Xingyao Wang 7db0a35305 feat(runtime): Set server process to run with highest system priority (#5206) 1 year ago
..
agenthub 7e38297732 fix: correct relative links in agenthub README.md (#5170) 1 year ago
controller c9ed9b166b handle exceptions more explicitly (#4971) 1 year ago
core d08886f30e Fix non-function calls messages (#5026) 1 year ago
events f55ddbed0e fix docker leak (#4970) 1 year ago
linter 97f3249205 Move linter and diff utils to openhands-aci (#5020) 1 year ago
llm 68d1e76ccd fix: remove repeated completion assignment in llm.py (#5167) 1 year ago
memory eeb2342509 Refactor history/event stream (#3808) 1 year ago
resolver 98b2994af2 [resolver] Select a non-main branch option (#5075) 1 year ago
runtime 7db0a35305 feat(runtime): Set server process to run with highest system priority (#5206) 1 year ago
security 436ecb80a3 Logger fixes for openhands-resolver (#4710) 1 year ago
server ea6809b283 rename github to github_utils to avoid import circular dependency pro… (#5180) 1 year ago
storage 641a15356f Better AWS S3 storage support (#4195) 1 year ago
utils 97f3249205 Move linter and diff utils to openhands-aci (#5020) 1 year ago
README.md dc0a1f3940 Fix wrong doc url (#3531) 1 year ago
__init__.py 4405b109e3 Fix issue #4809: [Bug]: Model does not support image upload when usin… (#4810) 1 year ago
py.typed 6ce77e157b Fix pypi build (#3548) 1 year ago

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.