Open-source LLM app development platform combining visual agentic workflows, RAG pipelines, model management and observability in one workspace.
the-open-agent/openagent
Self-hostable personal AI assistant as a single Go binary, combining LLM chat, RAG knowledge bases, and agent loops for browsing, shell, and MCP tools.
Open-source alternative to:ChatGPT
- Stars
- 5,705
- Forks
- 666
- Open issues
- 51
- Last commit
- 2 days ago
What is it?
OpenAgent is a personal AI assistant platform that combines chat with multiple large language model providers, a retrieval-augmented knowledge base built from your own documents, and autonomous agent loops. It is distributed as a single executable with no separate installation, and it can be run locally or in Docker.
On the agent side, OpenAgent can drive a browser, search and fetch web pages, run shell commands, and read or write Word, Excel, and PowerPoint files. It connects to MCP-compatible servers over SSE, Stdio, or StreamableHTTP, and every tool call is shown with its arguments and return value. Documents are chunked, embedded, and indexed, and relevant passages are retrieved before each model response.
The project includes an admin dashboard for token and cost usage, activity monitoring, tool management, and request logs, along with workflow automation with a visual BPMN-style editor, scheduled jobs, multi-tenant workspaces, SSO options, and a REST API with Swagger UI.
Key features
- 01Connects 30+ LLM providers and switches models per conversation
- 02Builds RAG knowledge bases from PDFs, Word, and Excel documents
- 03Drives browsers, runs shell commands, and fetches web content as agent tools
- 04Plugs into MCP-compatible servers over SSE, Stdio, or StreamableHTTP
- 05Ships as a single binary and runs natively on Windows
Use cases
- Running a self-hosted assistant that answers questions from your own documents
- Letting an agent browse websites and fill forms on your behalf
- Connecting one chat interface to several model providers and MCP tools
- Tracking token usage and cost across models and users in a team
Quick start
- 1
Run the official install script for macOS, Linux, or WSL from the README
- 2
Run the official PowerShell install script for Windows from the README
- 3
Open the web UI at port 14000 once it has started
- 4
Alternatively, start with Docker Compose
docker-compose up
Things to know
- The quick-start install relies on a script piped to a shell, which some users may not want to run without review.
Topics
FAQ
- What is openagent?
- Self-hostable personal AI assistant as a single Go binary, combining LLM chat, RAG knowledge bases, and agent loops for browsing, shell, and MCP tools. OpenAgent is a personal AI assistant platform that combines chat with multiple large language model providers, a retrieval-augmented knowledge base built from your own documents, and autonomous agent loops. It is distributed as a single executable with no separate installation, and it can be run locally or in Docker.
- Is openagent free to use? What license does it have?
- openagent is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
- Is openagent still maintained?
- Actively maintained. The last commit to openagent was on Oct 19, 2026.
- What can I use openagent for?
- Running a self-hosted assistant that answers questions from your own documents Letting an agent browse websites and fill forms on your behalf Connecting one chat interface to several model providers and MCP tools Tracking token usage and cost across models and users in a team
- How do I install openagent?
- Run the official install script for macOS, Linux, or WSL from the README Run the official PowerShell install script for Windows from the README Open the web UI at port 14000 once it has started Alternatively, start with Docker Compose: docker-compose up
- Where can I get openagent?
- The source code and installation instructions are on GitHub: https://github.com/the-open-agent/openagent
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
LobeHub is a platform for organizing AI agents into always-on teams that can be hired, scheduled, and reviewed from one place.
Self-hostable AI second brain that answers questions from the web and your own documents, with custom agents and scheduled automations.
A lightweight personal AI assistant written in Go that runs on low-cost hardware and connects to many LLM providers and chat apps.
Memory operating system for LLMs and AI agents that stores, retrieves, and manages long-term memory as an editable graph.
A zero-code platform that generates production-style AI agents from natural-language descriptions, with built-in tools, memory and orchestration.