Multiplayer & BYOK CLI and Neovim Coding Agent (optimised for the poor man).
- Script: Rust, Python, Lua, Vim Script, Bash
- Dependencies: ratatui, crossterm, tokio, clap, serde, google-genai, rich, PyYAML, aiofiles, aiohttp, cryptography
- Optional SDKs: openai, anthropic
- Distribution: Docker, GitHub Actions
The below instructions are for installing and running poor-cli from this repository.
- Bootstrap the project.
$ git clone https://github.com/gongahkia/poor-cli.git
$ cd poor-cli
$ python3 -m venv .venv && source .venv/bin/activate
$ pip install ".[all]"- Optionally configure providers in
.envor do it directly withinpoor-cli's TUI.
$ cp .env.example .env- Finally run any of the below to begin using
poor-cli's TUI.
$ ./run.sh
$ ./run_tui.sh
$ python3 -m poor_cli
$ docker build -t poor-cli .
$ docker run -it --env-file .env poor-cli- Alternatively, use
poor-cli's Neovim plugin. The easiest way to install this is with the lazy.nvim Package Manager.
{
"gongahkia/poor-cli",
submodules = false,
config = function()
require("poor-cli").setup({
trigger_key = "<C-Space>", -- Trigger completion
accept_key = "<Tab>", -- Accept completion
chat_key = "<leader>pc", -- Toggle chat panel
provider = nil, -- Auto-detect from env
})
end,
}poor-cli-server can run in multiplayer WebSocket host mode with room-scoped
invite tokens and role permissions (viewer or prompter).
$ poor-cli-server --host --bind 0.0.0.0 --port 8765 --room dev --room docs$ poor-cli-server --host --bind 127.0.0.1 --port 8765 --room dev --ngrok$ poor-cli --remote-url ws://HOST:8765/rpc --remote-room dev --remote-token <prompter-or-viewer-token>require("poor-cli").setup({
multiplayer = {
enabled = true,
url = "ws://HOST:8765/rpc",
room = "dev",
token = "<prompter-or-viewer-token>",
},
})poor-cli supports provider/model selection via /switch (inside TUI) or --provider/--model flags. You can pass any model ID accepted by the provider SDK/API.
| Provider | Key | Default Model | Common Models | Capabilities in poor-cli |
|---|---|---|---|---|
| Gemini | gemini |
gemini-2.0-flash |
gemini-2.0-flash, gemini-1.5-pro |
Streaming, function calling, system instructions, vision, JSON mode |
| OpenAI | openai |
gpt-4-turbo |
gpt-4o, gpt-4-turbo, gpt-3.5-turbo |
Streaming, function calling, system instructions, JSON mode, vision on GPT-4-class models |
| Anthropic / Claude | anthropic (alias: claude) |
claude-3-5-sonnet-20241022 |
claude-sonnet-4-20250514, claude-3-haiku-20240307 |
Streaming, function calling, system instructions, vision |
| Ollama | ollama |
llama3 |
Auto-discovered from local ollama (/api/tags), with fallbacks llama3, codellama, mistral, phi3 |
Streaming, system instructions, JSON mode, optional function calling (model-dependent), local-only execution via http://localhost:11434 |
Type @path/to/file in any message to attach file context.
Use quoted refs for spaces: @"docs/My File.md" or @'docs/My File.md'.
Run !<command> [| optional question] to execute local shell output and optionally ask the model about it.
