Skip to content

Commit 483c518

Browse files
authored
Adjust CI status placement and example catalog details (#193)
1 parent 948506f commit 483c518

File tree

8 files changed

+41
-16
lines changed

8 files changed

+41
-16
lines changed

README.md

Lines changed: 20 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -27,6 +27,16 @@ Read more on our [documentation website](https://microsoft.github.io/agent-light
2727
<img src="docs/assets/readme-diff.svg" alt="Agent-Lightning Core Quickstart" style="width:100%"/>
2828
</p>
2929

30+
## ⚡ Installation
31+
32+
```bash
33+
pip install agentlightning
34+
```
35+
36+
Please refer to our [installation guide](https://microsoft.github.io/agent-lightning/stable/tutorials/installation/) for more details.
37+
38+
To start using Agent-lightning, check out our [documentation](https://microsoft.github.io/agent-lightning/) and [examples](./examples).
39+
3040
## ⚡ Articles
3141

3242
- 8/11/2025 [Training AI Agents to Write and Self-correct SQL with Reinforcement Learning](https://medium.com/@yugez/training-ai-agents-to-write-and-self-correct-sql-with-reinforcement-learning-571ed31281ad) Medium.
@@ -39,14 +49,6 @@ Read more on our [documentation website](https://microsoft.github.io/agent-light
3949
- [DeepWerewolf](https://github.com/af-74413592/DeepWerewolf) — A case study of agent RL training for the Chinese Werewolf game built with AgentScope and Agent Lightning.
4050
- [AgentFlow](https://agentflow.stanford.edu/) — A modular multi-agent framework that combines planner, executor, verifier, and generator agents with the Flow-GRPO algorithm to tackle long-horizon, sparse-reward tasks.
4151

42-
## ⚡ Installation
43-
44-
```bash
45-
pip install agentlightning
46-
```
47-
48-
Please refer to our [installation guide](https://microsoft.github.io/agent-lightning/stable/tutorials/installation/) for more details.
49-
5052
## ⚡ Architecture
5153

5254
Agent Lightning keeps the moving parts to a minimum so you can focus on your idea, not the plumbing. Your agent continues to run as usual; you can still use any agent framework you like; you drop in the lightweight `agl.emit_xxx()` helper, or let the tracer collect every prompt, tool call, and reward. Those events become structured spans that flow into the LightningStore, a central hub that keeps tasks, resources, and traces in sync.
@@ -59,6 +61,16 @@ No rewrites, no lock-in, just a clear path from first rollout to steady improvem
5961
<img src="docs/assets/readme-architecture.svg" alt="Agent-lightning Architecture" style="width:100%"/>
6062
</p>
6163

64+
## ⚡ CI Status
65+
66+
| Workflow | Status |
67+
|----------|--------|
68+
| CPU Tests | [![tests workflow status](https://github.com/microsoft/agent-lightning/actions/workflows/tests.yml/badge.svg)](https://github.com/microsoft/agent-lightning/actions/workflows/tests.yml) |
69+
| GPU Tests | [![tests-full workflow status](https://github.com/microsoft/agent-lightning/actions/workflows/tests-full.yml/badge.svg)](https://github.com/microsoft/agent-lightning/actions/workflows/tests-full.yml) |
70+
| Examples Integration | [![examples summary workflow status](https://github.com/microsoft/agent-lightning/actions/workflows/badge-examples.yml/badge.svg)](https://github.com/microsoft/agent-lightning/actions/workflows/badge-examples.yml) |
71+
| Latest Dependency Compatibility | [![latest summary workflow status](https://github.com/microsoft/agent-lightning/actions/workflows/badge-latest.yml/badge.svg)](https://github.com/microsoft/agent-lightning/actions/workflows/badge-latest.yml) |
72+
| Legacy Examples Compatibility | [![examples compatibility workflow status](https://github.com/microsoft/agent-lightning/actions/workflows/examples-compat.yml/badge.svg)](https://github.com/microsoft/agent-lightning/actions/workflows/examples-compat.yml) |
73+
6274
## ⚡ Citation
6375

6476
If you find Agent Lightning useful in your research or projects, please cite our paper:

examples/README.md

Lines changed: 11 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -1,9 +1,14 @@
1-
## ⚡ Examples
1+
# ⚡ Examples Catalog
22

3-
README to be updated.
3+
This catalog highlights the examples shipped with Agent-lightning.
44

