Metadata-Version: 2.4
Name: langrepl
Version: 0.2.1
Summary: A powerful interactive terminal CLI for AI-powered assistance, built with Interactive command-line chat application powered by Langchain, Langgraph, Prompt Toolkit and Rich.
License-File: LICENSE
Requires-Python: >=3.13
Requires-Dist: aiofiles>=24.1.0
Requires-Dist: aiosqlite>=0.21.0
Requires-Dist: greenlet>=3.2.4
Requires-Dist: langchain-anthropic>=0.3.17
Requires-Dist: langchain-aws>=0.2.28
Requires-Dist: langchain-community>=0.3.27
Requires-Dist: langchain-core>=0.3.68
Requires-Dist: langchain-deepseek>=0.1.3
Requires-Dist: langchain-google-genai>=2.1.7
Requires-Dist: langchain-mcp-adapters>=0.1.9
Requires-Dist: langchain-ollama>=0.3.4
Requires-Dist: langchain-openai>=0.3.27
Requires-Dist: langchain>=0.3.26
Requires-Dist: langgraph-checkpoint-sqlite>=2.0.10
Requires-Dist: langgraph-prebuilt>=0.5.2
Requires-Dist: langgraph>=0.5.2
Requires-Dist: prompt-toolkit>=3.0.52
Requires-Dist: pydantic-settings>=2.10.1
Requires-Dist: pydantic>=2.11.7
Requires-Dist: pygments-cache>=0.1.3
Requires-Dist: pytest-asyncio>=1.1.0
Requires-Dist: python-dotenv>=1.1.1
Requires-Dist: python-multipart>=0.0.20
Requires-Dist: pyyaml>=6.0.2
Requires-Dist: rich>=14.1.0
Requires-Dist: trafilatura>=1.8.3
Requires-Dist: types-aiofiles>=24.1.0.20250822
Requires-Dist: types-pyyaml>=6.0.12.20250822
Description-Content-Type: text/markdown

# Langrepl

Interactive terminal CLI for building and running LLM agents. Built with LangChain, LangGraph, Prompt Toolkit, and Rich.

https://github.com/user-attachments/assets/5d95e221-3883-44f8-9694-74c5e215b4e2

## Table of Contents

- [Features](#features)
- [Prerequisites](#prerequisites)
- [Installation](#installation)
    - [From GitHub](#from-github)
    - [From Source](#from-source)
    - [Configure API Keys](#configure-api-keys)
    - [Tracing](#tracing)
- [Quick Start](#quick-start)
    - [Interactive Chat Mode](#interactive-chat-mode)
    - [LangGraph Server Mode](#langgraph-server-mode)
- [Interactive Commands](#interactive-commands)
    - [Conversation Management](#conversation-management)
    - [Configuration](#configuration)
    - [Utilities](#utilities)
- [Usage](#usage)
    - [Agents](#agents-configagentsyml)
    - [LLMs](#llms-configllmsyml)
    - [Custom Tools](#custom-tools)
    - [MCP Servers](#mcp-servers-configmcpjson)
    - [Sub-Agents](#sub-agents-configsubagentsyml)
    - [Tool Approval](#tool-approval-configapprovaljson)
- [Development](#development)
- [License](#license)

## Features

- **[Deep Agent Architecture](https://blog.langchain.com/deep-agents/)** - Planning tools, virtual filesystem, and
  sub-agent delegation for complex multi-step tasks
- **LangGraph Server Mode** - Run agents as API servers with LangGraph Studio integration for visual debugging
- **Multi-Provider LLM Support** - OpenAI, Anthropic, Google, AWS Bedrock, Ollama, DeepSeek, ZhipuAI, and local models (LMStudio, Ollama)
- **Extensible Tool System** - File operations, web search, terminal access, grep search, and MCP server integration
- **Persistent Conversations** - SQLite-backed thread storage with resume, replay, and compression
- **User Memory** - Project-specific custom instructions and preferences that persist across conversations
- **Human-in-the-Loop** - Configurable tool approval system with regex-based allow/deny rules
- **Cost Tracking (Beta)** - Token usage and cost calculation per conversation
- **MCP Server Support** - Integrate external tool servers via the MCP protocol

