#310310th of 324 in Skills, plugins and prompts
cli-continues
CLI that moves a coding session between 16 AI coding tools
- Stars
- 1.6k
- License
- MIT
- Last commit
- May 2026
- Language
- TypeScript
981 on 3 Apr 20261,589 on 30 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
continues reads local session files from 16 AI coding CLIs and editors, including Claude Code, Codex, Copilot CLI, Gemini CLI, Cursor and Cline. It builds a handoff document with recent messages, file changes and tool activity, then launches a different tool with it. It also does native same-tool resume, session listing, inspection and bulk export.
Who it is for: Developers who switch between several AI coding CLIs, e.g. after rate limits
Strengths
- Any-to-any handoff across 16 tools, 240 source and destination pairs
- Read-only access to session files; index cached at ~/.continues/sessions.jsonl
- Four verbosity presets plus .continues.yml for per-project defaults
- Scriptable: list with JSON/JSONL output, inspect, and dump to markdown or JSON
Weaknesses
- Requires Node.js 22.5+ for built-in node:sqlite
- Newer parsers were adapted from another project's adapters; fidelity unverified
- Handoff is a summary document, not full history; detail depends on preset
- No tagged releases
What it needs
- no GPU
- Needs Node.js 22.5+, At least one supported AI coding tool installed
- Models: Claude Code, Codex, GitHub Copilot CLI, Gemini CLI, Cursor
Quick answers
Is cli-continues open source?
Yes. Its code is on GitHub under the MIT license.
Also in Skills, plugins and prompts
See all 324| Rank | Project | Score |
|---|---|---|
| 1 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 96 out of 100 |
| 2 | skillsAgent skills for planning, TDD, debugging and code review | 95 out of 100 |
| 3 | eccAgents, skills, hooks and rules bundle for Claude Code, Codex and other harnesses | 95 out of 100 |
| #4 | gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles | 95 out of 100 |
| #5 | cavemanCuts token use in coding agents with terse replies and compressed inputs | 95 out of 100 |