mrh d3f569f815 修改环境变量 VSCODE_HOST 自定义 1 gadu atpakaļ
..
agenthub a2e9e206e8 Reset a failed tool call (#5666) 1 gadu atpakaļ
controller 50a0b1d91d fix llm err handling (#5958) 1 gadu atpakaļ
core f3885cadc1 Fix CLI and headless after changes to eventstream (#5949) 1 gadu atpakaļ
events f3885cadc1 Fix CLI and headless after changes to eventstream (#5949) 1 gadu atpakaļ
linter 97f3249205 Move linter and diff utils to openhands-aci (#5020) 1 gadu atpakaļ
llm a2e9e206e8 Reset a failed tool call (#5666) 1 gadu atpakaļ
memory ac5190c283 Add voyage ai embeddings (#5547) 1 gadu atpakaļ
resolver f3885cadc1 Fix CLI and headless after changes to eventstream (#5949) 1 gadu atpakaļ
runtime d3f569f815 修改环境变量 VSCODE_HOST 自定义 1 gadu atpakaļ
security 871c544b74 fix: asyncio issues with security analyzer + enable security analyzer in cli (#5356) 1 gadu atpakaļ
server 40d8245089 Fix history loading when state was corrupt/non-existent (#5946) 1 gadu atpakaļ
storage d7a3ec69d9 Refactor to make FileConversationStore more extendable (#5922) 1 gadu atpakaļ
utils e2a25f1b31 update .openhands instructions (#5821) 1 gadu atpakaļ
README.md dc0a1f3940 Fix wrong doc url (#3531) 1 gadu atpakaļ
__init__.py ceb60b9a37 Prioritize version from pyproject.toml (#5412) 1 gadu atpakaļ
py.typed 6ce77e157b Fix pypi build (#3548) 1 gadu atpakaļ

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.