Graham Neubig 83b94786a3 docs: Update CodeAct agent documentation (#5418) преди 1 година
..
agenthub 83b94786a3 docs: Update CodeAct agent documentation (#5418) преди 1 година
controller 871c544b74 fix: asyncio issues with security analyzer + enable security analyzer in cli (#5356) преди 1 година
core 05cc6d4fc3 docs: align docstrings with Google style (#5328) преди 1 година
events 4d3b035e00 feat(agent): add BrowseURLAction to CodeAct (produce markdown from URL) (#5285) преди 1 година
linter 97f3249205 Move linter and diff utils to openhands-aci (#5020) преди 1 година
llm 794408cd31 Fix issue #5383: [Bug]: LLM Cost is added to the `metrics` twice (#5396) преди 1 година
memory eeb2342509 Refactor history/event stream (#3808) преди 1 година
resolver bf2688de7e [Resolver][Bug]: Fix success list to str representation bug (#5351) преди 1 година
runtime 3314b97cb2 Fix e2b import (#5409) преди 1 година
security 871c544b74 fix: asyncio issues with security analyzer + enable security analyzer in cli (#5356) преди 1 година
server 9aa89e8f2f Fix: Only send the last agent state changed event (#5411) преди 1 година
storage c7d89713e8 Feat socket io (#5056) преди 1 година
utils c7d89713e8 Feat socket io (#5056) преди 1 година
README.md dc0a1f3940 Fix wrong doc url (#3531) преди 1 година
__init__.py ceb60b9a37 Prioritize version from pyproject.toml (#5412) преди 1 година
py.typed 6ce77e157b Fix pypi build (#3548) преди 1 година

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.