#410 · Primary category: AI Coding Assistants
working-activity
Lively Working-line extension for pi CLI and DSH
Project last updated:08/20/26
GitHub Stars
656
Forks
232
Contributors
3
License
MIT
Why we included this project
Anyone who spends long sessions watching a coding agent work will appreciate this: the working line stops being a static spinner and becomes a live view of what the model is actually doing. The extension hooks into tool execution events, so you see real-time progress percentages and recognizable stages such as builds, tests, and deploys, and quick tool calls get replayed so they don't flash by before you notice them. While the model thinks, the line cycles through casual status phrases, and there's a rare rainbow easter egg, model self-narration injected through the context, and a warning that turns the line yellow when context usage passes 80%. The same idea ships as two npm packages, one for pi CLI and one for DeepSeek Harness, so either setup can adopt it without changing its workflow. If you use pi or DSH and want a clearer picture of what your agent is doing while you wait, this is a small, focused upgrade worth trying.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
superpowers
An agentic skills framework & software development methodology that works.
ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
skills
Skills for Real Engineers. Straight from my .agents directory.
opencode
The open source coding agent.
andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.