|
| 1 | +# TAGLINE |
| 2 | + |
| 3 | +Open-source agent runtime harness with TUI and CLI |
| 4 | + |
| 5 | +# TLDR |
| 6 | + |
| 7 | +**Open** the interactive terminal UI |
| 8 | + |
| 9 | +```tura``` |
| 10 | + |
| 11 | +**Start** the TUI with an initial prompt |
| 12 | + |
| 13 | +```tura "[Inspect this repository]"``` |
| 14 | + |
| 15 | +**Run** a non-interactive gateway-backed prompt |
| 16 | + |
| 17 | +```tura run "[Fix the failing test and verify it]"``` |
| 18 | + |
| 19 | +**Run** a one-shot prompt via the direct Rust CLI |
| 20 | + |
| 21 | +```tura exec "[Summarize the architecture]"``` |
| 22 | + |
| 23 | +**List** configured LLM providers |
| 24 | + |
| 25 | +```tura provider list``` |
| 26 | + |
| 27 | +**List** sessions |
| 28 | + |
| 29 | +```tura session list --json``` |
| 30 | + |
| 31 | +**Resume** the latest session with a follow-up |
| 32 | + |
| 33 | +```tura resume --last "[Continue and verify the fix]"``` |
| 34 | + |
| 35 | +# SYNOPSIS |
| 36 | + |
| 37 | +**tura** [_global_options_] [_prompt_ | _command_ [_args_...]] |
| 38 | + |
| 39 | +# PARAMETERS |
| 40 | + |
| 41 | +**--gateway-url** _URL_ |
| 42 | +> Use an explicit gateway instead of auto-starting or discovering one. |
| 43 | +
|
| 44 | +**--cwd** _PATH_ |
| 45 | +> Workspace directory sent to the gateway. Defaults to the current directory. |
| 46 | +
|
| 47 | +**--initial-session** _ID_ |
| 48 | +> Open the TUI on a specific session. Also read from **TURA_TUI_INITIAL_SESSION_ID**. |
| 49 | +
|
| 50 | +**--json** |
| 51 | +> Request JSON output where the selected command supports it. |
| 52 | +
|
| 53 | +**--verbose** |
| 54 | +> Print gateway request diagnostics to stderr. |
| 55 | +
|
| 56 | +**--plain** / **--rich** |
| 57 | +> Force plain/safe terminal rendering or rich rendering. |
| 58 | +
|
| 59 | +**--lang** **en**|**zh-CN**, **--language** **en**|**zh-CN** |
| 60 | +> Set CLI display language. |
| 61 | +
|
| 62 | +With no subcommand, **tura** opens the interactive TUI. If the first argument is not a known command, remaining text is treated as the initial TUI prompt. |
| 63 | + |
| 64 | +# COMMANDS |
| 65 | + |
| 66 | +**run** [_options_] _"prompt"_ |
| 67 | +> Gateway-backed non-interactive prompt: create or reuse a session, stream until the turn completes, print the result. Options include **-m**/**--model**, **-a**/**--agent**, **--session**, **--output** text|json|ndjson, **--timeout**, **--stream**/**--no-stream**, **--bash**/**--zsh**/**--shel**. |
| 68 | +
|
| 69 | +**exec** [_options_] _"prompt"_ |
| 70 | +> Direct Rust CLI one-shot runner (**tura_exec**). Reads prompt from stdin if omitted. Options include **-C**/**--cwd**, **-m**/**--model**, **-a**/**--agent**, **--json**, **--quiet**, **--sandbox**, **--goal**, **--bash**/**--zsh**/**--shll**. |
| 71 | +
|
| 72 | +**bash** | **zsh** | **shel** _"prompt"_ |
| 73 | +> Aliases for **run** with the **command_run** shell surface forced. |
| 74 | +
|
| 75 | +**session** **list**|**show**|**update**|**abort** ... |
| 76 | +> Inspect and modify gateway sessions. **list** supports **--all** and **--json**. |
| 77 | +
|
| 78 | +**resume** [_SESSION_ID_ | **--last**] [_prompt_...] |
| 79 | +> Show a session, or append a follow-up prompt. |
| 80 | +
|
| 81 | +**config** **get**|**set**|**model-tier** ... |
| 82 | +> Read or patch workspace session config and model tiers. |
| 83 | +
|
| 84 | +**provider** **list**|**status**|**login**|**set-auth**|**logout** ... |
| 85 | +> List providers and manage local authentication (OAuth or API key). Credentials are not bundled; configure a provider before prompt commands. |
| 86 | +
|
| 87 | +**agent** **list**|**show**|**create**|**update**|**delete**|**model** ... |
