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.
Fast, Sharp & Reliable Agentic Intelligence
| Date | Stars |
|---|---|
| 2026-07-31 | 2093 |
| 2026-08-02 | 2093 |
| 2026-08-06 | 2093 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<!-- ---
license: apache-2.0
base_model:
- stepfun-ai/step-3.5-flash
--- -->
<div align="center">
<h1 style="margin: 0; border-bottom: none;"> <img src="assets/stepfun-1.png" width="25" style="margin-right: 10px;"/> Step 3.5 Flash</h1>
</div>
<p align="center">
<strong>English</strong> | <a href="README.zh-CN.md">简体中文</a>
</p>
<p align="center">
<a href="./cookbooks/openclaw">OpenClaw Guide</a> | <a href="./cookbooks/claude-code-best-practices/README.en.md">Claude Code Guide</a> | <a href="./cookbooks/roo-code-integration-guide">Roo Code Guide</a> | <a href="./cookbooks/hybrid-local-agent-macos">Local Agent Guide</a>
</p>
[](https://huggingface.co/stepfun-ai/Step-3.5-Flash/tree/main)
[](https://modelscope.cn/models/stepfun-ai/Step-3.5-Flash)
[](https://discord.gg/RcMJhNVAQc)
[](https://arxiv.org/pdf/2602.10604)
[](https://static.stepfun.com/blog/step-3.5-flash/)
[]()
[](https://openrouter.ai/chat?models=stepfun/step-3.5-flash:free)
[](https://huggingface.co/spaces/stepfun-ai/Step-3.5-Flash)
[](./cookbooks/openclaw)
</div>
## 1. Introduction
**Step 3.5 Flash** ([visit website](https://static.stepfun.com/blog/step-3.5-flash/)) is our most capable open-source foundation model, engineered to deliver frontier reasoning and agentic capabilities with exceptional efficiency. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token. This "intelligence density" allows it to rival the reasoning depth of top-tier proprietary models, while maintaining the agility required for real-time interaction.
### Contents
- [Key Capabilities](#2-key-capabilities)
- [Performance](#3-performance)
- [Architecture Details](#4-architecture-details)
- [Quick Start](#5-quick-start)
- [Local Deployment](#6-local-deployment)
- [Using Step 3.5 Flash on Agent Platforms](#7-using-step-35-flash-on-agent-platforms)
- [Cookbooks](#8-cookbooks)
- [Known Issues and Future Directions](#9-known-issues-and-future-directions)
- [Co-Developing the Future](#10-co-developing-the-future)
- [License](#license)
## 2. Key Capabilities
- **Deep Reasoning at Speed**: While chatbots are built for reading, agents must reason fast. Powered by 3-way Multi-Token Prediction (MTP-3), Step 3.5 Flash achieves a generation throughput of **100–300 tok/s** in typical usage (peaking at **350 tok/s** for single-stream coding tasks). This allows for complex, multi-step reasoning chains with immediate responsiveness.
- **A Robust Engine for Coding & Agents**: Step 3.5 Flash is purpose-built for agentic tasks, integrating a scalable RL framework that drives consistent self-improvement. It achieves **74.4% on SWE-bench Verified** and **51.0% on Terminal-Bench 2.0**, proving its ability to handle sophisticated, long-horizon tasks with unwavering stability.
- **Efficient Long Context**: The model supports a cost-efficient **256K context window** by employing a 3:1 Sliding Window Attention (SWA) ratio—integrating three SWA layers for every full-attention layer. This hybrid approach ensures consistent performance across massive datasets or long codebExcerpt of 22,712 characters
Read on GitHub
56
18
5
Sizhou Chen · China
3
3
hzwer · @stepfun-ai
2
2
2
1
Elliott Zheng
1
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:df6b6b6cbb40b275, desc:agentic