Graham Neubig 178dbfaf4a Run pre-commit (#4163) 1 yıl önce
..
controller c919086e25 Fix for regression (#4075) 1 yıl önce
core 8059e8e298 make runtime url configurable (#4093) 1 yıl önce
events 5a45c648a8 attributes for BE/FE should not be sent (#4150) 1 yıl önce
linter 178dbfaf4a Run pre-commit (#4163) 1 yıl önce
llm 4eaf28d7b1 Fix ctrl c not working during startup (#4155) 1 yıl önce
memory 4eaf28d7b1 Fix ctrl c not working during startup (#4155) 1 yıl önce
runtime 178dbfaf4a Run pre-commit (#4163) 1 yıl önce
security 6487175a31 refactored all relative paths to absolute paths (#3495) 1 yıl önce
server 178dbfaf4a Run pre-commit (#4163) 1 yıl önce
storage 31dbd3d02e Fix google cloud session manager (#3942) 1 yıl önce
utils 4eaf28d7b1 Fix ctrl c not working during startup (#4155) 1 yıl önce
README.md dc0a1f3940 Fix wrong doc url (#3531) 1 yıl önce
__init__.py 34f3b61536 [runtime hash] fix runtime hash mismatch between inside `app` image and in "development mode" (#4039) 1 yıl önce
py.typed 6ce77e157b Fix pypi build (#3548) 1 yıl önce

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.