0.11.0

What's Changed

• Python Implementation of HF "tiny-agent" by @njbrake in #168

from any_agent import AnyAgent, AgentConfig
from any_agent.config import MCPStdioParams

agent = AnyAgent.create(
    "tinyagent",
    AgentConfig(
        model_id="gpt-4.1-nano",
        instructions="You must use the available tools to find an answer",
        tools=[
            MCPStdioParams(
                command="uvx",
                args=["duckduckgo-mcp-server"]
            )
        ]
    )
)

result = agent.run(
    "Which Agent Framework is the best??"
)
print(result.final_output)

• feat: initial test refactor for google and agno mcp servers by @ELC in #153
• Update pre-commit-update permissions by @daavoo in #170
• fix(docs): Use python in code blocks to enusre mktestdocs runs. by @daavoo in #173
• Tracing as a class by @njbrake in #174
• MCP tools were missing schema by @njbrake in #179
• Add TinyAgent to docs by @njbrake in #181
• Consistent return no matter which agent framework by @njbrake in #177
• TinyAgent does not support multi-agents (because then it's not tiny) by @njbrake in #182
• pre-commit autoupdate by @github-actions in #188
• AgentResults contains token cost and usage, when available by @njbrake in #183
• Upgrade google-adk min version by @njbrake in #190
• docs: Create agents page. Add separate page for each framework. by @daavoo in #191
• feat: Support agent_type and model_type in every framework. by @daavoo in #192
• docs(tinyagent): Add example with mcp. by @daavoo in #193

Full Changelog: 0.10.0...0.11.0