back to home

flytohub / flyto-core

The open-source execution engine for AI agents. 412 modules, MCP-native, triggers, queue, versioning, metering.

View on GitHub
278 stars
46 forks
0 issues

AI Architecture Analysis

This repository is indexed by RepoMind. By analyzing flytohub/flyto-core in our AI interface, you can instantly generate complete architecture diagrams, visualize control flows, and perform automated security audits across the entire codebase.

Our Agentic Context Augmented Generation (Agentic CAG) engine loads full source files into context on-demand, avoiding the fragmentation of traditional RAG systems. Ask questions about the architecture, dependencies, or specific features to see it in action.

Source files are only loaded when you start an analysis to optimize performance.

Embed this Badge

Showcase RepoMind's analysis directly in your repository's README.

[![Analyzed by RepoMind](https://img.shields.io/badge/Analyzed%20by-RepoMind-4F46E5?style=for-the-badge)](https://repomind.in/repo/flytohub/flyto-core)
Preview:Analyzed by RepoMind

Repository Overview (README excerpt)

Crawler view

flyto-core > **A debuggable automation engine. Trace every step. Replay from any point.** > > **flyto2.com** · Desktop App · Documentation · YouTube Try in 30 seconds Screenshots captured. Performance metrics extracted. JSON report saved. **Every step traced.** --- What happens when step 8 fails? With a shell script you re-run the whole thing. With flyto-core: Steps 1–7 are instant. Only step 8 re-executes. Full context preserved. --- 3 recipes to try now Every recipe is traced. Every run is replayable. See all 32 recipes → --- Install --- The 85-line problem Here's what competitive pricing analysis looks like in Python: **Python** — 85 lines **flyto-core** — 12 steps No trace. No replay. No timing. If step 5 fails, re-run everything. Full trace. Replay from any step. Per-step timing. Every run is debuggable. --- What's New in v2.19.0 • **Smart validate_params** — auto-corrects wrong field names via alias mapping (e.g., to ) and suggests alternatives when a non-existent module is requested • **Enhanced search_modules** — word-level and tag matching scoring replaces the old substring-only search, producing more relevant results for natural language queries • **browser.extract default text mode** — when no are specified, now returns the text content of matched elements by default (previously returned empty objects) • **Browser channel support** — pass to to use the system-installed Chrome instead of bundled Chromium, useful for bypassing anti-bot detection on sites that fingerprint headless browsers Engine Features • **Execution Trace** — structured record of every step: input, output, timing, status • **Replay** — re-execute from any step with the original (or modified) context • **Breakpoints** — pause execution at any step, inspect state, resume • **Evidence Snapshots** — full state before and after each step boundary • **Data Lineage** — track data flow across steps, build dependency graphs • **Timeout Guard** — configurable workflow-level and per-step timeout protection --- 412 Modules, 78 Categories | Category | Count | Examples | |----------|-------|----------| | | 38 | launch, goto, click, extract, screenshot, fill forms, wait | | | 24 | switch, loop, branch, parallel, retry, circuit breaker, rate limit | | | 15 | filter, sort, map, reduce, unique, chunk, flatten | | | 11 | reverse, uppercase, split, replace, trim, slugify, template | | | 11 | OpenAI, Anthropic, Gemini, Notion, Slack, Telegram | | | 10 | keys, values, merge, pick, omit, get, set, flatten | | | 9 | resize, convert, crop, rotate, watermark, OCR, compress | | | 8 | json/xml/yaml/csv parse and generate | | | 8 | read, write, copy, move, delete, exists, edit, diff | | | 8 | mean, median, percentile, correlation, standard deviation | | | 7 | email, url, json, phone, credit card | | | 6 | run, ps, logs, stop, build, inspect | | | 6 | zip create/extract, tar create/extract, gzip, gunzip | | | 6 | calculate, round, ceil, floor, power, abs | | | 5 | get_pods, apply, logs, scale, describe | | | 4 | AES encrypt/decrypt, JWT create/verify | | | 4 | ping, traceroute, whois, port scan | | | 4 | parse, extract text, merge, compress | | | 4 | upload, download, list, delete | | | 4 | Gmail send/search, Calendar create/list events | | | 4 | get, set, delete, clear (memory + Redis) | | | 3 | remote exec, SFTP upload, SFTP download | | | 3 | clone, commit, diff | | | 3 | execute Python, Shell, JavaScript | | | 1 | DNS lookup (A, AAAA, MX, CNAME, TXT, NS) | | | 1 | HTTP health check with SSL cert verification | See the **Full Module Catalog** for every module, parameter, and description. --- How is this different? | | Playwright / Selenium | Shell scripts | flyto-core | |-|----------------------|---------------|------------| | Step 8 fails | Re-run everything | Re-run everything | | | What happened at step 3? | Add print(), re-run | Add echo, re-run | Full trace: input, output, timing | | Browser + API + file I/O | Write glue code | 3 languages | All built-in | | Share with team | "Clone my repo" | "Clone my repo" | | | Run in CI | Wrap in pytest/bash | Fragile | | --- How to Use CLI — run workflows from the terminal MCP Server — for Claude Code, Cursor, Windsurf Or add to your MCP config: Your AI gets all modules as tools. HTTP API — for integrations and remote execution | Endpoint | Purpose | |----------|---------| | | Execute workflow with evidence + trace | | | Replay from any step | | | Execute a single module | | | Discover all modules | | | MCP Streamable HTTP transport | Python API — for programmatic use --- 30+ Built-in Recipes No code required — every recipe is a YAML workflow template: Each recipe is a YAML workflow template. Run for full options. See **docs/RECIPES.md** for full documentation. --- Write Your Own Workflows Recipes are just YAML files. Write your own: Every run produces an execution trace and state snapshots. If step 3 fails, replay from step 3 — no re-running the whole thing. --- For Module Authors See **Module Specification** for the complete guide. --- Contributing We welcome contributions! See **CONTRIBUTING.md** for guidelines. Security Report security vulnerabilities via **security@flyto.dev**. See **SECURITY.md** for our security policy. License Apache License 2.0 — free for personal and commercial use. --- **Desktop App** · **Pricing** · **flyto2.com**