# anomalyco/opencode

> Open source AI coding agent with terminal and desktop interfaces. Ships with a build agent (full edit and command access) and a read-only plan agent for code analysis.

- Magnitude: 3.5 out of 10 — Steady
- Stars: 209,974 total · +68 stars today, ≈ 133 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: TypeScript · License: MIT · Created: 2025-04-30 · Last push: 2026-09-25
- GitHub: https://github.com/anomalyco/opencode · Homepage: https://opencode.ai · Page: https://gitnova.dev/en/r/anomalyco/opencode

## Useful for

- Run the plan agent to explore an unfamiliar codebase without file edits
- Use the build agent to make code changes and run commands in a project
- Invoke the @general subagent for complex multi-step searches across a repository

## Why it’s here

- 68 stars so far today, about 133 expected by the end of the day.
- GitHub Trending TypeScript today: #13, +198 stars.
- About 64 forks a day — people are taking the code.

## 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: 27,758
- Issues and pull requests: 50,669
- Watchers: 814
- Average over the last week: 248 per day
- Usual pace: 322 per day
- Stars in the last hour (measured): 13
- Latest release: v1.18.32 (2026-09-21)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-08-27 … 2026-09-25: 260, 259, 223, 251, 285, 247, 241, 308, 656, 570, 642, 354, 307, 251, 353, 269, 200, 249, 289, 306, 290, 305, 259, 252, 278, 296, 317, 254, 209, 68

## Spotted in now

- GitHub Trending TypeScript today: #13, +198 stars

## Similar by description

1. **anthropics/claude-code** — 3.5 · Cooling · AI agents · TypeScript · +39 stars today, ≈ 86 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
2. **xai-org/grok-build** — 2.3 · Steady · AI agents · Rust · +12 stars today, ≈ 22 by evening
   SpaceXAI's terminal-based AI coding agent: a fullscreen TUI that understands your codebase, edits files, runs shell commands, searches the web, and manages long-running tasks — interactively, headlessly, or via ACP in editors.
   Full card: https://gitnova.dev/en/r/xai-org/grok-build.md
3. **XiaomiMiMo/MiMo-Code** — 1.9 · Steady · AI agents · TypeScript · +5 stars today, ≈ 11 by evening
   Xiaomi's terminal-native AI coding assistant: reads and writes code, runs commands, manages Git, and keeps persistent project memory across sessions. Supports connecting to any mainstream LLM provider.
   Full card: https://gitnova.dev/en/r/XiaomiMiMo/MiMo-Code.md
4. **openai/codex** — 3.8 · Steady · AI agents · Rust · +63 stars today, ≈ 115 by evening
   A local coding agent from OpenAI that runs in the terminal: installed with one command and used as a CLI tool for working with code.
   Full card: https://gitnova.dev/en/r/openai/codex.md
5. **mukundzha/hazzel** — 0.4 · Quiet · AI agents · Python · +0 stars today, ≈ 0 by evening
   A small Python terminal coding agent that reads code, edits files, runs commands and works with git, asking for approval before every change. It works with any provider via your own API key or a local Ollama model.
   Full card: https://gitnova.dev/en/r/mukundzha/hazzel.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 2026-09-25 13:57 UTC, updated every 30 minutes.