โŒจ๏ธ cli toolActivePromisinghigh

terminaI

by Prof-Harita

Open-source, local-first alternative to Cowork-style computer assistants: real PTY terminal ops, explicit approvals, JSONL audit logs. Windows + Linux + macOS. Model agnostic.

Stars

414

Skill Type

๐Ÿงช Product Verification

Quality Score

104/200

License

Apache-2.0

Forks

38

Last Updated

Jun 11, 2026

Discovered

Mar 25, 2026

Validation

Passed

github.com/Prof-Harita/terminaI

Quality Breakdown

104/ 200

Content Signals

โ—‹Gotchas/Edge Cases+40
โœ“Progressive Disclosure+30
โ—‹Trigger Description+20
โ—‹Verification/Safety+20
โœ“Code Examples+15
โœ“Composability+15

Repo Health

โœ“Recent Activity+15
โœ“Scripts/Automation+10
โœ“Real Usage (Issues)+10
โœ“Single Responsibility+10
โœ“Config/Persistence+10
โœ“Install Instructions+5

Multi-platform bonus: +5 pts if tool supports 2+ platforms. Score derived from 12 structural signals โ€” not stars or popularity.

Trust & Verification

high

Broad system access required. Carefully review permissions before installing.

Active

Updated within the last 90 days. Actively maintained.

Unverified skill. Always review source code before installing any skill from an unknown author.

Risk Assessment

  • Real PTY terminal operations with shell/exec capabilities - can execute arbitrary system commands
  • Multi-stage workflow orchestration (.agent/workflows/ directory with 10+ workflow steps) enabling autonomous multi-agent execution patterns
  • Explicit approval ladder mechanism suggests attempt to gate execution, but system is designed to operate terminal with elevated capabilities
  • CI/CD automation that includes release, deployment, and docker build workflows with potential command execution
  • Multiple GitHub Actions and dispatch workflows that can trigger automated system operations
  • Configuration files for multiple AI models/providers (.gemini/, .gcp/) suggesting model-agnostic command execution