| 88 | +> Work with the gateway agent registry (default agent id often **balanced**). |
| 89 | +
|
| 90 | +**persona** **list**|**show**|**create**|**update**|**delete** ... |
| 91 | +> Work with the gateway persona registry. |
| 92 | +
|
| 93 | +**project** **current**|**list**|**create**|**default** ... |
| 94 | +> Inspect or create gateway workspaces. |
| 95 | +
|
| 96 | +**file** **list**|**read**|**open**|**reveal** ... |
| 97 | +> Operate on files in the selected workspace via the gateway. |
| 98 | +
|
| 99 | +**command** **list**|**run** ... |
| 100 | +> List or execute registered gateway commands (not arbitrary shell). |
| 101 | +
|
| 102 | +**inspect** **status**|**path**|**sessions**|**messages** ... |
| 103 | +> Diagnostics for gateway and session state. |
| 104 | +
|
| 105 | +**completion** **bash**|**zsh**|**fish** |
| 106 | +> Print shell completion snippets. |
| 107 | +
|
| 108 | +**gateway** _METHOD_ _PATH_ [**-d** _JSON_] |
| 109 | +> Send one raw HTTP request through the CLI gateway client. |
| 110 | +
|
| 111 | +**register-cli** | **unregister-cli** | **doctor-cli-path** |
| 112 | +> npm package-entry helpers to register or check the release binary on **PATH**. |
| 113 | +
|
| 114 | +Related binaries: **tura_gateway** (local HTTP/SSE gateway), **tura_gui** (desktop client), **tura_exec**, **tura_router**, **tura_session_db** (runtime plumbing). |
| 115 | + |
| 116 | +# DESCRIPTION |
| 117 | + |
| 118 | +**tura** is an open-source agent runtime harness designed to complete long-horizon coding tasks with fewer model turns and tokens than typical tool-calling loops. Instead of exposing many fine-grained tools per step, it emphasizes a macro **command_run** tool so related shell, patch, build, and test actions can run in one structured turn, plus runtime context management tied to task state. |
| 119 | + |
| 120 | +The primary entry point is the **tura** command: with no arguments it launches a terminal UI; **tura run** and **tura exec** provide non-interactive paths for scripts and CI-style prompts. A local gateway process coordinates sessions, agents, and providers. Install via npm (**tura-ai**) or from source with the project's install scripts; on first launch, configure an LLM provider and model before sending prompts. |
| 121 | + |
| 122 | +Published benchmarks compare Tura agent configurations against other coding agents on long-horizon tasks; results and methodology are documented upstream. License is AGPL-3.0-or-later. |
| 123 | + |
| 124 | +# CAVEATS |
| 125 | + |
| 126 | +Requires a configured LLM provider; installation alone does not supply credentials. Behavior and available models depend on which providers you authenticate. Some subcommands need a running or auto-started gateway. Companion binaries (**tura_gateway**, **tura_gui**, router/session DB tools) are for service and desktop use, not everyday prompt entry. Spelling of shell surfaces differs slightly between TypeScript (**shel**) and Rust (**shll**) frontends. |
| 127 | + |
| 128 | +# HISTORY |
| 129 | + |
| 130 | +Developed by **Tura-AI** as an open-source agent harness with TUI, CLI, and optional GUI, emphasizing macro command execution and context control. Distributed on npm as **tura-ai** and on GitHub as **Tura-AI/tura**. |
| 131 | + |
| 132 | +# SEE ALSO |
| 133 | + |
| 134 | +[codex](/man/codex)(1), [aider](/man/aider)(1), [opencode](/man/opencode)(1), [npm](/man/npm)(1) |
| 135 | + |
| 136 | +# RESOURCES |
| 137 | + |
| 138 | +```[Source code](https://github.com/Tura-AI/tura)``` |
| 139 | + |
| 140 | +```[Homepage](https://turaai.net/)``` |
| 141 | + |
| 142 | +```[Documentation](https://github.com/Tura-AI/tura/blob/main/docs/SUMMARY.md)``` |
| 143 | + |
| 144 | +<!-- verified: 2026-08-09 --> |
0 commit comments