Not found at this URL
https://www.merge.dev/llms-full.txt ↗- Discovery
- Conventional sibling path checked
- HTTP response
- 404 · text/html; charset=utf-8
Developer tools · llms.txt file breakdown
Merge llms.txt
A directly retrieved Markdown index for Merge, organized into Merge for Products, Merge for Workforce, Get started, Optional.
The actual file
Source Markdown
The saved llms.txt text, displayed as source. The file belongs to its publisher; the live endpoint may change.
Complete saved Markdown shown below.
# Merge
> Merge is the universal context engine for AI. One platform connects your agents to company data, tools, and models to reinvent what your business can do.
Merge has two product lines:
- **Merge for Products**: for product and engineering teams building AI into their own product. Includes Merge Unified, Merge Agent Handler and Merge Gateway.
- **Merge for Workforce**: for IT, security and AI leaders bringing AI to their employees.
Thousands of companies use Merge, from AI-native product teams to Fortune 500 engineering orgs.
Full technical docs for AI agents: https://docs.merge.dev/llms.txt
Complete docs in one file: https://docs.merge.dev/llms-full.txt
## Merge for Products
- [Merge Unified](https://www.merge.dev/unified-api): One API that syncs normalized customer data from hundreds of applications across HRIS, ATS, CRM, Accounting, Ticketing, File Storage and Knowledge Base. Read and write support. Merge maintains every integration.
- [Merge Agent Handler](https://www.merge.dev/merge-agent-handler): Gives AI agents authenticated, permissioned access to thousands of third-party tools, through MCP or standard HTTPS endpoints. Includes DLP rules, per-user credentials and a log of every tool call.
- [Merge Gateway](https://www.merge.dev/gateway): The control plane for production AI. One API for every major model, with routing, automatic fallback, cost controls and observability built in.
## Merge for Workforce
- [Merge for Workforce](https://www.merge.dev/workforce): The context and governance layer for employee AI. Employees get one place to reach company context, approved connectors, skills and models. IT gets visibility and control over usage and spend.
## Get started
- [Sign up for any Merge product](https://www.merge.dev/get-started)
- [Book a demo](https://www.merge.dev/get-in-touch)
- [Merge Unified quickstart](https://docs.merge.dev/merge-unified/quickstart.md)
- [Merge Agent Handler quickstart](https://docs.merge.dev/merge-agent-handler/quickstart.md)
- [Merge Gateway quickstart](https://docs.merge.dev/merge-gateway/get-started.md)
- [Merge for Workforce quickstart](https://docs.merge.dev/merge-workforce/get-started.md)
## Optional
- [Pricing](https://www.merge.dev/pricing)
- [Changelog](https://www.merge.dev/changelog)
- [Merge Gateway terms](https://www.merge.dev/legal/gateway-terms)
- Support: support@merge.dev
Measured from the saved file
Linked document
- UTF-8 text size
- 2.3 KB2380 bytes
- Token count
- 528o200k_base encoding
- Markdown links
- 1313 distinct URLs
- Fenced code blocks
- 034 lines in the file
Size measures the captured UTF-8 text, not compressed transfer size. Tokens are counted with a named tokenizer; other models can count differently. Neither measure establishes context compatibility or answer quality.
- Project H1
- Merge
Opening blockquote
Merge is the universal context engine for AI. One platform connects your agents to company data, tools, and models to reinvent what your business can do.
Context architecture
How the content is divided
4 H2 sections organize 13 parsed Markdown links. 4 links point to .md or .markdown paths; 4 link occurrences use another hostname. Linked destinations have not been recursively validated.
| H2 section | Links | UTF-8 bytes | Tokens |
|---|---|---|---|
| Merge for ProductsLine 14 | 3 | 727 | 150 |
| Merge for WorkforceLine 19 | 1 | 252 | 49 |
| Get startedLine 22 | 6 | 468 | 119 |
| OptionalLine 30 · Optional | 3 | 186 | 50 |
Link counts exclude parsed fenced and inline code and resolve relative destinations against the final endpoint. Section sizes cover the text below each H2 until the next H2.
Embedded material
Code, installation and API examples
- Fenced blocks
- 0 closed
- Declared languages
- No fenced blocks detected
- Package-install commands
- 0 detected in fenced or inline code
- Authentication examples
- 0 fenced lines match API-key, Authorization, Bearer, OAuth or access-token patterns
- HTTP request examples
- 0 fenced lines match request-method patterns
- Authentication links
- 0 links have authentication-related labels
Embedded example text and links to further documentation are counted separately. A code block does not establish that a sample runs or that an authentication flow succeeds.
Publisher prioritization
The Optional section
1 H2 section named “Optional” contain 3 parsed links. 10 links sit outside those sections. That puts 23.1% of the file’s parsed links under Optional.
The community proposal uses Optional by convention for secondary links that can be skipped for a shorter context. This label does not establish that everything outside it is critical, or that the material inside it is deprecated.
Machine-readable routes
MCP references and configuration text
MCP-related text was detected in the captured file. 0 links have MCP-related labels or paths. 0 fenced lines match mcpServers, mcp_servers or an mcp add command.
These are text and link observations. No MCP server connection, authentication or tool call was tested.
Index and bundle
llms-full.txt companion
Not found at checked URLs
A verified text response establishes a companion at the checked URL. It does not prove the bundle contains all product documentation, that generation is automated, or that it fits an assistant’s context window.
Change evidence
What can be said about freshness
This capture establishes a baseline. Update frequency cannot be determined from one observation.
Linked release and migration material
1 links have release, changelog, deprecation or migration terms in their labels or paths. These provide places to investigate product changes separately.
File changes can reveal documentation edits or navigation changes. They do not by themselves measure product release velocity, accuracy, agent adoption or AI visibility.
Capture identity and measurement method
- Requested endpoint
- https://www.merge.dev/llms.txt
- Final endpoint
- https://www.merge.dev/llms.txt
- HTTP status
- 200
- Content type
- text/plain; charset=utf-8
- Text retrieval
- Firecrawl literal text capture
- Tokenizer
- tiktoken 0.14.0 · o200k_base
- SHA-256 of saved UTF-8 text
4e869b940bce9be17ce1e1968af10da28d6085878ac088262d358debc91c39dc
Counts use a deterministic parser, not a spec-compliance grade. Unusual Markdown and indented code can fall outside its recognized patterns. See the llms.txt proposal and tokenizer implementation.