5-
Not completed list:
5+
| Example | Description | CI Maintenance |
6+
|---------|-------------|----------------|
7+
| [apo](./apo) | Automatic Prompt Optimization tutorials covering built-in, custom, and debugging workflows. | [![apo workflow status](https://github.com/microsoft/agent-lightning/actions/workflows/badge-apo.yml/badge.svg)](https://github.com/microsoft/agent-lightning/actions/workflows/badge-apo.yml) |
8+
| [calc_x](./calc_x) | VERL-powered math reasoning agent training that uses AutoGen with an MCP calculator tool. | [![calc_x workflow status](https://github.com/microsoft/agent-lightning/actions/workflows/badge-calc-x.yml/badge.svg)](https://github.com/microsoft/agent-lightning/actions/workflows/badge-calc-x.yml) |
9+
| [rag](./rag) | Retrieval-Augmented Generation pipeline targeting the MuSiQue dataset with Wikipedia retrieval. | **Unmaintained** — last verified with Agent-lightning v0.1.1 |
10+
| [search_r1](./search_r1) | Framework-free Search-R1 reinforcement learning training workflow with a retrieval backend. | **Unmaintained** — last verified with Agent-lightning v0.1.2 |
11+
| [spider](./spider) | Text-to-SQL reinforcement learning training on the Spider dataset using LangGraph. | [![spider workflow status](https://github.com/microsoft/agent-lightning/actions/workflows/badge-spider.yml/badge.svg)](https://github.com/microsoft/agent-lightning/actions/workflows/badge-spider.yml) |
12+
| [unsloth](./unsloth) | Supervised fine-tuning example powered by Unsloth with 4-bit quantization and LoRA. | [![unsloth workflow status](https://github.com/microsoft/agent-lightning/actions/workflows/badge-unsloth.yml/badge.svg)](https://github.com/microsoft/agent-lightning/actions/workflows/badge-unsloth.yml) |
613

7-
1. [calc_x](examples/calc_x): An agent built with AutoGen with calculator tool use, trained on Calc-X dataset with Reinforcement Learning.
8-
2. [spider](examples/spider): A write-check-rewrite looped agent with LangGraph with SQL execution; selectively optimize write and rewrite on Spider dataset with Reinforcement Learning.
9-
3. [apo](examples/apo): An example to customize an optimization algorithm: Automatic Prompt Optimization.
14+
*NOTE: CI status avoid taking any workflow running with latest dependencies into account. That's why we reference the corresponding `badge-*` workflows instead. Each example's own README also displays its `examples-*` workflow status whenever the project is maintained by CI.*

examples/apo/README.md

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,7 @@
11
# APO Example
22

3+
[![apo CI status](https://github.com/microsoft/agent-lightning/actions/workflows/examples-apo.yml/badge.svg)](https://github.com/microsoft/agent-lightning/actions/workflows/examples-apo.yml)
4+
35
This example folder contains three complementary tutorials that demonstrate different aspects of Agent-Lightning. It's compatible with Agent-lightning v0.2 or later.
46

57
## Overview

examples/calc_x/README.md

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,7 @@
11
# Calc-X Example
22

3+
[![calc_x CI status](https://github.com/microsoft/agent-lightning/actions/workflows/examples-calc-x.yml/badge.svg)](https://github.com/microsoft/agent-lightning/actions/workflows/examples-calc-x.yml)
4+
35
This example demonstrates training a mathematical reasoning agent using Agent-Lightning with the VERL algorithm and AutoGen framework. The agent solves math problems using a calculator tool through the Model Context Protocol (MCP). It's compatible with Agent-lightning v0.2 or later.
46

57
## Requirements

examples/spider/README.md

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,7 @@
11
# Spider Example
22

3+
[![spider CI status](https://github.com/microsoft/agent-lightning/actions/workflows/examples-spider.yml/badge.svg)](https://github.com/microsoft/agent-lightning/actions/workflows/examples-spider.yml)
4+
35
This example demonstrates how to train a text-to-SQL agent on the Spider dataset using Agent-Lightning with reinforcement learning. It's compatible with Agent-lightning v0.2 or later.
46

57
## Requirements

examples/unsloth/README.md

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,7 @@
11
# Unsloth SFT Example
22

3+
[![unsloth CI status](https://github.com/microsoft/agent-lightning/actions/workflows/examples-unsloth.yml/badge.svg)](https://github.com/microsoft/agent-lightning/actions/workflows/examples-unsloth.yml)
4+
35
This example demonstrates Supervised Fine-Tuning (SFT) using the Unsloth library for efficient training with 4-bit quantization and LoRA. The example trains a math-solving agent on the GSM-hard dataset. It's compatible with Agent-lightning v0.2 or later.
46

57
## Overview

mkdocs.yml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
1-
site_name: Agent Lightning
1+
site_name: Agent-lightning
22
site_url: https://microsoft.github.io/agent-lightning/
33
repo_url: https://github.com/microsoft/agent-lightning
44
repo_name: agent-lightning

pyproject.toml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,7 @@
11
[project]
22
name = "agentlightning"
33
version = "0.2.0"
4-
description = "Agent Lightning is the absolute trainer to light up AI agents."
4+
description = "Agent-lightning is the absolute trainer to light up AI agents."
55
readme = "README.md"
66
requires-python = ">=3.10"
77
dependencies = [

0 commit comments

Comments
 (0)