gemini-cli
https://github.com/google-gemini/gemini-cli
TypeScript
An open-source AI agent that brings the power of Gemini directly into your terminal.
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
TypeScript not yet supported3 Subscribers
Add a CodeTriage badge to gemini-cli
Help out
- Issues
- Bug: read_file and grep_search tools are not working as expected with .toml files.
- Remote config for compression threshold is not applied when there is no user setting
- Agent should read truncated file content if needed
- Skills creator skill should ask the user whether to create a skill package or create the skill in the repo
- gemini cli hangs indefinitely if .env is a named pipe (i.e. when using 1Password Environments)
- Extensions (e.g. Conductor) fail with "run_shell_command not found" + ask_user header >12 chars error + tool execution denied
- Automatically reads any file path it encounters, leads to context exhaustion, excessive billing and crashes
- No consistent way to get Gemini to read files the first time I ask without them being truncated
- use `/stats` to see the current Status , but how can use `gemini -p` to see current Status.
- ✕ Failed to authenticate with MCP server 'clerk': Failed to discover OAuth configuration from MCP server
- Docs
- TypeScript not yet supported