Skip to content
AgentEnv Framework

Supported Agents

Supported agent = An agent AgentEnv Framework ships, ready to deploy into any environment

New to agents? Agents explains what an agent is, and Creating your own agent writes one. Every agent below runs on any sandbox provider and calls the model endpoint in [model].

Supported Agents

AgentName it as
Claude Code (default)claude-code
pipi
OpenHandsopenhands

Claude Code

tasks/q3.json
{"id": "assistant", "type": "deploy_agent", "env_ids": ["email"], "a2a_agent_id": "claude-code"}
.agentenv/config.toml
[agents]
default_a2a_agent_id = "claude-code"   # already the default

Claude Code is the default agent, so any step that doesn't name an agent deploys it. It needs a model endpoint that speaks Anthropic's API, such as a LiteLLM gateway, and the agents README covers the rest.

pi

tasks/q3.json
{"id": "assistant", "type": "deploy_agent", "env_ids": ["email"], "a2a_agent_id": "pi"}
.agentenv/config.toml
[agents]
default_a2a_agent_id = "pi"   # every step and agent judge that names no agent

pi is Earendil's open-source coding agent, and it works with any model endpoint that speaks the OpenAI API. Give it a model with [model] default, and the pi README covers the rest.

OpenHands

tasks/q3.json
{"id": "assistant", "type": "deploy_agent", "env_ids": ["email"], "a2a_agent_id": "openhands"}
.agentenv/config.toml
[agents]
default_a2a_agent_id = "openhands"   # every step and agent judge that names no agent

OpenHands is an open-source coding agent, which AgentEnv runs through the OpenHands SDK, and it calls its model through a LiteLLM endpoint. Give it a model with [model] default, and the OpenHands README covers the rest.

Last updated on

Ask a question · Report an issue

On this page