by gradion-ai
Agent harness and CLI tool that acts and self-improves via code actions
# Add to your Claude Code skills
git clone https://github.com/gradion-ai/freeactFreeact is a lightweight agent harness and CLI tool that acts by executing Python code and shell commands. Code actions are key for an agent to improve itself and its tool library.
It generates Python APIs for MCP servers and calls their tools programmatically ("code mode") instead of JSON. This enables tool composition in code actions in a single inference pass.
Freeact has a tiny core and uses sandboxed IPython kernels to execute both Python code and shell commands in a uniform way. Execution runs locally with fine-grained approval of actions.
[!NOTE] Supported models: Freeact supports any model compatible with Pydantic AI, with
gemini-3-flash-previewas the default. See Models for provider configuration and examples.
No comments yet. Be the first to share your thoughts!
| Capability | Description | |---|---| | Code actions | Freeact agents act via Python code and shell commands. This enables tool composition and intermediate result processing in a single LLM inference pass. | | Local execution | Freeact executes code and shell commands locally in an IPython kernel provided by ipybox. Data, configuration and generated tools live in local workspaces. | | Sandbox mode | IPython kernels optionally run in a sandbox environment based on Anthropic's sandbox-runtime. It enforces filesystem and network restrictions on OS-level. | | MCP code mode | Freeact calls MCP server tools programmatically<sup>1)</sup> via generated Python APIs. This enables composition of tool calls in code actions with much lower latency. | | **Tool discover...