Starstruk Logo MarkStarstruk

python_1.1.0

agent0ai/agent-zeropython_1.1.0Jul 1, 2026by cornelcroi

AI Summary

Adds the same anti-hallucination `GroundedAgent` pattern to the Python SDK, ensuring LLM responses are strictly based on curated tool outputs.

Key Highlights

  • Two-LLM architecture to prevent hallucinations.
  • Separation of tool execution (gatherer) and response generation (presenter).
  • Support for custom output curators.
  • Includes runnable chatbot example.

New Features

  • GroundedAgent class
  • GroundedAgentOptions interface
  • ToolOutputCurator (DataBlockCurator, PerToolCurator)
  • PresenterPrompt type
  • Grounded Agent documentation

Full Release Notes

## GroundedAgent (two-LLM anti-hallucination pattern)

Adds `GroundedAgent`: a gatherer LLM calls tools and sees the raw results but never speaks; an isolated presenter LLM writes the reply from **only** the curated tool output, so it can't invent values beyond what was fetched. A no-tool turn is answered by the gatherer directly, skipping the presenter.

- `GroundedAgent` / `GroundedAgentOptions`, `ToolOutputCurator` (`DataBlockCurator`, `PerToolCurator`), `PresenterPrompt`
- Docs: Built-in Agents → Grounded Agent
- Runnable example: `examples/grounded-agent-chatbot`

Feature merged in #551.