Xingyao Wang 24117143ae feat(llm): add new haiku into func calling support model (#4738) 1 éve
..
agenthub 1d2a616be7 Fix issue #4739: '[Bug]: The agent doesn'"'"'t know its name' (#4740) 1 éve
controller 1638968509 History microfixes (#4728) 1 éve
core 966da7b7c8 feat(agent, CodeAct 2.2): native CodeAct support for Browsing (#4667) 1 éve
events 966da7b7c8 feat(agent, CodeAct 2.2): native CodeAct support for Browsing (#4667) 1 éve
linter ec3152b6e1 linter: only lint on updated lines in the new file (#4409) 1 éve
llm 24117143ae feat(llm): add new haiku into func calling support model (#4738) 1 éve
memory 1638968509 History microfixes (#4728) 1 éve
runtime 1d2a616be7 Fix issue #4739: '[Bug]: The agent doesn'"'"'t know its name' (#4740) 1 éve
security 0687608feb [Arch proposal] ENVIRONMENT event source (#4584) 1 éve
server 1d2a616be7 Fix issue #4739: '[Bug]: The agent doesn'"'"'t know its name' (#4740) 1 éve
storage 641a15356f Better AWS S3 storage support (#4195) 1 éve
utils 30eeaa641c Major logging overhaul (#4563) 1 éve
README.md dc0a1f3940 Fix wrong doc url (#3531) 1 éve
__init__.py 568c8ce993 Runtime build fixes for OpenHands as a python library (#3989) 1 éve
py.typed 6ce77e157b Fix pypi build (#3548) 1 éve

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.