## Prerequisites

- **Python 3.13+** - Required for the project
- **uv** - Fast Python package
  installer ([install instructions](https://docs.astral.sh/uv/getting-started/installation/))
- **ripgrep (rg)** - Fast search tool used by the grep_search functionality:
    - macOS: `brew install ripgrep`
    - Ubuntu/Debian: `sudo apt install ripgrep`
    - Arch Linux: `sudo pacman -S ripgrep`
    - Windows: `choco install ripgrep` or download from [releases](https://github.com/BurntSushi/ripgrep/releases)
- **Node.js & npm** (optional) - Required only if using MCP servers that run via npx

## Installation

The `.langrepl` config directory is created in your **working directory** (or use `-w` to specify a location).
Aliases: `langrepl` or `lg`

### From GitHub

**Quick try (no installation):**
```bash
uvx --from git+https://github.com/midodimori/langrepl langrepl
uvx --from git+https://github.com/midodimori/langrepl langrepl -w /path  # specify working dir
```

**Install globally:**
```bash
uv tool install git+https://github.com/midodimori/langrepl
```

Then run from any directory:
```bash
langrepl              # or: lg
langrepl -w /path     # specify working directory
```

### From Source

Clone and install:
```bash
git clone https://github.com/midodimori/langrepl.git
cd langrepl
make install
uv tool install --editable .
```

Then run from any directory (same as above).

### Configure API Keys

Set API keys via `.env`:

```bash
LLM__OPENAI_API_KEY=your_openai_api_key_here
LLM__ANTHROPIC_API_KEY=your_anthropic_api_key_here
LLM__GOOGLE_API_KEY=your_google_api_key_here
LLM__DEEPSEEK_API_KEY=your_deepseek_api_key_here
LLM__ZHIPUAI_API_KEY=your_zhipuai_api_key_here
```

### Tracing

#### LangSmith

Add to `.env`:

```bash
LANGCHAIN_TRACING_V2=true
LANGCHAIN_ENDPOINT="https://api.smith.langchain.com"
LANGCHAIN_API_KEY="your_langsmith_api_key"
LANGCHAIN_PROJECT="your_project_name"
```

## Quick Start

Langrepl ships with multiple prebuilt agents:
- **`general`** (default) - General-purpose agent for research, writing, analysis, and planning
- **`claude-style-coder`** - Software development agent mimicking Claude Code's behavior
- **`code-reviewer`** - Code review agent focusing on quality and best practices

### Interactive Chat Mode

```bash
langrepl              # Start interactive session (general agent by default)
langrepl -a general   # Use specific agent
langrepl -r           # Resume last conversation
langrepl -am ACTIVE   # Set approval mode (SEMI_ACTIVE, ACTIVE, AGGRESSIVE)
langrepl -w /path     # Set working directory
lg                    # Quick alias
```

### LangGraph Server Mode

```bash
langrepl -s -a general                # Start LangGraph server
langrepl -s -a general -am ACTIVE     # With approval mode

# Server: http://localhost:2024
# Studio: https://smith.langchain.com/studio/?baseUrl=http://127.0.0.1:2024
# API Docs: http://localhost:2024/docs
```

Server features:
- Auto-generates `langgraph.json` configuration
- Creates/updates assistants via LangGraph API
- Enables visual debugging with LangGraph Studio
- Supports all agent configs and MCP servers

## Interactive Commands

### Conversation Management

<details>
<summary><code>/resume</code> - Switch between conversation threads</summary>

Shows list of all saved threads with timestamps. Select one to continue that conversation.

</details>

<details>
<summary><code>/replay</code> - Branch from previous message</summary>

Shows all previous human messages in current thread. Select one to branch from that point while preserving the original
conversation.

</details>

<details>
<summary><code>/compress</code> - Compress conversation history</summary>

Compresses messages using LLM summarization to reduce token usage. Creates new thread with compressed history (e.g., 150
messages/45K tokens → 3 messages/8K tokens).

</details>

<details>
<summary><code>/clear</code> - Start new conversation</summary>

Clear screen and start a new conversation thread while keeping previous thread saved.

</details>

### Configuration

<details>
<summary><code>/agents</code> - Switch agent</summary>

Shows all configured agents with interactive selector. Switch between specialized agents (e.g., coder, researcher,
analyst).

</details>

<details>
<summary><code>/model</code> - Switch LLM model</summary>

Shows all configured models with interactive selector. Switch between models for cost/quality tradeoffs.

</details>

<details>
<summary><code>/tools</code> - View available tools</summary>

Lists all tools from impl/, internal/, and MCP servers.

</details>

<details>
<summary><code>/mcp</code> - Manage MCP servers</summary>

View and toggle enabled/disabled MCP servers interactively.

