Modular Multi-Agent System for Scientific Research Assistance
关键参数与规格
关键参数与规格
参数
值
语言
Ruby
类别
AI Engineering
子类别
Give agent tools,Build agent workflow (SDK)
星标数
615
分叉数
32
贡献者
1
创建日期
2025-05-06
更新日期
2026-09-23
1 天星标数
0
7 天星标数
0
排名
16,041
上次排名
15,840
排名变化
-201
7 天星标排名
15,314
上次 7 天星标排名
15,327
7 天星标排名变化
13
总星标排名
16,460
上次总星标排名
16,434
总星标排名变化
-26
国家
Singapore
README 摘录
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) 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: an alias of is available too. Commands: : Generate shell
function : Interactive selector : Create worktree from current repo : Merge worktree changes back to parent repo : Delete worktree and branch : Run Docker sandbox from . yml : Build service image (pass Docker Compose flags like ) : Exec into the sandbox container (defaults to interactive ) It is designed to support multiple, concurrent agent workflows: Installation 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 Use Cases Google's AlphaEvolve: ToolKami style A minimal implementation of AlphaEvolve using this framework with detailed writeup and code. (Credits to Social Website Blog Twitter toolkami@aperoc.
常见问题
记录了多少星标和分叉？
aperoc/toolkami 有 615 个星标和 32 个分叉。
仓库排名是多少？
aperoc/toolkami 排名第 16,041。
记录的语言和类别是什么？
aperoc/toolkami 有 615 个星标，语言为 Ruby，类别为 AI Engineering。
toolkami wt [NAME]: Create worktree from current repo
merge: Merge worktree changes back to parent repo
drop: Delete worktree and branch
toolkami sb: Run Docker sandbox from .toolkami/docker-compose.yml
build [--no-cache]: Build service image (pass Docker Compose flags like --no-cache)
exec [CMD...]: Exec into the sandbox container (defaults to interactive bash)
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.
(Credits to https://deepmind.google/discover/blog/alphaevolve-a-gemini-powered-coding-agent-for-designing-advanced-algorithms/)