# stepfun-ai/Step-Code > A TypeScript terminal coding agent that reads code, makes changes and runs tests, works with Step models, and supports MCP, Agent Skills, plugins and static site publishing. - Magnitude: 4.4 out of 10 — Early signal - Stars: 386 total · +5 stars today, ≈ 18 by evening - Star trust: star growth looks organic - Category: AI agents · Language: TypeScript · License: MIT · Created: 2026-06-01 · Last push: 2026-09-24 - GitHub: https://github.com/stepfun-ai/Step-Code · Page: https://gitnova.dev/en/r/stepfun-ai/Step-Code ## Useful for - Run step in a project and ask it to explain the stack and directory layout without edits - Generate AGENTS.md via /init to document the project - Delegate a long-running task with /goal and track progress in the status line ## Why it’s here - 5 stars so far today, about 18 expected by the end of the day. The usual pace is 0 per day, so that's 18× as much. - Before this, the repository barely got any stars — about 1 per day. - The spike has held for 3 days in a row — not a one-off blip. - GitHub Trending TypeScript today: #11, +37 stars. - About 11 forks a day — people are taking the code. - Recent forks include notable developers: @jasonkneen (439 followers). ## Star trust Star growth looks organic. Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer. ## Numbers - Forks: 40 - Issues and pull requests: 188 - Watchers: 3 - Average over the last week: 56 per day - Usual pace: 0 per day - Stars in the last hour (measured): 0 ## Stars per day, last 30 days (oldest → newest, today is partial) 2026-08-26 … 2026-09-24: 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 7, 317, 53, 5 ## Spotted in now - GitHub Trending TypeScript today: #11, +37 stars ## Similar by description 1. **cline/cline** — 2.8 · Steady · AI agents · TypeScript · +22 stars today, ≈ 52 by evening Open-source coding agent available as an SDK, IDE extension, CLI, or desktop app: reads your project, edits code, runs commands and tests with human-in-the-loop approval. Full card: https://gitnova.dev/en/r/cline/cline.md 2. **MoonshotAI/kimi-code** — 2.3 · Steady · AI agents · TypeScript · +14 stars today, ≈ 26 by evening Kimi Code CLI is a terminal AI coding agent that reads and edits code, runs shell commands, searches files and fetches web pages, using Kimi models or other compatible providers. Full card: https://gitnova.dev/en/r/MoonshotAI/kimi-code.md 3. **anthropics/claude-code** — 3.7 · Steady · AI agents · TypeScript · +66 stars today, ≈ 128 by evening An agentic coding tool that lives in the terminal: it understands your codebase, executes routine tasks, explains complex code, and handles git workflows via natural language commands. Full card: https://gitnova.dev/en/r/anthropics/claude-code.md 4. **jarrodwatts/claude-hud** — 1.7 · Steady · AI agents · JavaScript · +2 stars today, ≈ 8 by evening A Claude Code plugin that displays session state right below the input line: context window usage, active tools, running subagents, and todo progress. It uses Claude Code's native statusline API, with no tmux or separate windows. Full card: https://gitnova.dev/en/r/jarrodwatts/claude-hud.md --- Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score. Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast. Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself. Data as of 2026-09-24 13:15 UTC, updated every 30 minutes.