</details>

<details>
<summary><code>/memory</code> - Edit user memory</summary>

Opens `.langrepl/memory.md` for custom instructions and preferences. Content is automatically injected into agent
prompts.

**Advanced:** Use `{user_memory}` placeholder in custom agent prompts to control placement. If omitted, memory
auto-appends to end.

</details>

### Utilities

<details>
<summary><code>/graph [--browser]</code> - Visualize agent graph</summary>

Renders in terminal (ASCII) or opens in browser with `--browser` flag.

</details>

<details>
<summary><code>/help</code> - Show help</summary>

</details>

<details>
<summary><code>/exit</code> - Exit application</summary>

</details>

## Usage

Configs are auto-generated in `.langrepl/` on first run.

### Agents (`config.agents.yml`)

```yaml
agents:
  - name: my-agent
    prompt: prompts/my_agent.md  # Single file or array of files, this will look for `.langrepl/prompts/my_agent.md`
    llm: haiku-4.5
    checkpointer: sqlite
    recursion_limit: 40
    tool_output_max_tokens: 10000
    default: true
    tools:
      - impl:file_system:read_file
      - mcp:context7:resolve-library-id
    subagents:
      - general-purpose
    compression:
      auto_compress_enabled: true
      auto_compress_threshold: 0.8
      compression_llm: haiku-4.5
```

**Tool naming**: `<category>:<module>:<function>` with wildcard support (`*`, `?`, `[seq]`)
- `impl:*:*` - All built-in tools
- `impl:file_system:read_*` - All read_* tools in file_system
- `mcp:server:*` - All tools from MCP server

### LLMs (`config.llms.yml`)

```yaml
llms:
  - model: claude-haiku-4-5
    alias: haiku-4.5
    provider: anthropic
    max_tokens: 10000
    temperature: 0.1
    context_window: 200000
    input_cost_per_mtok: 1.00
    output_cost_per_mtok: 5.00
```

### Custom Tools

1. Implement in `src/tools/impl/my_tool.py`:
   ```python
   from src.tools.wrapper import approval_tool

   @approval_tool()
   def my_tool(query: str) -> str:
       """Tool description."""
       return result
   ```

2. Register in `src/tools/factory.py`:
   ```python
   MY_TOOLS = [my_tool]
   self.impl_tools.extend(MY_TOOLS)
   ```

3. Reference: `impl:my_tool:my_tool`

### MCP Servers (`config.mcp.json`)

```json
{
  "mcpServers": {
    "my-server": {
      "command": "uvx",
      "args": ["my-mcp-package"],
      "transport": "stdio",
      "enabled": true,
      "include": ["tool1"],
      "exclude": [],
      "repair_command": "rm -rf .some_cache"
    }
  }
}
```

- `repair_command`: Runs if server fails, then run this command before retrying
- Suppress stderr: `"command": "sh", "args": ["-c", "npx pkg 2>/dev/null"]`
- Reference: `mcp:my-server:tool1`
- Examples: [useful-mcp-servers.json](examples/useful-mcp-servers.json)

### Sub-Agents (`config.subagents.yml`)

Sub-agents use the same config structure as main agents.

```yaml
subagents:
  - name: code-reviewer
    prompt: prompts/code-reviewer.md
    tools: [impl:file_system:read_file]
```

**Add custom**: Create prompt, add to config above, reference in parent agent's `subagents` list.

### Tool Approval (`config.approval.json`)

```json
{
  "always_allow": [
    {
      "name": "read_file",
      "args": null
    },
    {
      "name": "run_command",
      "args": "pwd"
    }
  ],
  "always_deny": [
    {
      "name": "run_command",
      "args": "rm -rf /.*"
    }
  ]
}
```

**Modes**: `SEMI_ACTIVE` (ask unless whitelisted), `ACTIVE` (auto-approve except denied), `AGGRESSIVE` (bypass all)

## Development

For local development without global install:

```bash
git clone https://github.com/midodimori/langrepl.git
cd langrepl
make install
```

**Run from within repository:**
```bash
uv run langrepl              # Start interactive session
uv run langrepl -w /path     # Specify working directory
uv run langrepl -s -a general  # Start LangGraph server
```

**Development commands:**
```bash
make install      # Install dependencies + pre-commit hooks
make lint-fix     # Format and lint code
make test         # Run tests
make pre-commit   # Run pre-commit on all files
make clean        # Remove cache/build artifacts
```

## License

This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
