# Seriora Research

- [seri](https://docs.seriora.ai/index.md): A cross-platform coding-agent CLI that ships as one binary and asks before it writes.
- [Installation](https://docs.seriora.ai/get-started/installation.md): Install the seri binary on macOS, Linux or Windows, or download it yourself.
- [Your first session](https://docs.seriora.ai/get-started/quickstart.md): Guided setup, a first task, approving a write, and undoing it.
- [Providers and models](https://docs.seriora.ai/get-started/models.md): Six providers, three ways to pay, and how seri reroutes when a credential is missing.
- [Permissions](https://docs.seriora.ai/guides/permissions.md): The gate under every tool call: modes, remembered approvals, and what counts as a write.
- [Checkpoints and undo](https://docs.seriora.ai/guides/checkpoints.md): How much of seri's work is reversible, and the one case where it is not.
- [Subagents](https://docs.seriora.ai/guides/subagents.md): Built-in roles with their own context window, and agent files you write yourself.
- [Skills](https://docs.seriora.ai/guides/skills.md): Named procedures that run in the session's own context, and the ones seri proposes.
- [Rules](https://docs.seriora.ai/guides/rules.md): Standing instructions that load always, or only when the session touches a matching file.
- [MCP servers](https://docs.seriora.ai/guides/mcp.md): Connect remote tools over MCP, authenticate them, and decide which ones the model may call.
- [Hooks](https://docs.seriora.ai/guides/hooks.md): Scripts seri runs at fixed points in the loop, outside the model's control.
- [Checking code after a write](https://docs.seriora.ai/guides/verify.md): Run your project's own check command after every write and feed the diagnostics back.
- [Memory](https://docs.seriora.ai/guides/memory.md): What the archivist writes between turns, where it goes, and how you review it.
- [Profiles](https://docs.seriora.ai/guides/profiles.md): An isolated config, credential, session and extension root for work that should not mix.
- [Hosted accounts and usage](https://docs.seriora.ai/guides/usage.md): Sign in, see what you have spent, and know when the allowance resets.
- [Sessions and context](https://docs.seriora.ai/concepts/sessions.md): What a session holds, how compaction keeps it valid, and how clearing differs from compacting.
- [How extensions load](https://docs.seriora.ai/concepts/extensions.md): One discovery model behind agents, skills, rules, MCP servers and hooks.
- [Slash commands](https://docs.seriora.ai/reference/commands.md): Every command available inside a seri session.
- [Launching seri](https://docs.seriora.ai/reference/cli.md): The flags that start a session, and the exit codes a session ends with.
- [Tools](https://docs.seriora.ai/reference/tools.md): Every tool the model can call, what it does, and which permission class it falls in.
- [Settings and environment variables](https://docs.seriora.ai/reference/environment.md): Every setting, the command that changes it in a session, and the variable that overrides it.
- [Where files live](https://docs.seriora.ai/reference/files.md): Every directory seri reads or writes, in the project and in your profile root.