LLM Reference
Actively maintained
not read yet
Use
- For
- Developers and AI coding tools that need current, version-pinned library documentation instead of stale training data
- Activity
- Actively maintainedrelease 3 days ago · site updated 2 days ago
- Runs as
- API
- Used for
- fetch version-pinned library docs for an AI assistant
- search library documentation within a token budget
- connect AI coding tools to versioned documentation over MCP
- Has an MCP server (1 in the registry)public registry →
- MCP serverorg.llmref/llmrefverified in the MCP registry
- Stateanswers, 5 toolschecked 2026-10-26
- Address to connectapi.llmref.org/v1/mcp
- MCP docsllmref.org/guides/mcpthe vendor's page ↗
This card as JSON, for your agent →
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Figure and bar: visits/mo, estimate · year: online since
- #1
ExaMCP · open
Provides web search API and data indexing for AI agents with real-time web crawling and structured data extraction.
183kActiveFrom $4 per use - #2
You.com
Returns live web search results and cleaned page content through APIs that AI agents and LLM apps call for grounding.
13.6k2020 - #3
Activeloop
Stores images, video, text and embeddings as versioned tensors in Deep Lake, a database that streams data to model training and vector search.
12.1kActive - #4
Takara TLDR
Provides fast embeddings and code search for AI agents and retrieval-augmented generation applications.
660ActiveFree plan2024 - #5
TalarionMCP · sign-in
Search API returning post-training facts from a curated corpus, so LLM apps can correct stale model knowledge at inference time.
27ActiveFrom $2 per use - #6
Querit.aiMCP · open
Provides real-time search and retrieval API for language models with global multilingual content index.
22ActiveFrom $1 per use
Not it? Say what you need
betaThree tools from the Atlas for the job you describe, each with what fits and what does not.
No notes yet. What do you use LLM Reference for?
Sign in to leave a noteWhat is LLM Reference?
Serves versioned library documentation as model-ready llms.txt files and searchable chunks through a free public API and MCP server. It is listed in the Atlas under Retrieval (RAG).
Who is LLM Reference for?
Developers and AI coding tools that need current, version-pinned library documentation instead of stale training data
Do people use LLM Reference?
Little sign of use.
Is LLM Reference still maintained?
Actively maintained: release 3 days ago · site updated 2 days ago.
What are alternatives to LLM Reference?
In Retrieval (RAG), by use: Exa, You.com, Activeloop, Takara TLDR, Talarion, Querit.ai.
How we read a tool
No votes, no reviews, no vendor claims. Every week a crawler reads each tool's own site and a few public registries, and the words on the card are bands over what it read.
- Use: visits to the site (estimated), installs from npm and PyPI, presence in Chrome's usage report.
- Activity: the newest release on GitHub, npm or PyPI; the newest dated page on the site; open roles on a public jobs board.
- Price: the vendor's own pricing page, read with the date. A figure is printed only when it is on that page.
- The line and the use cases are written by us from the homepage, one tool at a time, and refused when they repeat the vendor's marketing.
How AI assistants read each site — the reading vendors ask us about — is on each tool's own visibility page.
How we read every tool → · By INITE Atlas Desk
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.