lmcli v0.7.0 – TUI harness with smooth performance up to 1M context

Lmcli v0.7.0, a general-purpose LLM harness written in Go, has been released with smooth performance at 1M+ token context and features including composable agents, custom tools, sandboxed execution, and branching conversations. The tool supports OpenAI-compatible and Anthropic-compatible APIs, consumes under 50MB of RAM per instance, and is available via Go install.

- Go 100% | | screenshots /mlow/lmcli/src/branch/main/screenshots .gitignore /mlow/lmcli/src/branch/main/.gitignore CHANGELOG.md /mlow/lmcli/src/branch/main/CHANGELOG.md config.sample.yaml /mlow/lmcli/src/branch/main/config.sample.yaml go.mod /mlow/lmcli/src/branch/main/go.mod go.sum /mlow/lmcli/src/branch/main/go.sum LICENSE /mlow/lmcli/src/branch/main/LICENSE main.go /mlow/lmcli/src/branch/main/main.go README.md /mlow/lmcli/src/branch/main/README.md lmcli - Large Model CLI lmcli is a general-purpose LLM harness. Use it to code, chat, or build custom agentic workflows We have screenshots /mlow/lmcli/src/branch/main/screenshots . Features - Buttery smooth at 1M+ tokens sliding-window rendering - Composable, nesting Agents user-content-agents - Custom tools user-content-tools exec-only, MCP coming soon Sandbox user-content-sandbox tool execution- OpenAI-compatible and Anthropic-compatible API clients talk to any local or remote API - Branching, persisted conversations thanks, SQLite <3 vi -like keybindings- Export conversations to JSON or HTML - Image support - < 50MB of RAM per instance Installation go install codeberg.org/mlow/lmcli@latest Dependencies lmcli works best when the following tools are available: - ripgrep - Grep tool - libchafa - image rendering - uv - Python tool --with dependencies - bubblewrap - Sandbox tools with bwrap Configuration See config.sample.yaml /mlow/lmcli/src/branch/main/config.sample.yaml for the full example configuration. Defaults Defaults which apply to new lmcli chat and lmcli new sessions. ~/.config/lmcli/config.yaml defaults: model: deepseek-v4-flash agent: default default lmcli chat agent codeAgent: coder default lmcli code agent - just an alias temperature: 1.0 maxTokens: 64000 effort: xhigh Agents An Agent is a system prompt and a set of available tools. Each lmcli session starts with a root agent, which the user interacts with directly. This agent may then delegate tasks using the SubAgent tool provided it has been given access , and those sub-agents may delegate further. Only synchronous sub-agents are supported at the moment; background/persisted sub-agents are planned for a future release. The contents of AGENT.md , AGENTS.md , and CLAUDE.md will automatically be injected into the system prompt if any of them exist, and the agent has the Read tool. ~/.config/lmcli/config.yaml agents: - name: default systemPrompt: You are a helpful assistant. - name: coding tools: - Bash - Glob - Grep - Read - Write - Edit - Python systemPrompt: |- You are an expert software engineer... see config.sample.yaml for an effective prompt - name: web summarizer tools: - WebReader systemPrompt: Your task is to summarize the web page. Tools The following tools are built-in: Glob - List files based on glob patterns Grep - ripgrep -powered code search Read - Read contents of a file Write - Write contents of a file Edit - Search and replace contents of a file Bash - Execute shell commands Python - uv run --with=<deps -powered python execution SubAgent - Spawn a sub-agent - see Agents user-content-agents WebReader - Fetch web content using a Firecrawl endpoint. Most tools execute out-of-process via the lmcli tool sub-command, which may be wrapped in the Sandbox user-content-sandbox . Tools usage is gated a very simple 'read-write-execute' permissions model. Press ctrl-p in the TUI to cycle through read-only, read-write, and read-write-execute unattended permissions, or use lmcli chat|reply|new -p rwx . Custom tools exec-based tools are supported. For example, given the GetWeather example below, the model's call to GetWeather location="Tokyo, Japan", units="celsius" would be piped the tool as: {"location": "Tokyo, Japan", "units": "celsius"} The executable's stdout is used as the tool result, which is returned to the model as-is. Environment variables defined on custom tools get passed set on the environment during execution, hidden from the model. MCP support is planned. ~/.config/lmcli/config.yaml tools: Override a built-in tool - name: WebReader config: backend: https://firecrawl.example.com/v1 apiKey: fc-... Custom external tool - name: GetWeather description: Get the current weather. path: fetch-weather.sh permission: read parameters: - name: location type: string required: true - name: Read - name: