allow AI agents to search, list, and read your previous local coding sessions from multiple CLI coding agents. Useful for:

• Finding past solutions to similar problems
• Reviewing what you worked on recently
• Learning from previous conversations
• Resuming interrupted work

Resuming a Claude Code session in Codex CLI.

Download the latest release for your platform from GitHub Releases. Unzip and move the binary somewhere in your path and point your MCP config at that location.

Prerequisites: Go 1.25 or later

Move the resulting binary anywhere you like and use that path in your MCP config.

Edit ~/.codex/config.toml and add:

Add to your Claude Desktop config file (open via Settings -> Developer -> Edit Config)

Restart Claude Desktop to activate.

Once configured, you can ask:

• "Let's continue my latest sesion from Claude Code"
• "Show me my recent Codex sessions"
• "Search my sessions for authentication bugs"
• "How many times did Claude tell me I was absolutely right yesterday?"

The server reads session files stored locally by various CLI coding agents:

• Claude Code: ~/.claude/projects/[PROJECT_DIR]/*.jsonl
• Gemini CLI: ~/.gemini/tmp/[PROJECT_HASH]/chats/session-*.json
• OpenAI Codex: ~/.codex/sessions/ and ~/.codex/archived_sessions/
• opencode: ~/.local/share/opencode/storage/

When you ask your AI agent to list or search sessions, it automatically uses these agents to access your session history.

Shows which AI CLI coding agents have sessions on your system.

Lists recent sessions from all projects (newest first).

Arguments:

• source (optional): Filter by claude, gemini, codex, or opencode
• project_path (optional): Filter by specific project directory
• limit (optional): Max results (default: 10)

Example: {"source": "claude", "limit": 20}

Searches session content using BM25 ranking. Returns results sorted by relevance score with contextual snippets.

Arguments:

• query (required): Search term (supports multiple keywords)
• source (optional): Filter by source
• project_path (optional): Filter by project
• limit (optional): Max results (default: 10)

Example: {"query": "authentication bug"}

Returns: Each match includes:

• session: Session metadata (ID, source, project, timestamp)
• score: Relevance score (higher = more relevant)
• snippet: Contextual excerpt (~300 chars) showing where the match occurred

Retrieves full session content with pagination.

Arguments:

• session_id (required): Session ID from list results
• source (required): Which coding agent created it
• page (optional): Page number (default: 0)
• page_size (optional): Messages per page (default: 20)

MIT