README / docs refactor (#2724)
This PR cleans up the monolithic README by breaking it into a set
navigable pages under docs/ (install, getting started, configuration,
authentication, sandboxing and approvals, platform details, FAQ, ZDR,
contributing, license). The top‑level README is now more concise and
intuitive, (with corrected screenshots).
It also consolidates overlapping content from codex-rs/README.md into
the top‑level docs and updates links accordingly. The codex-rs README
remains in place for now as a pointer and for continuity.
Finally, added an extensive config reference table at the bottom of
docs/config.md.
---------
Co-authored-by: easong-openai <easong@openai.com>
2025-08-27 10:30:39 -07:00
## Getting started
2025-10-19 16:41:10 -07:00
Looking for something specific? Jump ahead:
- [Tips & shortcuts ](#tips--shortcuts ) – hotkeys, resume flow, prompts
2025-11-11 14:45:40 +01:00
- [Non-interactive runs ](./exec.md ) – automate with `llmx exec`
2025-10-19 16:41:10 -07:00
- Ready for deeper customization? Head to [`advanced.md` ](./advanced.md )
README / docs refactor (#2724)
This PR cleans up the monolithic README by breaking it into a set
navigable pages under docs/ (install, getting started, configuration,
authentication, sandboxing and approvals, platform details, FAQ, ZDR,
contributing, license). The top‑level README is now more concise and
intuitive, (with corrected screenshots).
It also consolidates overlapping content from codex-rs/README.md into
the top‑level docs and updates links accordingly. The codex-rs README
remains in place for now as a pointer and for continuity.
Finally, added an extensive config reference table at the bottom of
docs/config.md.
---------
Co-authored-by: easong-openai <easong@openai.com>
2025-08-27 10:30:39 -07:00
### CLI usage
| Command | Purpose | Example |
| ------------------ | ---------------------------------- | ------------------------------- |
2025-11-11 14:45:40 +01:00
| `llmx` | Interactive TUI | `llmx` |
| `llmx "..."` | Initial prompt for interactive TUI | `llmx "fix lint errors"` |
| `llmx exec "..."` | Non-interactive "automation mode" | `llmx exec "explain utils.ts"` |
README / docs refactor (#2724)
This PR cleans up the monolithic README by breaking it into a set
navigable pages under docs/ (install, getting started, configuration,
authentication, sandboxing and approvals, platform details, FAQ, ZDR,
contributing, license). The top‑level README is now more concise and
intuitive, (with corrected screenshots).
It also consolidates overlapping content from codex-rs/README.md into
the top‑level docs and updates links accordingly. The codex-rs README
remains in place for now as a pointer and for continuity.
Finally, added an extensive config reference table at the bottom of
docs/config.md.
---------
Co-authored-by: easong-openai <easong@openai.com>
2025-08-27 10:30:39 -07:00
Key flags: `--model/-m` , `--ask-for-approval/-a` .
2025-09-14 19:33:19 -04:00
### Resuming interactive sessions
2025-09-03 23:20:40 -07:00
2025-11-11 14:45:40 +01:00
- Run `llmx resume` to display the session picker UI
- Resume most recent: `llmx resume --last`
- Resume by id: `llmx resume <SESSION_ID>` (You can get session ids from /status or `~/.llmx/sessions/` )
2025-09-03 23:20:40 -07:00
Examples:
```shell
2025-09-14 19:33:19 -04:00
# Open a picker of recent sessions
2025-11-11 14:45:40 +01:00
llmx resume
2025-09-14 19:33:19 -04:00
# Resume the most recent session
2025-11-11 14:45:40 +01:00
llmx resume --last
2025-09-14 19:33:19 -04:00
# Resume a specific session by id
2025-11-11 14:45:40 +01:00
llmx resume 7f9f9a2e-1b3c-4c7a-9b0e-123456789abc
2025-09-03 23:20:40 -07:00
```
README / docs refactor (#2724)
This PR cleans up the monolithic README by breaking it into a set
navigable pages under docs/ (install, getting started, configuration,
authentication, sandboxing and approvals, platform details, FAQ, ZDR,
contributing, license). The top‑level README is now more concise and
intuitive, (with corrected screenshots).
It also consolidates overlapping content from codex-rs/README.md into
the top‑level docs and updates links accordingly. The codex-rs README
remains in place for now as a pointer and for continuity.
