{"name":"ragtime: Self-Host a RAG API and MCP Server","description":"Ragtime connects local knowledge and tools to LLM clients through a self-hosted, OpenAI-compatible RAG API, MCP server, and built-in chat UI. It supports FAISS and PostgreSQL pgvector indexes, plus hosted and local model providers.","github":"https://github.com/mattv8/ragtime","url":"https://osrepos.com/repo/mattv8-ragtime","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/mattv8-ragtime","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/mattv8-ragtime.md","json":"https://osrepos.com/repo/mattv8-ragtime.json","topics":["python","self-hosted","mcp","rag","mcp-server","vector-database","knowledge-base"],"keywords":["python","self-hosted","mcp","rag","mcp-server","vector-database","knowledge-base"],"stars":null,"summary":"Ragtime connects local knowledge and tools to LLM clients through a self-hosted, OpenAI-compatible RAG API, MCP server, and built-in chat UI. It supports FAISS and PostgreSQL pgvector indexes, plus hosted and local model providers.","content":"## Overview\n\nRagtime is a self-hosted RAG service that brings local knowledge and configured tools into existing LLM clients. It combines an OpenAI-compatible chat API, an MCP server, and a built-in chat UI, with FAISS or PostgreSQL pgvector as vector-store options.\n\nIt is aimed at people who want to connect indexed files, repositories, databases, and other tools to coding assistants or OpenAI-compatible clients without relying on a separate hosted RAG service. The project supports hosted and local model providers, and also includes workspace previews for agent-driven development.\n\n## Key Features\n\n- OpenAI-compatible `/v1/chat/completions` endpoint with streaming for compatible clients.\n- MCP tools exposed over HTTP Streamable or stdio transports, with configurable authentication.\n- Built-in chat UI with tool visualization, charts, tables, and sandboxed HTML components.\n- Index uploads, Git repositories, and filesystems with FAISS or pgvector; schema and PDM indexes use pgvector.\n- Configure hosted services and local runtimes including OpenAI, Anthropic, Ollama, llama.cpp, and LM Studio.\n- Workspaces combine files, conversations, tools, and isolated runtime previews.\n- Tool safeguards include SQL allowlist patterns, query LIMIT enforcement, and optional write-operation controls.\n\n## Use Cases\n\n- A self-hosting team can index internal documentation or repositories and query them from an OpenAI-compatible client.\n- Developers using Claude Desktop, VS Code Copilot, Cursor, or JetBrains IDEs can expose configured tools and knowledge through MCP.\n- Teams with local model runtimes can connect indexed knowledge to those models while keeping the service and indexes on their own infrastructure.\n- An organization working with databases or business systems can let assistants query configured tools, subject to its own permissions and security controls.\n\n## Our Take\n\nRagtime is an actively maintained, feature-rich self-hosted RAG and agent integration service, but its development is heavily concentrated in one contributor.\n\n**Good fit if:**\n- You want one self-hosted service for a RAG API, MCP connections, and a web chat UI.\n- Your clients need OpenAI-compatible chat or MCP access to indexed files and configured tools.\n- You can operate its Docker Compose stack and review its tool-access and network security settings.\n\n**Look elsewhere if:**\n- You need a lightweight library or a single-purpose vector search component rather than a full service.\n- You cannot accept a project whose contributions come overwhelmingly from one person.\n- Your deployment cannot run Docker Compose with PostgreSQL and the other bundled services.\n\n## Project Health\n\n| Signal | Value |\n|---|---|\n| Status | **Active**: regular commits and releases |\n| Last commit | 2026-10-12 (3 days ago) |\n| Commits, last 90 days | 100+ |\n| Releases, last 12 months | 4 (latest v1.2.0, 2026-10-13) |\n| Contributors | 3 (top contributor: 98% of commits) |\n| Issues closed, last 90 days | 1 |\n| Pull requests merged, last 90 days | 51 (typically merged in 0 days) |\n| Project age | 10 months |\n\nChecked on 2026-10-16 with the GitHub API.\n\n## Project Facts\n\n- Language: Python\n- License: MIT\n- Stars: 34\n- Forks: 10\n- Archived: no\n\n## What You Need\n\nDetected in the repository:\n\n- Python >=3.10 (from pyproject.toml)\n- A Compose file to run it with its related services\n- A test suite and automated checks on GitHub Actions\n\n## Getting Started\n\nThe README's Compose setup requires Docker and Docker Compose. Create a `.env` file from `.env.example`, set credentials, then start the stack:\n\n```bash\ndocker compose up -d\n```\n\nSee the [README](https://github.com/mattv8/ragtime) for the Compose configuration, provider setup, and security guidance.\n\n## License in Plain Words\n\n**MIT** (permissive).\n\n- Commercial use: yes\n- Modify and redistribute: yes\n- You must keep: the copyright and license notice\n- Share your changes: no\n\nA summary, not legal advice: the LICENSE file is what applies.\n\n## Alternatives\n\n- [rag-web-ui](https://osrepos.com/repo/rag-web-ui-rag-web-ui): RAG Web UI focuses on document ingestion and web-based question answering, while ragtime also exposes an OpenAI-compatible RAG API and MCP server.\n- [rag-agent-platform](https://osrepos.com/repo/nedonion-rag-agent-platform): rag-agent-platform combines retrieval with configurable agents and MCP tools in a Java and Next.js stack, while ragtime centers on RAG access through its API, MCP server, and chat UI.\n- [MaxKB](https://osrepos.com/repo/1panel-dev-maxkb): MaxKB emphasizes building agents with workflows and external tools, while ragtime focuses on serving local knowledge through RAG APIs, MCP, and chat.\n\n| Project | Language | License | Stars | Status |\n|---|---|---|---|---|\n| **ragtime** | Python | MIT | 34 | Active |\n| [rag-web-ui](https://osrepos.com/repo/rag-web-ui-rag-web-ui) | TypeScript | Apache-2.0 | 3.3k | Quiet |\n| [rag-agent-platform](https://osrepos.com/repo/nedonion-rag-agent-platform) | Java | MIT | 89 | Active |\n| [MaxKB](https://osrepos.com/repo/1panel-dev-maxkb) | Python | GPL-3.0 | 22.9k | Active |\n\n## Considerations\n\n- The project is active, with regular commits and releases, but the measured contributor base is small and highly concentrated. That is a maintenance and continuity consideration for production adopters.\n- The recommended deployment is a multi-service Docker Compose stack, including PostgreSQL with pgvector, a runtime service, and SearXNG. This is more operational work than adopting a standalone library.\n- Tool access can include database queries, SSH, shell execution, and workspace operations. The README warns that read-only controls are guardrails, not complete isolation; deployments need carefully scoped credentials and network boundaries.\n- Some capabilities require elevated container or host permissions. Workspace preview isolation can fall back to chroot when mount authority is unavailable, and changing runtime isolation modes can risk snapshot history.\n- The project is MIT-licensed. Review the [license](https://github.com/mattv8/ragtime/blob/beta/LICENSE) and any obligations of the external services or models you configure.","metrics":{"detailViews":3,"githubClicks":3},"dates":{"published":null,"modified":"2026-10-16T07:48:27.000Z"}}