aboutsummaryrefslogtreecommitdiff
path: root/docs
diff options
context:
space:
mode:
authorGravatar Reinier van der Leer <pwuts@agpt.co> 2023-11-24 15:48:31 +0100
committerGravatar Reinier van der Leer <pwuts@agpt.co> 2023-11-24 15:48:31 +0100
commit9f20c027bfc09b01715ae287644050f4bc85e946 (patch)
treeede29e6bed4ba47fe76f17439dafd5135bbdca8b /docs
parentdocs: Fix small errors and markup issues in documentation (diff)
downloadAuto-GPT-9f20c027bfc09b01715ae287644050f4bc85e946.tar.gz
Auto-GPT-9f20c027bfc09b01715ae287644050f4bc85e946.tar.bz2
Auto-GPT-9f20c027bfc09b01715ae287644050f4bc85e946.zip
docs: Add section about project CLI to documentation
- Added a new section to the documentation about the project CLI - Provided an overview of the CLI and its usage - Included common commands and their descriptions
Diffstat (limited to 'docs')
-rw-r--r--docs/content/index.md33
1 files changed, 29 insertions, 4 deletions
diff --git a/docs/content/index.md b/docs/content/index.md
index 6898da36f..85c8a2bd0 100644
--- a/docs/content/index.md
+++ b/docs/content/index.md
@@ -9,7 +9,7 @@ The AutoGPT project consists of four main components:
* The [Forge](#forge)
* The [Frontend](#frontend)
-To tie these together, we also have a CLI at the root of the project.
+To tie these together, we also have a [CLI] at the root of the project.
---
@@ -37,7 +37,7 @@ We continue to develop this project with the goal of providing access to AI assi
**[🗒️ Readme](https://github.com/Significant-Gravitas/AutoGPT/blob/master/benchmark/README.md)**
-Measure your agent's performance! The `agbenchmark` can be used with any agent that supports the agent protocol, and the integration with the project's CLI makes it even easier to use with AutoGPT and forge-based agents. The benchmark offers a stringent testing environment. Our framework allows for autonomous, objective performance evaluations, ensuring your agents are primed for real-world action.
+Measure your agent's performance! The `agbenchmark` can be used with any agent that supports the agent protocol, and the integration with the project's [CLI] makes it even easier to use with AutoGPT and forge-based agents. The benchmark offers a stringent testing environment. Our framework allows for autonomous, objective performance evaluations, ensuring your agents are primed for real-world action.
<!-- TODO: insert visual demonstrating the benchmark -->
@@ -73,6 +73,33 @@ An easy-to-use and open source frontend for any Agent Protocol-compliant agent.
---
+## 🔧 CLI
+[CLI]: #cli
+
+The project CLI makes it easy to use all of the components in the repo, separately or
+together. To install its dependencies, simply run `./run setup`, and you're ready to go!
+
+```shell
+$ ./run
+Usage: cli.py [OPTIONS] COMMAND [ARGS]...
+
+Options:
+ --help Show this message and exit.
+
+Commands:
+ agent Commands to create, start and stop agents
+ arena Commands to enter the arena
+ benchmark Commands to start the benchmark and list tests and categories
+ setup Installs dependencies needed for your system.
+```
+
+Common commands:
+* `./run agent start autogpt` &ndash; [runs](./AutoGPT/usage.md#serve-agent-protocol-mode-with-ui) the AutoGPT agent
+* `./run agent create <name>` &ndash; creates a new Forge-based agent project at `autogpts/<name>`
+* `./run benchmark start <agent>` &ndash; benchmarks the specified agent
+
+---
+
🤔 Join the AutoGPT Discord server for any queries:
[discord.gg/autogpt](https://discord.gg/autogpt)
@@ -85,5 +112,3 @@ An easy-to-use and open source frontend for any Agent Protocol-compliant agent.
- **Benchmarking**: Testing your agent's skills in the Forge.
- **Forge**: The template for building your AutoGPT agent.
- **Frontend**: The UI for tasks, logs, and task history.
-
----