Engel Nyst e6847e9e61 Move agenthub within openhands (#4130) 1 年之前
..
agenthub e6847e9e61 Move agenthub within openhands (#4130) 1 年之前
controller c919086e25 Fix for regression (#4075) 1 年之前
core e6847e9e61 Move agenthub within openhands (#4130) 1 年之前
events 9d0e6a24bc Refactor embeddings (#4219) 1 年之前
linter 178dbfaf4a Run pre-commit (#4163) 1 年之前
llm 8c32ef2234 Fix to use async variant of completion (#4228) 1 年之前
memory 9d0e6a24bc Refactor embeddings (#4219) 1 年之前
runtime 9c07370559 fix runtime_startup_env_vars not being used (#4250) 1 年之前
security 6487175a31 refactored all relative paths to absolute paths (#3495) 1 年之前
server e6847e9e61 Move agenthub within openhands (#4130) 1 年之前
storage 641a15356f Better AWS S3 storage support (#4195) 1 年之前
utils 9d0e6a24bc Refactor embeddings (#4219) 1 年之前
README.md dc0a1f3940 Fix wrong doc url (#3531) 1 年之前
__init__.py 34f3b61536 [runtime hash] fix runtime hash mismatch between inside `app` image and in "development mode" (#4039) 1 年之前
py.typed 6ce77e157b Fix pypi build (#3548) 1 年之前

README.md

OpenHands Architecture

This directory contains the core components of OpenHands.

This diagram provides an overview of the roles of each component and how they communicate and collaborate. OpenHands System Architecture Diagram (July 4, 2024)

Classes

The key classes in OpenHands are:

  • LLM: brokers all interactions with large language models. Works with any underlying completion model, thanks to LiteLLM.
  • Agent: responsible for looking at the current State, and producing an Action that moves one step closer toward the end-goal.
  • AgentController: initializes the Agent, manages State, and drive the main loop that pushes the Agent forward, step by step
  • State: represents the current state of the Agent's task. Includes things like the current step, a history of recent events, the Agent's long-term plan, etc
  • EventStream: a central hub for Events, where any component can publish Events, or listen for Events published by other components
    • Event: an Action or Observeration
      • Action: represents a request to e.g. edit a file, run a command, or send a message
      • Observation: represents information collected from the environment, e.g. file contents or command output
  • Runtime: responsible for performing Actions, and sending back Observations
    • Sandbox: the part of the runtime responsible for running commands, e.g. inside of Docker
  • Server: brokers OpenHands sessions over HTTP, e.g. to drive the frontend
    • Session: holds a single EventStream, a single AgentController, and a single Runtime. Generally represents a single task (but potentially including several user prompts)
    • SessionManager: keeps a list of active sessions, and ensures requests are routed to the correct Session

Control Flow

Here's the basic loop (in pseudocode) that drives agents.

while True:
  prompt = agent.generate_prompt(state)
  response = llm.completion(prompt)
  action = agent.parse_response(response)
  observation = runtime.run(action)
  state = state.update(action, observation)

In reality, most of this is achieved through message passing, via the EventStream. The EventStream serves as the backbone for all communication in OpenHands.

flowchart LR
  Agent--Actions-->AgentController
  AgentController--State-->Agent
  AgentController--Actions-->EventStream
  EventStream--Observations-->AgentController
  Runtime--Observations-->EventStream
  EventStream--Actions-->Runtime
  Frontend--Actions-->EventStream

Runtime

Please refer to the documentation to learn more about Runtime.