bf793c7ae0bff9488fa8b6271663adae70425831
Agent source in examples/agents/python/ is pure code — reusable templates. Each PoC owns its Dockerfile since it may include data, tools, extra deps.
Agl-lite: A Minimal Workable Version of Agent Lightning
This project agl-lite which is a minimal workable version of the popular agentic rl project Agent Lightning (https://github.com/microsoft/agent-lightning).
here are some key changes:
- remove the dependency of
litellmand build self-owned request gateway instead; - remove the dependency of
OpenTelemetryand the whole stack built upon it, such as the tracers of agents; instead, use gateway to collect request-response data during transfer and record them into data store; - following (2), the organization of data is not based on span in opentelemetry, instead, the basic trajectory format is sequence of requests (with response);
- use
kubenetesas the default agent runner (minikubefor single machine), and move the retry control from data store to k8s controller, and simplify the rollout states
Instruction for Coding Agents
The architecture of agl-lite is described in the high-level architecture design doc in docs/design/0_architecture.md, you should read it to get the overall picture of the system. Since the document is quite long, you should first read the TOC by greping ## in the markdown file, and then read the sections you are interested in.
There are some local environment setup and configuration needed for this project refactoring in .local/.
Description
用于快速构建 AI Agent 的训练工具。|GitHub 镜像 ⭐ 17.7k · 🍴 1.6k
https://github.com/microsoft/agent-lightning
Readme
MIT
56 MiB
Languages
Python
98.1%
Shell
1.9%