Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
KohakuTerrarium is a general-purpose AI agent framework and batteries-included app for building, running, and composing self-contained agents and multi-agent teams, with built-in tools, sub-agents, persistent sessions, TUI, and web UI.
| Date | Stars |
|---|---|
| 2026-07-31 | 445 |
| 2026-08-03 | 447 |
| 2026-08-06 | 447 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
15.0
growth rate 0.00%/day
<p align="center">
<img src="images/banner.png" alt="KohakuTerrarium" width="800">
</p>
<p align="center">
<strong>The machine for building agents, so you stop rebuilding the machine every time you want a new one.</strong>
</p>
<p align="center">
<img src="https://img.shields.io/badge/python-3.10%2B-blue" alt="Python 3.10+">
<img src="https://img.shields.io/badge/license-KohakuTerrarium--1.0-green" alt="License">
<img src="https://img.shields.io/badge/version-2.0.0-orange" alt="Version">
</p>
<p align="center">
<strong>English</strong> · <a href="README.zh.md">繁體中文</a> · <a href="README.zh-CN.md">简体中文</a>
</p>
<p align="center">
<a href="https://terrarium.kohaku-lab.org"><strong>Documentation</strong></a>
</p>
---
## See it run (60 seconds)
```bash
pip install kohakuterrarium # install
kt login codex # authenticate a provider
kt install @kt-biome # get the official creature pack
kt run @kt-biome/creatures/swe --mode cli # run a full coding agent
```
That's an interactive shell with a complete coding agent: file tools, shell access, web search, sub-agents, resumable sessions. `Ctrl+D` exits; `kt resume --last` picks back up exactly where you stopped.
The same agent, as a library, is four lines:
```python
from kohakuterrarium import Agent
agent = await Agent.build("@kt-biome/creatures/swe")
await agent.start()
result = await agent.run("Explain what this codebase does.") # -> TurnResult
print(result.text, result.usage)
```
Want more hand-holding? [Getting Started](docs/en/guides/getting-started.md). Want to build your own? [First Creature](docs/en/tutorials/first-creature.md). Want to embed it? [Programmatic Usage](docs/en/guides/programmatic-usage.md).
## Is this for you?
**You probably want KohakuTerrarium if** you need a new agent shape and don't want to rebuild the substrate; you want strong out-of-the-box agents you can customise; you want to drive agents from your own Python (batch jobs, bots, pipelines); your requirements are still evolving.
**You probably don't if** an existing agent product (Claude Code, Codex, …) already fits your stable needs; your mental model doesn't map onto controller / tools / triggers / sub-agents / channels; you need sub-50 ms per-operation latency. More honesty at [boundaries](docs/en/concepts/boundaries.md).
## What KohakuTerrarium is
KohakuTerrarium is a framework for building agents, not another agent.
The last two years produced a striking number of agent products: Claude Code, Codex, Gemini CLI, OpenCode, OpenClaw, Hermes Agent, and many more. They are genuinely different products, and they all re-implement the same substrate from scratch: a controller loop, tool dispatch, triggers, sub-agents, sessions, persistence, multi-agent wiring. Every new agent shape costs a ground-up reimplementation of the plumbing.
KohakuTerrarium puts that substrate in one place, so the next agent shape costs a config file and a few custom modules, not a new repo.
The core abstraction is the **creature**: a standalone agent with its own controller, tools, sub-agents, triggers, memory, and I/O. Creatures are hosted by a **Terrarium** engine: a graph runtime that owns channels, lifecycle, output wiring, hot-plug, and the topology + session bookkeeping that follows graph changes. A **Studio** layer sits above that for catalog, identity, active sessions, persistence, and the web/desktop/API management surfaces. Optionally, a **Laboratory** transport layer splits host and engine across machines. Studio and Terrarium stay unchanged; a WebSocket hop is slotted in between.
Everything is Python. Agents are objects you `await`, with typed results. They embed inside your tools, your bots, your batch jobs, and even inside other agents.
For out-of-the-box creatures you can try today, see [**kt-biome**](https://github.com/Kohaku-Lab/kt-biome), the official pack of useful agents and plugins built on Excerpt of 30,922 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:23bc1a6a02c45a4c, llm:Repository topics: agent, agentic-framework, llm; description: 'general-purpose AI agent framework and batteries-included app for building, running, and composing self-contained agents and multi-agent teams, with built-in tools, sub-agents, persistent sessions, TUI, and web UI.'
matched fp:23bc1a6a02c45a4c, llm:Repository topics: agent, agentic-framework, llm; description: 'general-purpose AI agent framework and batteries-included app for building, running, and composing self-contained agents and multi-agent teams, with built-in tools, sub-agents, persistent sessions, TUI, and web UI.'
matched fp:23bc1a6a02c45a4c, llm:Repository topics: agent, agentic-framework, llm; description: 'general-purpose AI agent framework and batteries-included app for building, running, and composing self-contained agents and multi-agent teams, with built-in tools, sub-agents, persistent sessions, TUI, and web UI.'