sessionfs 0.9.1

Capture, sync, and resume AI coding sessions across 8 tools — Claude Code, Codex, Gemini, Copilot, Cursor, Amp, Cline, and Roo Code.

SessionFS

Stop re-prompting. Start resuming.

SessionFS captures your AI coding sessions and makes them portable across tools and teammates.

Start a session in Claude Code, resume it in Codex. Push a session to the cloud, your teammate pulls it with full context — conversation history, workspace state, tool configs, and token usage. No copy-pasting. No re-explaining.

Supported Tools

Tool	Capture	Resume
Claude Code	Yes	Yes
Codex CLI	Yes	Yes
Gemini CLI	Yes	Yes
Copilot CLI	Yes	Yes
Cursor IDE	Yes	Capture-only
Amp	Yes	Capture-only
Cline	Yes	Capture-only
Roo Code	Yes	Capture-only

Quick Start

# 1. Install
pip install sessionfs

# 2. Start the daemon — it watches all 8 tools automatically
sfs daemon start

# 3. Use your AI tools normally — sessions are captured in the background

# 4. Browse captured sessions
sfs list

# 5. Resume a session (same tool or different)
sfs resume ses_abc123 --in codex

See the full Quickstart Guide for detailed steps.

How It Works

The sfsd daemon uses filesystem events (fsevents on macOS, inotify on Linux) to watch native AI tool session storage. When it detects new or updated sessions, it converts them into the .sfs format — a portable directory containing manifest.json, messages.jsonl, workspace.json, and tools.json.

Each tool has its own watcher:

• Claude Code — watches ~/.claude/projects/ JSONL files
• Codex CLI — watches ~/.codex/sessions/ rollout files, reads SQLite index
• Gemini CLI — watches ~/.gemini/tmp/*/chats/ JSON sessions
• Copilot CLI — watches ~/.copilot/session-state/ event files
• Cursor IDE — reads state.vscdb SQLite database (capture-only)
• Amp — watches ~/.local/share/amp/threads/ JSON threads (capture-only)
• Cline — watches VS Code globalStorage task directories (capture-only)
• Roo Code — watches VS Code globalStorage task directories (capture-only)

Sessions are indexed locally for fast browsing via the CLI. Cloud sync is opt-in; the daemon defaults to local-only.

Commands

Command	Description
sfs list	List captured sessions with filtering and sorting
sfs show <id>	Show session details, messages, and cost estimates
sfs resume <id> [--in TOOL]	Resume a session in any supported tool (auto-launches)
sfs fork <id>	Fork a session into a new independent session
sfs checkpoint <id>	Create a named checkpoint of a session
sfs export <id>	Export as .sfs, markdown, or Claude Code format
sfs import	Import sessions from any supported tool
sfs push <id>	Push a session to the cloud
sfs pull <id>	Pull a session from the cloud
sfs handoff <id> --to EMAIL	Hand off a session to a teammate with email notification
sfs search "query"	Full-text search across all sessions
sfs storage	Show local disk usage and retention policy
sfs storage prune	Prune old sessions to free disk space
sfs daemon start|stop|restart|status|logs	Manage the background daemon
sfs watcher list|enable|disable	Manage tool watchers
sfs audit <id>	Audit a session for hallucinations with LLM-as-a-Judge
sfs project init|edit|show	Manage shared project context for your team
sfs config show|set	Manage configuration
sfs mcp serve	Start MCP server for AI tool integration
sfs mcp install --for TOOL	Auto-configure MCP for Claude Code, Cursor, or Copilot
sfs admin reindex	Re-extract metadata for all cloud sessions

See the full CLI Reference for options and examples.

Cross-Tool Resume

# Start in Claude Code, resume in Codex
sfs resume ses_abc123 --in codex

# Start in Gemini, resume in Claude Code
sfs resume ses_def456 --in claude-code

# Cursor sessions can be resumed in any bidirectional tool
sfs resume ses_ghi789 --in gemini

SessionFS converts between native formats automatically — message roles, tool calls, thinking blocks, and workspace state are mapped across tools. See Compatibility for details on which tools support resume and why some are capture-only.

Cloud Sync (Optional)

# Create an account
sfs auth signup --url https://api.sessionfs.dev

# Push a session
sfs push <session_id>

# Pull on another machine
sfs pull <session_id>
sfs resume <session_id>

Free tier includes 14-day cloud retention with 1 device. See the Sync Guide for setup, conflict handling, and self-hosted options.

Session Search

# Search across all local sessions
sfs search "rate limiting middleware"

# MCP server lets AI tools search your past sessions
sfs mcp install --for claude-code

Team Handoff

# Hand off a session to a teammate
sfs handoff ses_abc123 --to [e-mail]

# Teammate pulls and resumes
sfs pull ses_abc123
sfs resume ses_abc123 --in codex

Shared Project Context

Share architecture decisions, conventions, and team knowledge with every AI agent working on your codebase.

# Initialize project context (run from inside a git repo)
sfs project init
sfs project edit    # Opens in $EDITOR

# Any teammate with sessions in the repo can read it
sfs project show

AI agents connected via the MCP server can call get_project_context to read the document automatically. See Project Context for details.

Web Dashboard

A browser-based interface for browsing and managing synced sessions. Accessible at http://localhost:8000 when running the self-hosted server, or at app.sessionfs.dev for cloud accounts.

Self-Hosted Server

docker compose up -d

Starts the SessionFS API server, PostgreSQL, and web dashboard. See the Sync Guide for full configuration.

Session Format

Sessions are stored as .sfs directories:

• manifest.json — identity, provenance, model info, stats
• messages.jsonl — conversation history with content blocks
• workspace.json — git state, files, environment
• tools.json — tool definitions and shell context

All file paths are relative to workspace root. Sessions are append-only — conflict resolution appends both sides rather than merging.

Status

v0.9.1 — Public Beta. 835 tests passing.

What works today:

• Eight-tool session capture (Claude Code, Codex, Gemini, Cursor, Copilot CLI, Amp, Cline, Roo Code)
• Cross-tool resume between Claude Code, Codex, Gemini, and Copilot CLI (auto-launches native tool)
• Shared project context — one document per repo, shared across the team, readable via MCP
• Local storage management with configurable retention, pruning, and disk warnings
• Full-text search across all sessions (CLI + dashboard + API)
• MCP server with 5 tools — search, context, recent, related, and project context
• LLM-as-a-Judge — audit sessions for hallucinations (BYOK, multi-provider, OpenRouter, custom base URL for LiteLLM/vLLM/Ollama)
• GitHub PR App — auto-comment AI session context on pull requests
• Team handoff with email notification and smart workspace resolution
• Multi-provider email (Resend, SMTP, or disabled for air-gapped)
• Browse, inspect, export, fork, and checkpoint sessions
• Cloud sync with push/pull, email verification, and ETag conflict detection
• Self-hosted deployment via Helm chart (EKS/GKE/AKS tested)
• Web dashboard with session management, search, handoffs, and audit

On the roadmap:

• Stripe billing integration
• Session similarity and duplicate detection
• Cost analytics dashboard
• VS Code extension

Contributing

See CONTRIBUTING.md for development setup, testing, and PR guidelines.

License

Apache 2.0