by cohere-ai · Agent Tool · ★ 312
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
⚠️ No longer maintained: This repository is archived and no longer supported. If you wish to continue development, please fork the project. Terrarium - A Simple Python Sandbox Terrarium is a relatively low latency, easy to use, and economical Python sandbox - to be used as a docker deployed container, for example in GCP Cloud Run - for executing untrusted user or LLM generated code. Terrarium is fast: 900ms runtime to generate a 200 dpi png with a simple matplotlib barchart - 500 ms for a svg version. (hosted on GCP Cloud Run) Terrarium is cheap: We spent less than $30 a month hosting terrarium on GCP during internal annotations (2GB mem + 1vCPU and at least 1 alive instance + autoscale on demand) Terrarium is fully compartmentalized: The sandbox gets completely recycled after every invocation. No state whatsoever is carried over between calls. Cohere does not give any guarantees for the sandbox integrity. Terrarium supports native input & output files: You can send any number & type of files as part of the request and we put it them in the python filesystem. After the code execution we gather up all generated files and return them with the response.
| Stars | 312 |
| Forks | 56 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 56.006/100 |
| Open Issues | 8 |
| Last Updated | 2026-04-22 |
| Created | 2024-04-24 |
| Platforms | python |
| Est. Tokens | ~20k |
Looking for a cohere-terrarium alternative? If you're comparing cohere-terrarium with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
A fully-featured, GUI-powered local LLM Agent sandbox with complete MCP protocol support. Features both CLI
An Execution Isolation Architecture for LLM-Based Agentic Systems
[GenAI Application Development Framework] 🚀 Build GenAI application quick and easy 💬 Easy to interact with
Sandbox your local AI agents so they can read/write only what they need
Agentic-RAG explores advanced Retrieval-Augmented Generation systems enhanced with AI LLM agents.
The LLM Anti-Framework
Explore other popular agent tool tools:
cohere-terrarium is A simple Python sandbox for helpful LLM data agents. It is categorized as a Agent Tool with 312 GitHub stars.
cohere-terrarium is primarily written in Python. It covers topics such as code-interpreter, llm-agent, sandbox.
You can find installation instructions and usage details in the cohere-terrarium GitHub repository at github.com/cohere-ai/cohere-terrarium. The project has 312 stars and 56 forks, indicating an active community.
cohere-terrarium is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to cohere-terrarium on Agent Skills Hub include EdgeBox, SecGPT, Agently. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.