@action-llama/action-llama 0.13.5 → 0.13.7

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/README.md CHANGED
@@ -1,34 +1,12 @@
1
- <p align="center">
2
- <img src="action_llama.jpg" alt="Action Llama" />
3
- </p>
4
-
5
1
  # Action Llama
6
2
 
7
- Run agents like scripts: triggered by cron or webhooks.
8
-
9
- Dev Experience:
10
-
11
- 1. The agent is triggered by a webhook, agent, or cron schedule.
12
- 2. The agent runs according to the instructions in ACTIONS.md you define
13
- 3. The agent shuts down
14
-
15
- Key features:
16
-
17
- - Agent runs are contained in a Docker container using only the credentials they need. Credentials are stored separately.
18
- - Define your agents in a git repo, add custom ones, and share them.
19
- - BYOM: bring your own model (Anthropic, OpenAI, Groq, Google Gemini, xAI, Mistral, OpenRouter, or any custom provider).
20
-
21
- Philosophy:
22
-
23
- - AL is a thin wrapper around Claude or GPT. The models move so quickly, it's important to minimize the harness.
24
-
25
- Use cases:
3
+ [![CI](https://github.com/Action-Llama/action-llama/actions/workflows/ci.yml/badge.svg)](https://github.com/Action-Llama/action-llama/actions/workflows/ci.yml)
4
+ [![npm](https://img.shields.io/npm/v/@action-llama/action-llama)](https://www.npmjs.com/package/@action-llama/action-llama)
26
5
 
27
- - A developer agent that watches for new Github issues and reacts (works great with OpenAI Codex for code generation)
28
- - A reviewer agent that watches for new Github Pull Requests and reviews them then merges if all ok
29
- - Deploy on a VPS (DigitalOcean, Vultr, Hetzner) for cost-effective remote hosting
6
+ Deploy agent workflows to the cloud.
30
7
 
31
- Have as many agents as you like. Customize the behaviour as you wish. The system is MIT licensed and fully extensible.
8
+ - [**Documentation**](https://docs.actionllama.org)
9
+ - [**actionllama.org**](https://actionllama.org)
32
10
 
33
11
  Built on [pi.dev](https://github.com/badlogic/pi-mono) as the agent harness.
34
12