Robert Brennan e21abce786 Load GitHub users list at startup for improved authentication performance (#4567) 1 год назад
..
agenthub 997dc80d18 chance default model to 3.5 sonnet new (#4612) 1 год назад
controller 30eeaa641c Major logging overhaul (#4563) 1 год назад
core 997dc80d18 chance default model to 3.5 sonnet new (#4612) 1 год назад
events ae13171194 feat(agent): CodeAct with function calling (#4537) 1 год назад
linter ec3152b6e1 linter: only lint on updated lines in the new file (#4409) 1 год назад
llm 572b3ad682 safer model info access (#4619) 1 год назад
memory da23189e4c refactor: move get_pairs from memory to shared utils (#4411) 1 год назад
runtime d50425865a fix(runtime): only accept one request at a time for exec action requests (#4589) 1 год назад
security 30eeaa641c Major logging overhaul (#4563) 1 год назад
server e21abce786 Load GitHub users list at startup for improved authentication performance (#4567) 1 год назад
storage 641a15356f Better AWS S3 storage support (#4195) 1 год назад
utils 30eeaa641c Major logging overhaul (#4563) 1 год назад
README.md dc0a1f3940 Fix wrong doc url (#3531) 1 год назад
__init__.py 568c8ce993 Runtime build fixes for OpenHands as a python library (#3989) 1 год назад
py.typed 6ce77e157b Fix pypi build (#3548) 1 год назад

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.