Best for
- Developers needing reliable, replayable workflow automation
- Teams wanting deterministic tools for AI agents
- Users requiring unified execution engine for browser, API, and file operations
F
Flyto2 Core
Community
Open-source execution engine for AI agents with 468 modules, MCP-native, triggers, queue, versioning, and metering.
GitHub source repository ↗
50FMRS · D
Flyto2 Core is a feature-rich open-source execution engine, particularly suited for automation scenarios needing reliable, replayable workflows. Its modular architecture and MCP support make integration easy, but self-hosting requires technical proficiency.
Flyto2 Core is the open-source execution kernel behind Flyto2, designed for AI agents and workflow automation. It offers a registry-backed module library, MCP-native transport, YAML recipes, evidence capture, replay, triggers, queue, versioning, and metering. It is suitable for browser automation, API integration, web scraping, replayable YAML flows, evidence capture, and deterministic tools that agents can call without generating unreviewed code.
Tools
468 registry-backed modules
468 registry-backed modules across 85 catalog categories including browser, API, data, file, verification, and more.
Setup
- Install Python 3.9+. 2. Run
pip install flyto-core[browser]andplaywright install chromium. 3. Usepython -m core.mcp_serveror add via MCP config.
claude_desktop_config.json
{
"mcpServers": {
"flyto-core": {
"command": "python",
"args": ["-m", "core.mcp_server"]
}
}
}
Fit and risk
Not for
- Users looking for a hosted cloud service rather than self-hosting
- Users needing non-Python language support
- Users needing simple scripts without advanced replay and evidence features
Required permissions
- File system read/write (sandboxed path guard)
- Network requests (guarded HTTP clients)
- Environment variable reads (93 documented readers)
- Browser automation via Playwright
Risks and side effects
- Sandbox path guard may block some file writes
- Network access may be restricted, affecting external API calls
- Requires Python environment for MCP server
- Active development may change features
Troubleshooting
- Ensure Python 3.9+ is installed
- If browser automation fails, check Chromium installation
- Verify MCP config command and arguments are correct
- Consult configuration reference for security-related environment variables
Use cases
Browser automation and web scraping
API integration and workflow orchestration
Replayable YAML recipe execution
Evidence capture and audit trails
Supported clients
Claude DesktopFull support