Finally, added an extensive config reference table at the bottom of
docs/config.md.
---------
Co-authored-by: easong-openai <easong@openai.com>
2025-08-27 10:30:39 -07:00
### Running with a prompt as input
2025-11-11 14:45:40 +01:00
You can also run LLMX CLI with a prompt as input:
README / docs refactor (#2724)
This PR cleans up the monolithic README by breaking it into a set
navigable pages under docs/ (install, getting started, configuration,
authentication, sandboxing and approvals, platform details, FAQ, ZDR,
contributing, license). The top‑level README is now more concise and
intuitive, (with corrected screenshots).
It also consolidates overlapping content from codex-rs/README.md into
the top‑level docs and updates links accordingly. The codex-rs README
remains in place for now as a pointer and for continuity.
Finally, added an extensive config reference table at the bottom of
docs/config.md.
---------
Co-authored-by: easong-openai <easong@openai.com>
2025-08-27 10:30:39 -07:00
```shell
2025-11-11 14:45:40 +01:00
llmx "explain this codebase to me"
README / docs refactor (#2724)
This PR cleans up the monolithic README by breaking it into a set
navigable pages under docs/ (install, getting started, configuration,
authentication, sandboxing and approvals, platform details, FAQ, ZDR,
contributing, license). The top‑level README is now more concise and
intuitive, (with corrected screenshots).
It also consolidates overlapping content from codex-rs/README.md into
the top‑level docs and updates links accordingly. The codex-rs README
remains in place for now as a pointer and for continuity.
Finally, added an extensive config reference table at the bottom of
docs/config.md.
---------
Co-authored-by: easong-openai <easong@openai.com>
2025-08-27 10:30:39 -07:00
```
### Example prompts
2025-09-11 02:52:50 +09:00
Below are a few bite-size examples you can copy-paste. Replace the text in quotes with your own task.
README / docs refactor (#2724)
This PR cleans up the monolithic README by breaking it into a set
navigable pages under docs/ (install, getting started, configuration,
authentication, sandboxing and approvals, platform details, FAQ, ZDR,
contributing, license). The top‑level README is now more concise and
intuitive, (with corrected screenshots).
It also consolidates overlapping content from codex-rs/README.md into
the top‑level docs and updates links accordingly. The codex-rs README
remains in place for now as a pointer and for continuity.
Finally, added an extensive config reference table at the bottom of
docs/config.md.
---------
Co-authored-by: easong-openai <easong@openai.com>
2025-08-27 10:30:39 -07:00
| ✨ | What you type | What happens |
| --- | ------------------------------------------------------------------------------- | -------------------------------------------------------------------------- |
2025-11-11 14:45:40 +01:00
| 1 | `llmx "Refactor the Dashboard component to React Hooks"` | LLMX rewrites the class component, runs `npm test` , and shows the diff. |
| 2 | `llmx "Generate SQL migrations for adding a users table"` | Infers your ORM, creates migration files, and runs them in a sandboxed DB. |
| 3 | `llmx "Write unit tests for utils/date.ts"` | Generates tests, executes them, and iterates until they pass. |
| 4 | `llmx "Bulk-rename *.jpeg -> *.jpg with git mv"` | Safely renames files and updates imports/usages. |
| 5 | `llmx "Explain what this regex does: ^(?=.*[A-Z]).{8,}$"` | Outputs a step-by-step human explanation. |
| 6 | `llmx "Carefully review this repo, and propose 3 high impact well-scoped PRs"` | Suggests impactful PRs in the current codebase. |
| 7 | `llmx "Look for vulnerabilities and create a security review report"` | Finds and explains security bugs. |
README / docs refactor (#2724)
This PR cleans up the monolithic README by breaking it into a set
navigable pages under docs/ (install, getting started, configuration,
authentication, sandboxing and approvals, platform details, FAQ, ZDR,
contributing, license). The top‑level README is now more concise and
intuitive, (with corrected screenshots).
It also consolidates overlapping content from codex-rs/README.md into
the top‑level docs and updates links accordingly. The codex-rs README
remains in place for now as a pointer and for continuity.
Finally, added an extensive config reference table at the bottom of
docs/config.md.
