tobitege 8fcf0817d4 (eval) Aider_bench: add eval_ids arg to run specific instance id's (#3592) vor 1 Jahr
..
controller 11d8d05b1a [Fix] Metrics should be updated when agent reaches max iterations. (#3549) vor 1 Jahr
core 8fcf0817d4 (eval) Aider_bench: add eval_ids arg to run specific instance id's (#3592) vor 1 Jahr
events 6487175a31 refactored all relative paths to absolute paths (#3495) vor 1 Jahr
llm 01ae22ef57 Rename OpenDevin to OpenHands (#3472) vor 1 Jahr
memory 6487175a31 refactored all relative paths to absolute paths (#3495) vor 1 Jahr
runtime 6ce77e157b Fix pypi build (#3548) vor 1 Jahr
security 6487175a31 refactored all relative paths to absolute paths (#3495) vor 1 Jahr
server 6487175a31 refactored all relative paths to absolute paths (#3495) vor 1 Jahr
storage 8c4c3b18b5 Feat google cloud storage (#3574) vor 1 Jahr
utils 01ae22ef57 Rename OpenDevin to OpenHands (#3472) vor 1 Jahr
README.md dc0a1f3940 Fix wrong doc url (#3531) vor 1 Jahr
__init__.py 01ae22ef57 Rename OpenDevin to OpenHands (#3472) vor 1 Jahr
py.typed 6ce77e157b Fix pypi build (#3548) vor 1 Jahr

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.