openchatwidget
AGENTS.md16 starsChanged 8 months agoMITView on GitHub
Keep this Mintlify site focused on the public Open Chat Widget setup flow. Use the Mintlify skill or current Mintlify docs when you need component or configuration details.
- Reads credentials
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository2 other files it gives its agents.
- ai-elementsSkill
- mintlifySkill
The file
Show its rules and text
We split this AGENTS.md into the rules it gives an agent
13 rules. About 0 are common, 11 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈11
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 19
Use "Open Chat Widget" as the product name and "widget" on second reference
- Distinctive: line 20
Use "agent" for the AI backend and "streaming endpoint" for the HTTP route the widget calls
- Distinctive: line 21
Use "mount the widget" instead of "inject" or "drop in"
- Very specific: line 22
Use "React app" and "Next.js app" when referring to the supported repo examples
- Distinctive: line 26
Use active voice and second person ("you")
- Distinctive: line 27
Keep sentences concise and concrete
- Distinctive: line 29
Prefer code that matches this repo over invented abstractions
- Very specific: line 30
Use exact package names, env vars, and endpoint paths from the repo: @openchatwidget/sdk, OPENAI_API_KEY, and /api/chat
- Distinctive: line 31
When referencing examples, use the actual folder names in this repo
- Distinctive: line 35
Document the public SDK, setup flow, and example apps
- Distinctive: line 37
Do not document roadmap items as shipped features
- Distinctive: line 38
Do not document internal-only experiments or unpublished APIs
- Distinctive: line 39
Avoid compatibility claims that are not backed by the code in this repo
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Keep this Mintlify site focused on the public Open Chat Widget setup flow. Use the Mintlify skill or current Mintlify docs when you need component or configuration details.
Documentation project instructions
About this project
- This is a documentation site built on Mintlify
- Pages are MDX files with YAML frontmatter
- Site configuration lives in
docs/docs.json - The primary getting-started flow is
index,installation, andcreate-an-agent - The building-agents section currently contains
agent-use-casesandcompatibility - The examples section currently contains
examples,example-nextjs-landing-page,example-nextjs-portfolio-chat, andexample-basic-react-express-app - The public package name is
@openchatwidget/sdk - The main example apps live in
examples/basic-react-express-app,examples/nextjs-landing-page, andexamples/nextjs-portfolio-chat
Terminology
- Use "Open Chat Widget" as the product name and "widget" on second reference
- Use "agent" for the AI backend and "streaming endpoint" for the HTTP route the widget calls
- Use "mount the widget" instead of "inject" or "drop in"
- Use "React app" and "Next.js app" when referring to the supported repo examples
Style preferences
- Use active voice and second person ("you")
- Keep sentences concise and concrete
- Lead with the next action the reader should take
- Prefer code that matches this repo over invented abstractions
- Use exact package names, env vars, and endpoint paths from the repo:
@openchatwidget/sdk,OPENAI_API_KEY, and/api/chat - When referencing examples, use the actual folder names in this repo
Content boundaries
- Document the public SDK, setup flow, and example apps
- Favor Vercel AI SDK patterns that match the existing repo examples
- Do not document roadmap items as shipped features
- Do not document internal-only experiments or unpublished APIs
- Avoid compatibility claims that are not backed by the code in this repo
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

