Skip to content

Latest commit

 

History

History
83 lines (58 loc) · 4.9 KB

File metadata and controls

83 lines (58 loc) · 4.9 KB

KsADK

Build agents once. Run them anywhere.

KsADK is the Agent Runtime Platform for AI agents. Keep building with Google ADK, LangGraph, LangChain, or DeepAgents, then run, debug, expose, sandbox, deploy, and observe them through one runtime experience.

简体中文 · English

Docs PyPI Ask Zread License

Real KsADK CLI screenshot: agentengine -h

30 Seconds Quick Start

python -m venv .venv
source .venv/bin/activate
pip install -U "ksadk[all]"

agentengine init demo-agent -f langgraph
cd demo-agent
agentengine config set OPENAI_API_KEY=your-api-key OPENAI_MODEL_NAME=gpt-4o-mini
agentengine run -i

Start the local debugging Web UI:

agentengine web . --no-open

Real KsADK Web UI debugging screenshot

Real local Web UI demo

Why KsADK

Most agent frameworks solve how to build agents. KsADK solves how to run, debug, deploy, and observe them.

  • Local development: agentengine init, agentengine run, agentengine web.
  • Unified debugging: browser Web UI, streaming, attachments, workspace files, tool calls, and sessions.
  • Unified protocol: local /v1/responses and /v1/chat/completions.
  • Tool boundaries: Skill Runtime, Workspace, Sandbox, Memory, Knowledge.
  • Engineering workflow: packaging, deployment, OpenTelemetry observability.

Architecture

KsADK Agent Runtime Platform architecture

Docs And Examples

Related Projects

Contributing

Issues, pull requests, samples, and documentation improvements are welcome. Before submitting, run:

make public-preflight

License: Apache-2.0.