bytechef
starsforks
How to install bytechef?
bytechefhq/bytechef
$git clone https://github.com/bytechefhq/bytechefDocumentation · Live Demo · Discord · Connect on X · [Roadmap](https://github.com/orgs/
README.md
| 1 | <div align="center"> |
| 2 | |
| 3 | [](https://github.com/bytechefhq/bytechef/blob/master/LICENSE) |
| 4 | [](https://hub.docker.com/r/bytechef/bytechef) |
| 5 | [](https://github.com/bytechefhq/bytechef/actions/workflows/build_push.yml) |
| 6 | [](https://discord.gg/VKvNxHjpYx) |
| 7 | |
| 8 | [](https://www.bytechef.io?utm_source=github&utm_medium=organic&utm_campaign=readme) |
| 9 | |
| 10 | # **The open-source platform that unifies AI agent orchestration and workflow automation** |
| 11 | ### Autonomy and precision — in one platform. |
| 12 | |
| 13 | [Documentation](https://docs.bytechef.io?utm_source=github&utm_medium=organic&utm_campaign=readme) · [Live Demo](https://www.youtube.com/watch?v=vFpobtcdWSc) · [Discord](https://discord.gg/VKvNxHjpYx) · [Connect on X](https://x.com/bytechefhq) · [Roadmap](https://github.com/orgs/bytechefhq/projects/3) |
| 14 | |
| 15 | </div> |
| 16 | |
| 17 | > <!-- VISUAL 1 — Workflow editor. Capture: full canvas with multiple steps, branches, and a trigger. Save as static/workflow-editor.png --> |
| 18 | >  |
| 19 | |
| 20 | [//]: # (---) |
| 21 | |
| 22 | [//]: # (## About ByteChef) |
| 23 | |
| 24 | [//]: # () |
| 25 | [//]: # (ByteChef is an open-source platform for AI agents, workflow automation, and API integration.) |
| 26 | |
| 27 | [//]: # () |
| 28 | [//]: # (Instead of using separate tools for AI agents and automated workflows, ByteChef brings both into a single platform with one orchestration layer, centralized management, and enterprise-grade security.) |
| 29 | |
| 30 | [//]: # () |
| 31 | [//]: # (Built for modern enterprises, ByteChef can run in regulated environments and be embedded into products that deliver AI capabilities to end users.) |
| 32 | |
| 33 | [//]: # () |
| 34 | [//]: # (---) |
| 35 | |
| 36 | ### AI Agents — built in, not bolted on |
| 37 | |
| 38 | > <!-- VISUAL 2 — Agent editor (cluster element editor). Capture: the AI agent component opened with its cluster of sub-elements visible — model, tools list, memory, guardrails, knowledge base. Save as static/agent-editor.png --> |
| 39 | >  |
| 40 | |
| 41 | A drag-and-drop **AI Agent** component runs the full agent loop — model → tool selection → execution → observation → next step — with streaming and structured output. |
| 42 | |
| 43 | [//]: # (| Capability | What ships |) |
| 44 | |
| 45 | [//]: # (| --- | --- |) |
| 46 | |
| 47 | [//]: # (| **LLM providers** (14) | OpenAI · Anthropic · Azure OpenAI · Bedrock · Vertex Gemini · Mistral · Groq · DeepSeek · Hugging Face · Nvidia · Perplexity · Stability · Ollama · OpenRouter |) |
| 48 | |
| 49 | [//]: # (| **Tools** | Every component is a tool. Mark properties with `fromAi("…", "STRING", { required: true })` and the agent fills them at runtime. Sub-workflows are tools too. |) |
| 50 | |
| 51 | [//]: # (| **Memory** (8 backends) | JDBC · Redis · MongoDB · Cassandra · Cosmos DB · Neo4j · vector-store-backed · in-memory |) |
| 52 | |
| 53 | [//]: # (| **Guardrails** (12) | PII · LLM-PII · jailbreak · NSFW · topical alignment · keywords · secret keys · URLs · sanitize · custom regex · custom rules · violation aggregator |) |
| 54 | |
| 55 | [//]: # (| **Knowledge bases & RAG** | Native ingestion + chunking. 15+ vector stores: pgvector · Pinecone · Qdrant · Weaviate · Milvus · Couchbase · Neo4j · Redis · Typesense · MariaDB · Oracle · S3 · built-in. Two RAG patterns: `rag-modular`, `rag-questionanswer`. |) |
| 56 | |
| 57 | [//]: # (| **Agent Skills** 🚧 | _In development._ Versioned, downloadable bundles of prompt + tools + memory + guardrails + knowledge bindings. [Track on roadmap](https://github.com/orgs/bytechefhq/projects/3). |) |
| 58 | |
| 59 | [//]: # (| **MCP** (in & out) | Consume any MCP server as a tool source. Expose any workflow as an MCP tool to Claude Desktop, Cursor, Windsurf — w |
People who liked this also viewed
6 picksType
- excel-mcpA Model Context Protocol (MCP) server for working with Excel (.xlsx) files without requiring Microsoft Excel. Enables AI assistants to create, read, modify, and format spreadsheets using openpyxl, fully in Python and cross-platform.MCP ServersOct 2025
- memories-with-lessons-mcp-serverI enhance the existing memory mcp server from the official mcp github, so big thanks and credits for creating thisMCP ServersFeb 2025
- anytype-mcpAn MCP server enabling AI assistants to interact with Anytype - your encrypted, local and collaborative wiki - to organize objects, lists, and more through natural language.MCP ServersJul 2026
- mcp-server-kubernetesMCP Server for kubernetes management commandsMCP ServersJul 2026
- thoughtboxThoughtbox is an intention ledger for agents. Evaluate AI's decisions against its decision-making.MCP ServersJul 2026
- google-drive-mcpA Model Context Protocol (MCP) server that provides secure integration with Google Drive, Docs, Sheets, Slides and Calendar. It allows Claude Desktop and other MCP clients to manage files in Google Drive through a standardized interface.MCP ServersJul 2026
