Explyt configuration reference
Pick a mechanism based on your task. The individual pages describe file paths, scope, limitations and ways to verify the setup. Where a user-facing contract has not been published yet, the documentation says so explicitly.
Which mechanism to choose
| Task | Mechanism | Where to read |
|---|---|---|
| Give the agent general information and project rules | AGENTS.md | AGENTS.md |
| Apply an instruction to specific files | Rules | Rules |
| Capture a repeatable working scenario | Skills | Skills and the SKILL.md schema |
| Keep durable knowledge across chats | Memory Bank | Memory Bank |
| Assign different models to subagents | Model Routing | Subagent profiles |
| Connect an external service or tool | MCP | MCP |
| Restrict reading, writing and running actions | Edit Scope, ignore files and permissions | Permissions and safety |
Text instructions in AGENTS.md, Rules, Skills and Memory Bank do not replace technical access restrictions. If an instruction asks for an unavailable action, the agent mode, Edit Scope, .readignore, .writeignore and tool permissions take precedence as technical restrictions.
Interface and current chat settings
- Connection modes: the differences between Personal, Community and Enterprise.
- Tools menu: how to allow, forbid or confirm a tool call.
- Tool catalog: what the built-in tools do and the related risks.
- Active configuration: what to check when a result depends on several settings.
- Glossary: short definitions of Explyt terms.
If a setting does not apply
- Check the selected mode, Edit Scope, the ignore files, the model and the MCP status.
- Keep the instruction you are testing in a single source: the current request, a Skill, a Rule or
AGENTS.md. - Start a new chat to rule out the influence of old history.
- Bring the sources back one at a time and note which step changes the behavior.
Detailed checks for each mechanism are collected on the Configuration troubleshooting page.