---------
Co-authored-by: easong-openai <easong@openai.com>
2025-08-27 10:30:39 -07:00
2025-10-18 15:58:31 -07:00
Looking to reuse your own instructions? Create slash commands with [custom prompts ](./prompts.md ).
README / docs refactor (#2724)
This PR cleans up the monolithic README by breaking it into a set
navigable pages under docs/ (install, getting started, configuration,
authentication, sandboxing and approvals, platform details, FAQ, ZDR,
contributing, license). The top‑level README is now more concise and
intuitive, (with corrected screenshots).
It also consolidates overlapping content from codex-rs/README.md into
the top‑level docs and updates links accordingly. The codex-rs README
remains in place for now as a pointer and for continuity.
Finally, added an extensive config reference table at the bottom of
docs/config.md.
---------
Co-authored-by: easong-openai <easong@openai.com>
2025-08-27 10:30:39 -07:00
### Memory with AGENTS.md
2025-11-11 14:45:40 +01:00
You can give LLMX extra instructions and guidance using `AGENTS.md` files. LLMX looks for them in the following places, and merges them top-down:
README / docs refactor (#2724)
This PR cleans up the monolithic README by breaking it into a set
navigable pages under docs/ (install, getting started, configuration,
authentication, sandboxing and approvals, platform details, FAQ, ZDR,
contributing, license). The top‑level README is now more concise and
intuitive, (with corrected screenshots).
It also consolidates overlapping content from codex-rs/README.md into
the top‑level docs and updates links accordingly. The codex-rs README
remains in place for now as a pointer and for continuity.
Finally, added an extensive config reference table at the bottom of
docs/config.md.
---------
Co-authored-by: easong-openai <easong@openai.com>
2025-08-27 10:30:39 -07:00
2025-11-11 14:45:40 +01:00
1. `~/.llmx/AGENTS.md` - personal global guidance
2. Every directory from the repository root down to your current working directory (inclusive). In each directory, LLMX first looks for `AGENTS.override.md` and uses it if present; otherwise it falls back to `AGENTS.md` . Use the override form when you want to replace inherited instructions for that directory.
README / docs refactor (#2724)
This PR cleans up the monolithic README by breaking it into a set
navigable pages under docs/ (install, getting started, configuration,
authentication, sandboxing and approvals, platform details, FAQ, ZDR,
contributing, license). The top‑level README is now more concise and
intuitive, (with corrected screenshots).
It also consolidates overlapping content from codex-rs/README.md into
the top‑level docs and updates links accordingly. The codex-rs README
remains in place for now as a pointer and for continuity.
Finally, added an extensive config reference table at the bottom of
docs/config.md.
---------
Co-authored-by: easong-openai <easong@openai.com>
2025-08-27 10:30:39 -07:00
2025-09-02 23:13:04 -07:00
For more information on how to use AGENTS.md, see the [official AGENTS.md documentation ](https://agents.md/ ).
README / docs refactor (#2724)
This PR cleans up the monolithic README by breaking it into a set
navigable pages under docs/ (install, getting started, configuration,
authentication, sandboxing and approvals, platform details, FAQ, ZDR,
contributing, license). The top‑level README is now more concise and
intuitive, (with corrected screenshots).
It also consolidates overlapping content from codex-rs/README.md into
the top‑level docs and updates links accordingly. The codex-rs README
remains in place for now as a pointer and for continuity.
Finally, added an extensive config reference table at the bottom of
docs/config.md.
---------
Co-authored-by: easong-openai <easong@openai.com>
2025-08-27 10:30:39 -07:00
### Tips & shortcuts
#### Use `@` for file search
Typing `@` triggers a fuzzy-filename search over the workspace root. Use up/down to select among the results and Tab or Enter to replace the `@` with the selected path. You can use Esc to cancel the search.
#### Esc– Esc to edit a previous message
2025-11-11 14:45:40 +01:00
When the chat composer is empty, press Esc to prime “backtrack” mode. Press Esc again to open a transcript preview highlighting the last user message; press Esc repeatedly to step to older user messages. Press Enter to confirm and LLMX will fork the conversation from that point, trim the visible transcript accordingly, and pre‑ fill the composer with the selected user message so you can edit and resubmit it.
