Robert Brennan 642e962f89 randomize branch names (#5784) 1 jaar geleden
..
agenthub 642e962f89 randomize branch names (#5784) 1 jaar geleden
controller e9cafb0372 chore: Cleanup runtime exception handling (#5696) 1 jaar geleden
core faf8b5829c Fix for dying sessions/runtimes (#5755) 1 jaar geleden
events d646b2089d Fix several async lockups (#5734) 1 jaar geleden
linter 97f3249205 Move linter and diff utils to openhands-aci (#5020) 1 jaar geleden
llm 4a8bf3d2d0 Fix not initialized response latencies (#5679) 1 jaar geleden
memory ac5190c283 Add voyage ai embeddings (#5547) 1 jaar geleden
resolver 725e71ad22 Update Slack links again (#5773) 1 jaar geleden
runtime 642e962f89 randomize branch names (#5784) 1 jaar geleden
security 871c544b74 fix: asyncio issues with security analyzer + enable security analyzer in cli (#5356) 1 jaar geleden
server f9cc0bce53 Fix connection check (#5787) 1 jaar geleden
storage faf8b5829c Fix for dying sessions/runtimes (#5755) 1 jaar geleden
utils 2fb45d410d Fix: Making the logs quieter (#5525) 1 jaar geleden
README.md dc0a1f3940 Fix wrong doc url (#3531) 1 jaar geleden
__init__.py ceb60b9a37 Prioritize version from pyproject.toml (#5412) 1 jaar geleden
py.typed 6ce77e157b Fix pypi build (#3548) 1 jaar geleden

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.