1. Conduid
  2. AI
  3. Ollama Ocli
MCP server Β· AI

Ollama Ocli

πŸ¦‰ AI coding assistant with self-improvement, LCARS styling, and MCP support

34Low

Scored 6 months ago Β· breakdown

About Ollama Ocli

Ollama Ocli is an MCP server in the AI category: πŸ¦‰ AI coding assistant with self-improvement, LCARS styling, and MCP support.

Install

From source
git clone https://github.com/wiseowltechnet/ollama-ocli

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about Ollama Ocli

Powered by Claude · Grounded in docs

I know everything about Ollama Ocli. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

  • βœ“README presentThe repository ships documentation.

5 checks have not been run yet.

README

⚠️ DEPRECATED β€” This project has been superseded by wiseowl-cli (Java 21 + Micronaut). All features have been consolidated into the new project. This repository is archived and will no longer receive updates.


πŸ¦‰ OCLI - Ollama Command Line Interface

CI Release Downloads License Rust

πŸ¦‰ OCLI - Ollama Command Line Interface

A Claude Code-like AI coding assistant with self-improvement capabilities, LCARS Star Trek styling, and full terminal UI control.

✨ Features

πŸ€– AI-Powered Development

  • Autonomous tool calling - AI automatically uses tools to read/write files, execute commands
  • Streaming responses - Real-time output with progress indicators
  • Context-aware - Maintains conversation history and file context
  • Self-improving - Can read and modify its own source code

πŸ› οΈ Built-in Tools

  • read_file - Read any file with syntax awareness
  • write_file - Create/modify files with automatic backups
  • execute_bash - Run shell commands safely
  • search_files - Find files and content across your project
  • list_directory - Explore directory structures

πŸ“‹ Planning Mode

  • /plan - Create AI-generated step-by-step plans
  • /next - Execute next step in plan
  • /show-plan - View plan progress

πŸ”§ Project Management (WiseOwl)

  • Auto-creates wiseowl/ folder for project tracking
  • /todo - Add tasks to TODO.md
  • /done - Mark tasks complete
  • /rule - Add project rules to RULES.md
  • /context - Add context to CONTEXT.md

🎨 LCARS Interface

  • Authentic Star Trek LCARS styling
  • RGB colors in multiples of 51 (hex 33)
  • Status indicators: ● (blue=success, red=error, purple=info, yellow=warning)
  • Clean vector look with high contrast

πŸ“Š Terminal UI

  • /monitor - Full-screen real-time statistics (like top/htop)
  • Cursor positioning and color control
  • Alternate buffer support

πŸ”Œ MCP (Model Context Protocol) Support

See MCP Architecture Documentation for detailed deployment options.

  • Load external MCP servers for extended functionality
  • /mcp list - Show available MCP tools
  • /mcp call <tool> [params] - Invoke MCP tools
  • AI automatically knows about available MCP tools
  • Configure servers in .ocli/mcp_servers.json

βš™οΈ Configuration & Export

  • /config set <key> <value> - Set configuration
  • /config get <key> - Get configuration value
  • /config list - Show all settings
  • /export [filename] - Export conversation to markdown

πŸ“ˆ Statistics & Git

  • /stats - Show session statistics
  • /git status|diff|log|commit - Git integration
  • /version - Show OCLI version

πŸš€ Installation

From Source

git clone https://github.com/wiseowltechnet/ollama-ocli.git
cd ollama-ocli
cargo build --release
./target/release/ocli

Homebrew (macOS/Linux)

brew tap wiseowltechnet/ocli
brew install ocli

πŸ“– Quick Start

  1. Start OCLI
ocli
  1. Ask the AI to help
You: create a hello world rust program
  1. Use planning mode for complex tasks
You: /plan build a web server with authentication
You: /next
  1. Monitor your session
You: /monitor
  1. Configure MCP servers
mkdir -p .ocli
cat > .ocli/mcp_servers.json << JSON
{
  "servers": [
    {
      "name": "filesystem",
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-filesystem", "/tmp"]
    }
  ]
}
JSON

🎯 Use Cases

Self-Improvement

OCLI can modify itself:

You: add a /version command to show OCLI version
AI: *reads src/main.rs, adds version command, rebuilds*

Project Scaffolding

You: /plan create a REST API with user authentication
You: /next

Code Review

You: review the code in src/main.rs for potential issues

Debugging

You: the tests are failing, can you fix them?

πŸ“ Slash Commands

Command Description
/help Show all commands
/plan <task> Create step-by-step plan
/next Execute next plan step
/show-plan View plan progress
/read <file> Read file
/write <file> Write file
/preview Preview pending changes
/apply Apply pending changes
/rollback Undo last change
/todo <task> Add TODO item
/done <id> Mark TODO complete
/rule <rule> Add project rule
/context <info> Add context
/mcp list List MCP tools
/mcp call <tool> Call MCP tool
/config <cmd> Manage settings
/export [file] Export conversation
/stats Show statistics
/git <cmd> Git operations
/monitor Real-time monitor
/version Show version
/clear Clear context
/exit Exit OCLI

🎨 LCARS Colors

  • Orange (#FF9900) - Headers, borders
  • Purple (#CC99FF) - Session info
  • Blue (#99CCFF) - Success indicators
  • Yellow (#FFCC00) - Warnings
  • Red (#FF6666) - Errors

πŸ”§ Configuration

OCLI stores configuration in .ocli/:

  • config.json - User settings
  • mcp_servers.json - MCP server configuration
  • sessions/ - Conversation history

🀝 Contributing

OCLI is designed to be self-improving. You can:

  1. Ask OCLI to add features to itself
  2. Submit PRs with new capabilities
  3. Create MCP servers for extended functionality

πŸ“œ License

MIT

πŸ™ Acknowledgments

  • Built with Ollama
  • Inspired by Claude Code
  • LCARS design from Star Trek
  • MCP protocol support

Made with πŸ¦‰ by the OCLI community

Development & QA

OCLI uses professional QA tools similar to Gradle:

# Format code (like Spotless)
make fmt

# Lint code (like Checkstyle/SpotBugs)
make lint

# Run tests (like JUnit)
make test

# Full QA pipeline
make qa

# CI pipeline
make ci

See QA_TOOLS.md for complete guide.

README copy captured when this server was indexed; it may lag the repository. The original is authoritative.

Questions

About Ollama Ocli

How do I install Ollama Ocli?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is Ollama Ocli safe to use with an AI agent?

Its trust score is 34 out of 100 (low). It passes 1 of the 1 static security checks run so far. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Ollama Ocli still maintained?

Conduid hasn't recorded a commit date for this repository yet. Check the repository directly for recent activity.