README / docs refactor (#2724)
This PR cleans up the monolithic README by breaking it into a set
navigable pages under docs/ (install, getting started, configuration,
authentication, sandboxing and approvals, platform details, FAQ, ZDR,
contributing, license). The top‑level README is now more concise and
intuitive, (with corrected screenshots).
It also consolidates overlapping content from codex-rs/README.md into
the top‑level docs and updates links accordingly. The codex-rs README
remains in place for now as a pointer and for continuity.
Finally, added an extensive config reference table at the bottom of
docs/config.md.
---------
Co-authored-by: easong-openai <easong@openai.com>
2025-08-27 10:30:39 -07:00
In the transcript preview, the footer shows an `Esc edit prev` hint while editing is active.
2025-10-19 16:41:10 -07:00
#### `--cd`/`-C` flag
2025-11-11 14:45:40 +01:00
Sometimes it is not convenient to `cd` to the directory you want LLMX to use as the "working root" before running LLMX. Fortunately, `llmx` supports a `--cd` option so you can specify whatever folder you want. You can confirm that LLMX is honoring `--cd` by double-checking the **workdir ** it reports in the TUI at the start of a new session.
2025-10-19 16:41:10 -07:00
#### `--add-dir` flag
Need to work across multiple projects in one run? Pass `--add-dir` one or more times to expose extra directories as writable roots for the current session while keeping the main working directory unchanged. For example:
```shell
2025-11-11 14:45:40 +01:00
llmx --cd apps/frontend --add-dir ../backend --add-dir ../shared
2025-10-19 16:41:10 -07:00
```
2025-11-11 14:45:40 +01:00
LLMX can then inspect and edit files in each listed directory without leaving the primary workspace.
2025-10-19 16:41:10 -07:00
README / docs refactor (#2724)
This PR cleans up the monolithic README by breaking it into a set
navigable pages under docs/ (install, getting started, configuration,
authentication, sandboxing and approvals, platform details, FAQ, ZDR,
contributing, license). The top‑level README is now more concise and
intuitive, (with corrected screenshots).
It also consolidates overlapping content from codex-rs/README.md into
the top‑level docs and updates links accordingly. The codex-rs README
remains in place for now as a pointer and for continuity.
Finally, added an extensive config reference table at the bottom of
docs/config.md.
---------
Co-authored-by: easong-openai <easong@openai.com>
2025-08-27 10:30:39 -07:00
#### Shell completions
Generate shell completion scripts via:
```shell
2025-11-11 14:45:40 +01:00
llmx completion bash
llmx completion zsh
llmx completion fish
README / docs refactor (#2724)
This PR cleans up the monolithic README by breaking it into a set
navigable pages under docs/ (install, getting started, configuration,
authentication, sandboxing and approvals, platform details, FAQ, ZDR,
contributing, license). The top‑level README is now more concise and
intuitive, (with corrected screenshots).
It also consolidates overlapping content from codex-rs/README.md into
the top‑level docs and updates links accordingly. The codex-rs README
remains in place for now as a pointer and for continuity.
Finally, added an extensive config reference table at the bottom of
docs/config.md.
---------
Co-authored-by: easong-openai <easong@openai.com>
2025-08-27 10:30:39 -07:00
```
2025-10-19 16:41:10 -07:00
#### Image input
README / docs refactor (#2724)
This PR cleans up the monolithic README by breaking it into a set
navigable pages under docs/ (install, getting started, configuration,
authentication, sandboxing and approvals, platform details, FAQ, ZDR,
contributing, license). The top‑level README is now more concise and
intuitive, (with corrected screenshots).
It also consolidates overlapping content from codex-rs/README.md into
the top‑level docs and updates links accordingly. The codex-rs README
remains in place for now as a pointer and for continuity.
Finally, added an extensive config reference table at the bottom of
docs/config.md.
---------
Co-authored-by: easong-openai <easong@openai.com>
2025-08-27 10:30:39 -07:00
2025-10-19 16:41:10 -07:00
Paste images directly into the composer (Ctrl+V / Cmd+V) to attach them to your prompt. You can also attach files via the CLI using `-i/--image` (comma‑ separated):
```bash
2025-11-11 14:45:40 +01:00
llmx -i screenshot.png "Explain this error"
llmx --image img1.png,img2.jpg "Summarize these diagrams"
2025-10-19 16:41:10 -07:00
```