AI Sessions
Searching and access your AI coding sessions from Claude Code, Gemini CLI, opencode, and OpenAI Codex.
AI Sessions MCP Server
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.
What It Does
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
Demo
Resuming a Claude Code session in Codex CLI.
Installation
Quick Install
macOS, Linux, and Windows (Git Bash/WSL):
curl -fsSL https://aisessions.dev/install.sh | bash
This installs the binary to ~/.aisessions/bin. Follow the instructions to add it to your PATH.
Custom installation directory:
INSTALL_DIR=/custom/path curl -fsSL https://aisessions.dev/install.sh | bash
Manual Download
Download pre-built binaries from GitHub Releases.
Build from Source
Prerequisites: Go 1.25 or later
go build -o bin/aisessions ./cmd/ai-sessions
Setup
After installation, configure your MCP client to use the binary:
Claude Code
claude mcp add ai-sessions ~/.aisessions/bin/aisessions
Or if using a custom install location:
claude mcp add ai-sessions /path/to/aisessions
Codex CLI
Edit ~/.codex/config.toml:
[mcp_servers.ai_sessions]
command = "~/.aisessions/bin/aisessions"
Claude Desktop
Add to your config file (Settings → Developer → Edit Config):
{
"mcpServers": {
"ai-sessions": {
"command": "/Users/YOUR_USERNAME/.aisessions/bin/aisessions"
}
}
}
Replace YOUR_USERNAME with your actual username, or use your custom install path.
Restart Claude Desktop to activate.
CLI Upload
The ai-sessions binary includes a CLI tool for uploading Claude Code transcripts to aisessions.dev for sharing.
Authentication
aisessions login
Opens your browser to generate a CLI token. The token is saved locally in ~/.aisessions/config.json.
Uploading Sessions
Interactive mode (no file argument):
aisessions upload
Displays a searchable list of your recent Claude Code sessions. Use arrow keys to navigate and select a session to upload.
Direct mode (with file path):
aisessions upload /path/to/session.jsonl
aisessions upload /path/to/session.jsonl --title "Custom Title"
Options
--title <title>- Set a custom title for the uploaded transcript
MCP Usage
Once configured as an MCP server, 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?"
How It Works
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.
Available Tools
list_available_sources
Shows which AI CLI coding agents have sessions on your system.
list_sessions
Lists recent sessions from all projects (newest first).
Arguments:
source(optional): Filter byclaude,gemini,codex, oropencodeproject_path(optional): Filter by specific project directorylimit(optional): Max results (default: 10)
Example: {"source": "claude", "limit": 20}
search_sessions
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 sourceproject_path(optional): Filter by projectlimit(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
get_session
Retrieves full session content with pagination.
Arguments:
session_id(required): Session ID from list resultssource(required): Which coding agent created itpage(optional): Page number (default: 0)page_size(optional): Messages per page (default: 20)
Development
To keep formatting consistent and catch regressions early:
- Install pre-commit and run
pre-commit installto enable hooks (gofmt,go vet,go test). - All pushes and pull requests run the GitHub Actions workflow (
.github/workflows/build.yml), which checks formatting, runsgo vet, builds the binary, and executesgo test -cover ./....
License
MIT
Máy chủ liên quan
Scout Monitoring MCP
nhà tài trợPut performance and error data directly in the hands of your AI assistant.
Alpha Vantage MCP Server
nhà tài trợAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
zig-mcp
MCP server for Zig that connects AI coding assistants to ZLS (Zig Language Server) via LSP — 16 tools for code intelligence, build, and test.
Deriv API Server
An MCP server and OpenAI function calling service for interacting with the Deriv API.
Process Manager MCP
Manage system processes (start, stop, restart, monitor) via an MCP interface with automatic cleanup.
Second Opinion MCP Server
An AI-powered coding assistant that combines insights from Gemini, Stack Overflow, and Perplexity AI to help solve programming problems.
Hive MCP Server
Provides real-time crypto and Web3 intelligence using the Hive Intelligence API.
MCP SeriesGenerator
A .NET server for generating and validating vehicle serial numbers.
MCP Options Order Flow Server
A high-performance MCP server for comprehensive options order flow analysis.
GXtract
GXtract is a MCP server designed to integrate with VS Code and other compatible editors. It provides a suite of tools for interacting with the GroundX platform, enabling you to leverage its powerful document understanding capabilities directly within your development environment.
Google Workspace Developers
Developer documentation for Google Workspace APIs
Figma (Oficial)
The Figma MCP server brings Figma directly into your workflow by providing important design information and context to AI agents generating code from Figma design files.