ToolKami - Simple Agents Made Easy
ToolKami is an open sourced "simple" framework with conceptually clear, independant parts that allows you to build and work seamlessly with AI agents. It comes with a Command Line Interface and curated Tools.
Command Line Interface (CLI)
toolkami CLI is a modified version of 's CEO Tobias try implementation. It extends the implementation with sandboxing capabilities and designed with functional core, imperative shell in mind.
Usage
NOTE: tk an alias of toolkami is available too.
Commands:
toolkami init [PATH]: Generate shell functiontoolkami cd [QUERY]: Interactive selectortoolkami wt [NAME]: Create worktree from current repomerge: Merge worktree changes back to parent repodrop: Delete worktree and branch
toolkami sb: Run Docker sandbox from .toolkami/docker-compose.ymlbuild [--no-cache]: Build service image (pass Docker Compose flags like--no-cache)exec [CMD...]: Exec into the sandbox container (defaults to interactivebash)
It is designed to support multiple, concurrent agent workflows:
Installation
curl -sL https://raw.githubusercontent.com/aperoc/toolkami/refs/heads/main/toolkami.rb > ~/.local/toolkami.rb # Make "try" executable so it can be run directly chmod +x ~/.local/toolkami.rb # Add to your shell (bash/zsh) echo >> ~/.zshrc # add new line echo 'eval "$(ruby ~/.local/toolkami.rb init)"' >> ~/.zshrc
Framework
ToolKami's framework let deterministic tools and dynamic agents to work together seamlessly. It is designed on the premise of simplicity, composability and extensibility that scales nicely with LLM's increasing capability.
All the MCP servers can be distributed as a single file binary, thanks to UV script.
I have elaborated on default File and Shell tool in this blog post, along with what can be improved.
Installation
# Install UV ## OSX/Linux curl -LsSf https://astral.sh/uv/install.sh | sh ## Windows powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex" # Start the MCP server `./servers/__main__.py`
Use Cases
Google's AlphaEvolve: ToolKami style
A minimal implementation of AlphaEvolve using this framework with detailed writeup and code.
(Credits to https://deepmind.google/discover/blog/alphaevolve-a-gemini-powered-coding-agent-for-designing-advanced-algorithms/)


