Step Code can be installed on macOS, Linux, or WSL

SStepFun9/22/2026, 09:57:28

Step Code can be installed on macOS, Linux, or WSL with StepFun’s bash install script. On Windows, WSL is recommended, and StepFun says PowerShell support is currently in beta.

Issues and pull requests are welcome in the Step Code repository on GitHub.

#step-code #stepfun #installation #developer-tools

View original post ↗

Previous articleEvolveTrade rewrites a trading agent's system prompt after each interval Next articleStep Code includes StepPage for one-command static site publishing

Related AI news

Step Code includes StepPage for one-command static site publishing

StepPage publishes a local static site to a shareable URL with one command, with version management and rollback built in so development, debugging, and delivery can stay in the same terminal.

SStepFun•9/22/2026, 09:49:33•

#step-code #steppage #stepfun #developer-tools

StepFun open-sources Step Code v0.1.0 under the MIT License

StepFun has released the Step Code v0.1.0 command-line tool as open source under the MIT License, including one-command static site publishing with StepPage. StepFun reports 80.9% on Terminal-Bench 2.1 and 73.3% on Multi-Frame, its 150-task long-horizon benchmark.

SStepFun•9/22/2026, 09:51:11•

#stepfun #step-code #open-source #cli #terminal-bench

StepFun open-sources terminal coding agent Step Code v0.1.0

Step Code v0.1.0 is an MIT-licensed CLI agent that reads and edits code, runs tests, and ships from one command line. StepFun reports 80.9% on Terminal-Bench 2.1 and 73.3% on Multi-Frame, its 150-task benchmark, and includes one-command publishing with StepPage.

SStepFun•9/22/2026, 09:20:44•

#step-code #stepfun #coding-agent #open-source

StepFun says it has open-sourced onPanda

StepFun says onPanda, its internal tool for LLM data annotation and model inspection, is now open source. It reports a 52% lower median annotation time than manual post-editing and on-policy fidelity of ΔPPL under 1% versus the model’s resampling baseline.

SStepFun•9/22/2026, 10:50:44•

#stepfun #onpanda #open-source #data-annotation #llm

StepFun Step 5 Preview scores 44 on Artificial Analysis Intelligence Index at $0.71 per task

StepFun highlighted Artificial Analysis results putting Step 5 Preview at 44 on the Intelligence Index and $0.71 per task, with more to come on Oct 15. The evaluation describes a 600B/27B MoE flagship with first-party API access and open weights planned for October 15.

SStepFun•9/21/2026, 20:06:22•

#stepfun #step-5-preview #artificial-analysis #llm #open-weights

Reset history AI News FAQ Email alerts RSS feeds API MCP Skill

News is compiled from public information. The data is for reference only, and this site has no affiliation with OpenAI.