Search

More Filters

Show More
Add Listing
Go Back

toolkami

0
New
Multi-Agent Platforms & Frameworks
Report

Report Abuse

Basic Information

Toolkami is a minimal, Python-based AI agent framework for defining, running and iterating structured AI workflows using a small set of composable tools. The project centers on the idea of seven core tools (Ask, Browse, File, Shell plus three task-specific tools) and supports declarative workflow definitions in YAML as well as node-based visual editing for non-technical contributors. It includes a lightweight MCP server and self-executable client scripts to run agents, guidance for running in a development container, and instructions to install the UV runtime used to host the server and clients. The framework emphasizes autonomous and self-modifying agents via a Turbo mode and hot-reloading, and is compatible with OpenAI-style APIs including Anthropic. The README documents quickstart commands, environment file usage, troubleshooting tips, and an example use case implementing an AlphaEvolve-style agent.

Links

Stars
546
App URL
https://github.com/aperoc/toolkami
Github Repository
https://github.com/aperoc/toolkami/blob/main/README.md

App Details

Features
Seven minimal, composable tools designed to follow a UNIX-like philosophy for building agent capabilities. Declarative YAML workflows where steps and tools are listed and parameterized. Hands-free Turbo mode to increase autonomy by removing interactive Ask steps. Hot-reloading so code and configuration changes take effect without restarting the server. A node-based editor for building and testing prompts and workflows visually. A Python MCP server and self-executable client scripts for Gemini and OpenAI-compatible endpoints. Devcontainer support and explicit UV runtime install instructions. Built-in examples and a demo of web browsing behavior. Migration work in progress from SSE to SHTTP is noted and the README includes troubleshooting advice such as clearing content_history.json.
Use Cases
Toolkami provides a compact, opinionated foundation for teams who want to prototype or run autonomous AI agents without a large framework overhead. Its seven-tool approach reduces surface area to reason about, making it easier to compose behaviors and debug workflows. Declarative YAML plus a visual node editor lets engineers and non-engineers collaborate on prompt engineering and task orchestration. Hot-reloading and Turbo mode speed iteration and enable self-modifying experiments. Compatibility with OpenAI-style APIs and example clients for Gemini and OpenAI-compatible endpoints make it straightforward to connect models. Included quickstart commands, devcontainer, and troubleshooting notes lower onboarding friction. The README also highlights a concrete use case and a roadmap so users understand current limitations, such as guardrails being planned for future releases.

Categories

Content Creation (5042)
Monetization & Business (2246)
Development Tools (1407)
Marketing & Social Media (1403)
Education & Career (1380)
Multi-Agent Platforms & Frameworks (1009)
Health & Life (957)
AI Resources (920)
Agents & Automation (778)
Data & Analytics (764)
Productivity Tools (679)
Writing & Editing (666)

Similar Listings

listing image

virtual lab

0 (0 review)
listing image

mnemo

0 (0 review)
listing image

EdgeChains

0 (0 review)
listing image

RAG Agents Accelerator

0 (0 review)
listing image

LLM Zero to Hundred

0 (0 review)

Featured Listings

Tags

Please fill the required fields*