RTFM
Index code, docs, PDFs and data in a local SQLite file and serve context to agents
- Pricing
- Open source
- Platforms
- CLI, Linux, macOS
- Runs
- Locally
- Version
- 1.0.0
- Listing updated
- 3 days ago
About RTFM
RTFM is an open-source MCP server for knowledge and memory. It runs locally on your machine and is started by your AI client.
RTFM exists because its author watched Claude Code grep the same folders in loops while writing a French tax article from about 50 pages of regulation. The fix is retrieval: one query returns ranked pointers, about three results and 300 tokens, and the agent calls rtfm_expand(source, target_section) to read more.
Everything lives in .rtfm/library.db, a single SQLite file. Search defaults to FTS5, with optional local embeddings through FastEmbed and ONNX. It has 24 built-in parsers covering Python AST, Markdown headers, XML legal text, LaTeX, CSV and XLSX, Jupyter notebooks and SQLite, and you can add formats with about 50 lines of Python or 30 lines of YAML.
On the author's own task the site reports a cost drop from $22.61 to $11.14. That figure is the project's benchmark, not an independent test.
Install
Run in a terminal
claude mcp add rtfm -- uvx rtfm-aiAdd to claude_desktop_config.json
{
"mcpServers": {
"rtfm": {
"command": "uvx",
"args": [
"rtfm-ai"
]
}
}
}Add to ~/.cursor/mcp.json
{
"mcpServers": {
"rtfm": {
"command": "uvx",
"args": [
"rtfm-ai"
]
}
}
}Add to .vscode/mcp.json
{
"servers": {
"rtfm": {
"type": "stdio",
"command": "uvx",
"args": [
"rtfm-ai"
]
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"rtfm": {
"command": "uvx",
"args": [
"rtfm-ai"
]
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"rtfm": {
"command": "uvx",
"args": [
"rtfm-ai"
]
}
}
}Tools this server provides (1)
Taken from the project documentation; the running server may differ.
- rtfm_expand
- Read more of a search hit by source and target section.
What it does
- Single SQLite index
- One local file holds the whole knowledge base.
- 24 parsers
- Code, Markdown, legal XML, LaTeX, tables, notebooks and databases.
- Expandable results
- Short ranked hits, then rtfm_expand for a section.
- Local only
- No cloud, API keys or telemetry.
- Declarative mappings
- Map JSON schemas to chunks with YAML.
- Obsidian vault mode
- Search large note vaults.
Good for
- Find the right spec section before editing code
- Search PDFs and regulations alongside source
- Cut down grep loops in a large repo
- Index an Obsidian vault for an agent
Pricing
Open source
MIT licence; free and local
Prices change. Check rtfm.roomi-fields.com before you buy.
RTFM FAQ
Does it need a cloud service?
No. The docs say it runs locally with no accounts, API keys or quotas.
Is it a vector database?
No. Default search is FTS5; embeddings are optional and local.
How do I start?
Install the Claude Code plugin or pip install rtfm-ai, then run rtfm init in your project.
What licence?
MIT.
Is RTFM free?
Yes. RTFM is open source, so you can use and self-host it for free.
How do I add RTFM to Claude Code?
Run this command in your terminal: claude mcp add rtfm -- uvx rtfm-ai
What are the best alternatives to RTFM?
The closest alternatives to RTFM are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.
Alternatives to RTFM

REA
MCP serverCLI and MCP server that lets coding agents reverse engineer apps and binaries
Runs locally- Open source
- 464K GitHub stars
- Developer tools

Codebase Memory
MCP serverLocal MCP server that builds a code knowledge graph for AI coding agents
Runs locally- Open source
- 48.7K GitHub stars
- Knowledge and memory

GitHub
MCP serverOfficial MCP server connecting AI assistants to GitHub repos, issues and workflows
Not checked yet- Remote
- Open source
- 34.5K GitHub stars
- Developer tools

Serena MCP: the IDE for your agent
MCP serverMCP toolkit giving coding agents symbol-level code retrieval and editing
Runs locally- Open source
- 31.5K GitHub stars
- Developer tools

XERJ
MCP serverLocal search engine for AI agents with cited answers over your code and docs
Runs locally- Open source
- 19.2K GitHub stars
- Knowledge and memory

Ouroboros
MCP serverSpec-first layer that pins requirements and verifies results of AI coding agent work
Runs locally- Open source
- 6.4K GitHub stars
- Developer tools