Write - name: Edit - name: Glob - name: Grep Providers lmcli supports local and remote OpenAI-compatible and Anthropic-compatible providers. ~/.config/lmcli/config.yaml providers: - name: deepseek display: DeepSeek kind: openai baseUrl: https://api.deepseek.com/ models: - deepseek-v4-pro - name: anthropic kind: anthropic apiKey: ... models: - name: claude-sonnet-4-6 Sandbox When enabled, lmcli sandboxes local tool invocations with bubblewrap https://github.com/containers/bubblewrap . The sandbox is configured to prevent filesystem access outside of the CWD with configured exceptions , and to prevent leaking of lmcli 's environment API keys, etc . Access to the host network stack remains a vector for escape. Sandboxing is currently opt-in: sandbox.enabled must be true. ~/.config/lmcli/config.yaml sandbox: Whether to use the sandbox, default false enabled: true Whether to remap the working directory to /workspace in the sandbox remapWorkspace: true Paths to map from the host into the sandbox bindDirs: - /home/user/.config:/home/user/.config:ro - /home/user/.cache:/home/user/.cache:ro Paths to persist across lmcli instances and tool invocations Stored in ~/.local/share/lmcli/sandbox/<path persistDirs: - /tmp Misc Various settings that affect lmcli 's behavior. ~/.config/lmcli/config.yaml Conversation title generation conversations: titleGeneration: Defaults to defaults.model model: optional set to agent with custom prompt for title generation. Agent must respond with {"title": "<title "} JSON Defaults to built-in agent, see pkg/lmcli/tasks/title.go agent: title-generator effort: none maxTokens: 1024 Syntax highlighting by Chroma: https://github.com/alecthomas/chroma chroma: Refer to: https://github.com/alecthomas/chroma/tree/master/styles style: onedark - terminal - 8 colors - terminal16 - 16 colors - terminal256 - 256 colors - terminal16m - true color default formatter: terminal16m tui: hideHelpHint: false Usage bash $ lmcli help lmcli - Large Language Model CLI Usage: lmcli <command flags lmcli command Available Commands: chat Open the chat interface clone Clone conversations code Open the chat interface with a code agent completion Generate the autocompletion script for the specified shell edit Edit the last user reply in a conversation export Export a conversation help Help about any command list List conversations new Start a new conversation prompt Do a one-shot prompt rename Rename a conversation reply Reply to a conversation retry Retry the last user reply in a conversation rm Remove conversations view View messages in a conversation Flags: -h, --help help for lmcli Use "lmcli command --help" for more information about a command. Note: Use ctrl+h in the TUI view for keybindings. Examples Start a new chat with the code agent wired up to perform file editing. bash $ lmcli code Start a new conversation, imperative style no tui : bash $ lmcli new "Help me plan meals for the next week" Send a one-shot prompt no persistence : bash $ lmcli prompt "What is the answer to life, the universe, and everything?" tmux Do you run lmcli with tmux ? To get scroll-wheel scrolling working, you'll want the following in your ~/.tmux.conf : Emulate scrolling by sending up and down keys if these commands are running in the pane tmux commands with legacy scroll="lmcli" bind-key -T root WheelUpPane \ if-shell -Ft= ' {?mouse any flag,1, {pane in mode}}' \ 'send -Mt=' \ 'if-shell -t= " {?alternate on,true,false} || echo \" {tmux commands with legacy scroll}\" | grep -q \" {pane current command}\"" \ "send -t= Up" "copy-mode -et="' bind-key -T root WheelDownPane \ if-shell -Ft = ' {?pane in mode,1, {mouse any flag}}' \ 'send -Mt=' \ 'if-shell -t= " {?alternate on,true,false} || echo \" {tmux commands with legacy scroll}\" | grep -q \" {pane current command}\"" \ "send -t= Down" "send -Mt="' This example will be removed when bubbletea is able to handle scrolling in tmux on its own. Roadmap I aim to keep lmcli a light-weight and easy to understand shim between users and models. A driving philosophy is that models will grow capable of accomplishing increasingly complex tasks with access to the same set of simple tools. In rough order of priority: - MCP local custom tools already supported - Skills - Image output - Built-in web search tool - RAG-driven prior conversation search - Computer use connect to Wayland and/or X, pass display output to model, feed back mouse/KB inputs - Semantic conversation search - Conversation categorization/tagging - Token accounting - Fleshed-out permissions model beyond current read-write-execute model License MIT Acknowledgements lmcli is a hobby project. Special thanks to the Go community and the creators of the libraries used in this project.