Overview
mamba-architecture is an open-source productivity skill for Claude Code and compatible agents, published by Orchestra-Research. Its author describes it as: “State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and Mamba-2 (d_state=128, multi-…”. The project has 12k stars on GitHub and is available under the MIT license. Add it to your setup with `/plugin marketplace add Orchestra-Research/AI-Research-SKILLs`.
What mamba-architecture does
Mamba is a state-space model architecture achieving O(n) linear complexity for sequence modeling.
What’s inside
The SKILL.md for mamba-architecture is organised into these sections:
- Quick start
- Common workflows
- Workflow 1: Language model with Mamba-2
- Workflow 2: Use pretrained Mamba models
- Workflow 3: Mamba-1 vs Mamba-2
- Workflow 4: Benchmark vs Transformers
- When to use vs alternatives
- Common issues
- Advanced topics
- Hardware requirements
- Resources
Installation
Add mamba-architecture to your agent with:
/plugin marketplace add Orchestra-Research/AI-Research-SKILLsReview a skill’s source before installing it — skills can instruct your agent to run commands. This command comes from the skill’s public repository, which is the source of truth for setup steps. New to skills? Read how to install Claude Code skills.
Supported agents
- Claude Code — ships a claude code plugin marketplace
- Codex — declared in the repository topics
License
mamba-architecture is published under the MIT license.
Strengths
- Clear MIT license — safe to read and adapt within its terms
- Ships in Orchestra-Research/AI-Research-SKILLs, an established project with 11,807 GitHub stars
- Works with Claude Code, Codex
Author
Topics
Frequently asked questions
- What does mamba-architecture do?
- State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and Mamba-2 (d_state=128, multi-head). Models 130M-2.8B on HuggingFace.
- How do I install mamba-architecture?
- Run /plugin marketplace add Orchestra-Research/AI-Research-SKILLs in your agent, then reload your skills. Review the source at https://github.com/Orchestra-Research/AI-Research-SKILLs before installing.
- Is mamba-architecture free to use?
- Yes. mamba-architecture is free and open source under the MIT license, so you can read, run, and adapt it within that license's terms.
- Which agents does mamba-architecture work with?
- mamba-architecture lists Claude Code and Codex — named in its SKILL.md, its plugin marketplace or its repository topics. Skills use the portable SKILL.md format, so other agents that read that format may load it too.
- Where does mamba-architecture come from?
- mamba-architecture ships inside Orchestra-Research/AI-Research-SKILLs, a repository that contains 41 catalogued skills in total. The repository's 11,807 GitHub stars apply to that whole collection, not to this skill on its own.