cavekit

Repository facts

Stars

1,156

Forks

90

Open issues and pull requests

18

Primary language

Not detected

License

MIT License (MIT)

Owner

JuliusBrussee · Personal account

Created

Mar 14, 2026

Last push

Aug 14, 2026

Topics

• claude-code
• parallel-agents
• skills
• spec-driven-development
• test-driven-development

Rank #5,554 of 9,507 in AI on GitHub, by stars. Data from the GitHub API, fetched Oct 18, 2026; star counts change daily. Stars measure popularity, not quality or safety, and a listing is not an endorsement. How this list is made

Related projects

Projects that share this one’s GitHub topics.

• 3,531

  Rank 3,531: maxritter/pilot-shell

  Professional context and harness engineering for Claude Code and OpenAI Codex. Build production-grade software with spec-driven development, TDD, persistent memory, quality gates,…

  2,094 starsJavaScriptOther licenseLast push Oct 18, 2026

• 606

  Rank 606: OrchestratorInc/agent-orchestrator

  Run and supervise teams of coding agents from planning to merge. Any harness (Claude code, codex, +25 more). Desktop, web, mobile, and cloud agents.

  13,324 starsGoApache-2.0Last push Oct 18, 2026

• 3,988

  Rank 3,988: zhnt/loushang

  AI-native agent harness for coding workflows by python: multi-model LLM orchestration, stateful sessions, tool governance, traceable delivery, and provider routing for GPT, Claude…

  1,797 starsPythonApache-2.0Last push Oct 18, 2026

• 6,154

  Rank 6,154: zhu1090093659/spec_driven_develop

  Spec-driven development workflow for AI coding agents: architecture-first planning, task decomposition, GitHub Issue/PR tracking, Deep Discuss, and adaptive control for Claude Cod…

  990 starsShellMITLast push Jul 26, 2026

• 6,703

  Rank 6,703: MageByte-Zero/spec-superflow

  源码级融合 OpenSpec 规划引擎 + Superpowers 执行纪律的 AI 编程工作流插件。17 平台支持，9 skills，Spec-first，契约驱动。

  867 starsJavaScriptMITLast push Oct 1, 2026

• 7,374

  Rank 7,374: AmazingAng/old-coder

  An old coder's strategy for the agent era: don't read the code — make it run the gauntlet. Evidence-first development skill for coding agents, inspired by Uncle Bob.

  753 starsPythonMITLast push Aug 18, 2026