FastGPT is an open-source AI Agent building platform with data processing, RAG knowledge bases, and visual workflow orchestration for LLM apps.
8treenet/goraven
Self-hosted AI agent platform for teams, where agents read files, run code, call APIs and deliver results in isolated workspaces.
- Stars
- 816
- Forks
- 30
- Open issues
- 32
- Last commit
- 6 days ago
What is it?
GoRaven gives each team member an independent Agent workspace rather than a plain chat window. Agents can read and write files, run shell commands, call MCP tool chains and internal APIs, search a knowledge base, analyze data and produce reports or charts. A task is assigned, broken into steps, and returned as a finished result.
The platform is aimed at teams. Members share projects and a skill library, where prompts, scripts and workflows can be packaged and installed. Admins manage model quotas, tool permissions and data access. Knowledge documents can be loaded for retrieval-augmented generation so answers draw on sources during execution.
GoRaven runs as a Docker image that bundles the Go backend, the React frontend and the runtimes it needs. It works with OpenAI, Claude, DeepSeek, Qwen, GLM and other compatible model APIs, and supports plugin hooks around conversations, tool calls and SSE event streams.
Key features
- 01Isolated Agent workspace per team member with shared projects and skills
- 02Agents read and write files, run shell commands and call MCP tools
- 03Shared skill marketplace for installing prompts, scripts and workflows
- 04RAG knowledge base so answers can cite retrieved sources
- 05Plugin hooks before and after conversations, tool calls and event streams
- 06Self-hosted via Docker with support for OpenAI-compatible model APIs
Use cases
- Giving a team shared AI agents that access internal APIs and databases
- Automating recurring file processing, reporting and data analysis tasks
- Keeping company policies and documents available to agents through RAG
- Self-hosting an agent platform so data stays on the company's own server
Topics
FAQ
- What is goraven?
- Self-hosted AI agent platform for teams, where agents read files, run code, call APIs and deliver results in isolated workspaces. GoRaven gives each team member an independent Agent workspace rather than a plain chat window. Agents can read and write files, run shell commands, call MCP tool chains and internal APIs, search a knowledge base, analyze data and produce reports or charts. A task is assigned, broken into steps, and returned as a finished result.
- Is goraven free to use? What license does it have?
- goraven is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
- Is goraven still maintained?
- Actively maintained. The last commit to goraven was on Oct 16, 2026.
- What can I use goraven for?
- Giving a team shared AI agents that access internal APIs and databases Automating recurring file processing, reporting and data analysis tasks Keeping company policies and documents available to agents through RAG Self-hosting an agent platform so data stays on the company's own server
- Where can I get goraven?
- The source code and installation instructions are on GitHub: https://github.com/8treenet/goraven
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Open-source, sessionless personal AI agent that turns goals into Tasks and keeps working on them across devices, with self-hosting via Docker Compose.
Open-source multi-agent platform that gives each AI agent its own cloud workspace with filesystem, desktop, browser, network and long-term memory.
A self-hosted, Web UI-based personal AI coworker powered by a Claude Code agent, with IM integration and sandboxed task execution.
An open-source autonomous research agent that plans questions, gathers web and local sources, and writes cited reports with any LLM provider.
Open-source AI agent application platform built on Java, LangChain4j, Spring Boot and Vue 3, covering models, agents, RAG, Skills, MCP and text-to-SQL analysis.