Core Workflow:
/help- Show all available commands/onboarding- Start guided CLI onboarding/plan- Generate a plan before executing/history- Show recent messages/sessions- List recent sessions/new-session- Start a fresh session/queue- Manage prompt queue (add/list/clear/drop)/compact- Manage context (compact/compress/handoff)/search- Search transcript, tools, and diffs/status- Show session status summary/export- Export conversation history/retry- Retry last request/edit-last- Edit and resend last prompt/copy- Copy last assistant response/quit- Exit the TUI/exit- Exit the TUI (alias)/clear- Clear conversation history/clear-output- Clear screen output only/cost- Show session token usage and estimated cost/ollama-models- List locally available Ollama models/mcp-health- Check health of MCP servers
Review & Safety:
/review- Review code or staged diff/test- Generate tests for a file/permission-mode- Show permission mode/sandbox- Show or set sandbox preset/instructions- Inspect the active instruction stack/memory- Show or update repo-local memory/policy- Inspect repo-local hooks and audit status/context- Open backend context inspector/timeline- Open agent timeline and diffs/explain-diff- Explain behavior and risk in current diff/fix-failures- Analyze latest test/lint failure output/checkpoints- List available checkpoints/checkpoint- Create manual checkpoint/save- Quick checkpoint alias/rewind- Restore checkpoint by id or latest/restore- Restore latest checkpoint/diff- Compare two files/undo- Undo last file change (checkpoint)/plan-mode- Toggle plan-first execution guidance
Providers & Config:
/provider- Show active provider/switch- Switch provider/model/providers- List providers and models/config- Show active configuration/model-info- Show model capabilities/profile- Set execution profile (speed|safe|deep-review)/broke- Set poor mode (terse responses)/my-treat- Set rich mode (comprehensive responses)/settings- List editable config settings/setup- Open the guided API key and .env editor/env- Open the guided API key and .env editor/api-key- Open the API key editor or use/api-key status/verbose- Toggle verbose logging/toggle- Toggle boolean config value/set- Set config key to a value/theme- Show or set UI theme (dark/light)/tools- List backend tools/mcp- Inspect or control MCP servers and tools
Context & Reuse:
/files- List pinned context files/add- Pin file/directory for context/drop- Unpin context file/clear-files- Clear all pinned context files/focus- Manage persistent coding focus state/resume- Resume with branch/checkpoint/session summary/workspace-map- Summarize repository layout and hotspots/bootstrap- Detect project type and suggest quickstart commands/context-budget- Rank context files against a token budget/image- Queue image for next message/save-prompt- Save reusable prompt/use- Load and run saved prompt/prompts- List saved prompts/save-session- Save current session for later restore/restore-session- Restore most recent saved session
Automation & Tasks:
/autopilot- Toggle bounded autonomous execution mode/qa- Run background QA watch for lint/tests/task- Manage durable background tasks/inbox- Show pending and actionable tasks/tasks- Legacy alias for /task/skills- Inspect or run repo and user skills/commands- Inspect or run repo and user commands/watch- Watch directory for changes/unwatch- Stop watch mode
Services & Shell:
/doctor- Run environment and service health checks/service- Manage local background services/ollama- Manage Ollama service and models/run- Run shell command via backend/read- Read file through backend/pwd- Show current working directory/ls- List files in directory
Git & Workspace:
/commit- Create commit message from staged diff
Collaboration:
/collab- Start, join, and manage collaboration sessions/pair- Legacy pair alias for collaboration sessions/pass- Hand driver role to the next collaborator/suggest- Send suggestion to the active driver/leave- Disconnect from collaboration session/host-server- Legacy advanced host controls for collaboration/join-server- Legacy join alias for invite/manual room entry/kick- Remove a room member from collaboration/who- Show room members and roles/members- Alias for /who
Safety & Undo:
/gc- Run checkpoint garbage collection
poor-cli can currently use these tools.
- File & Workspace Tools:
read_file,write_file,edit_file,list_directory,glob_files,grep_files,copy_file,move_file,delete_file,create_directory,diff_files - Execution & Quality Tools:
bash,run_tests,format_and_lint,dependency_inspect,process_logs - Git Tools:
git_status,git_diff,git_status_diff,apply_patch_unified - Network/Data Tools:
fetch_url,web_search,json_yaml_edit - Optional GitHub Tools (available when
ghCLI is installed):gh_pr_list,gh_pr_view,gh_pr_create,gh_pr_comment,gh_issue_list,gh_issue_view