百科.dev
全部条目在线工具AI 编程趋势榜开源项目技术资讯提交条目
登录
< 返回工具列表
S

sparc2

> 编程语言
开源

SPARC 框架是一套全面的方法,旨在指导可靠、可扩展应用程序的开发。SPARC 的全称是 Specification, Pseudo Code, Architecture, and Reuse (规范、伪代码、架构和重用)。

199 stars0 点赞1 次浏览
访问官网GitHub

工具介绍

SPARC 框架是一套全面的方法,旨在指导可靠、可扩展应用程序的开发。SPARC 的全称是 Specification, Pseudo Code, Architecture, and Reuse (规范、伪代码、架构和重用)。

SPARC Code Agent + MCP Server

SPARC 2.0, agentic code analysis and generation, is an intelligent coding agent framework built to automate and streamline software development. It combines secure execution environments, version control, and Model Context Protocol (MCP) capabilities into a unified system where specialized agents collaborate to understand, modify, and manage code.

These agents analyze patterns, suggest improvements, implement changes, and validate solutions, all while maintaining a detailed history that allows for easy rollbacks when needed.

Install globally

npm install -g @agentics.org/sparc2

SPARC 2.0 (alpha)

By bridging the gap between human developers and AI assistants, SPARC 2.0 enhances productivity across the entire development lifecycle, from initial code review to final deployment.

A defining feature of SPARC is its ability to track code changes over time, functioning like a perfect memory of your code's evolution. It uses a unified diff system to capture precisely what changed between versions rather than storing entire files, dramatically reducing storage needs and speeding up operations. By default, the system tracks changes at the file level for optimal performance, yet it can zoom in to function-level tracking when more granular detail is required. This efficient diff tracking ensures smooth performance whether you are working on a small project or a massive enterprise codebase.

Essentially, SPARC acts as an advanced version control enhancer that integrates with Git and GitHub while leveraging artificial intelligence to manage updates automatically. Its understanding of temporal relationships between code modifications allows it to orchestrate complex workflows that support simultaneous contributions from both human developers and AI agents. SPARC adapts its processing pace to match developers' speed, ensuring seamless, conflict-free collaboration.

At the heart of SPARC lies its vector store, a specialized database that transforms code and text into abstract patterns. Instead of merely memorizing exact words, it captures the underlying meaning of the code, similar to understanding cooking techniques rather than just listing ingredients. This approach enables the system to locate similar code snippets despite differences in variable names or styles, creating a smart library of your development history.

Another key element is its integrated code interpreter built using E2B—a language-agnostic execution environment that builds, runs, and modifies code without relying on a traditional IDE. It creates secure, isolated sandboxes for execution across languages such as Python, JavaScript, TypeScript, Go, Rust, and more.

SPARC 2.0 employs a ReACT (Reason + Act) strategy to semantically understand code. It first reasons about what the code means and then takes appropriate actions. This combination of efficient diff tracking and intelligent reasoning enables rapid processing of large codebases without sacrificing deep comprehension of the code's purpose and structure.

Key Benefits

  • Automated Code Analysis: Identifies bugs, performance issues, and potential improvements in your code
  • Intelligent Code Modifications: Applies suggested changes with precision, maintaining code style and patterns
  • Secure Code Execution: Tests code in a sandboxed environment before applying changes
  • Version Control Integration: Creates checkpoints and enables rollbacks to previous states
  • Vector Search: Finds similar code changes and patterns across your codebase
  • Flexible Processing Modes: Supports parallel, sequential, concurrent, and swarm processing
  • Multiple Execution Modes: Works in automatic, semi-automatic, or manual modes to fit your workflow
  • Configurable: Extensive configuration options via TOML files and environment variables
  • Cross-Platform: Works on any platform that supports Deno
  • MCP Integration: Provides Model Context Protocol (MCP) server for AI agent integration
  • Real-time Updates: Supports Server-Sent Events (SSE) for streaming real-time progress and results

How It Works

At its core, SPARC 2.0 uses advanced diff tracking to compare previous and updated versions of code:

  1. Diff Tracking: By default, it logs changes on a per-file basis for optimal performance, but you can opt for a per-function approach for more granular detail
  2. AI-Powered Analysis: Uses OpenAI's models to analyze code and suggest improvements
  3. Sandboxed Execution: Tests code changes in a secure environment using E2B Code Interpreter
  4. Git Integration: Creates checkpoints and enables rollbacks to previous states
  5. Vector Database: Stores and indexes all changes for easy retrieval and analysis

Processing Modes

SPARC 2.0 supports multiple processing modes:

  • Parallel: Process multiple code changes simultaneously (ideal for large projects)
  • Sequential: Process changes one after another in a defined order
  • Concurrent: Use asynchronous operations to ensure I/O-bound tasks don't block others
  • Swarm: Coordinate multiple agents to work on different aspects of the same problem

Execution Modes

  • Automatic: Autonomously makes and commits code changes
  • Semi-automatic: Proposes modifications and waits for your approval
  • Manual: Provides analysis but requires manual implementation
  • Custom: Define your own workflow with custom steps

Use Cases

SPARC 2.0 is ideal for:

  • Code Refactoring: Identify and fix code smells, improve performance, and enhance readability
  • Bug Fixing: Analyze and fix bugs with automated testing
  • Code Reviews: Get AI-powered insights on code quality and potential issues
  • Learning: Understand how to improve your code with detailed explanations
  • Technical Debt Reduction: Systematically identify and address technical debt
  • Codebase Exploration: Use vector search to find similar patterns across your codebase
  • AI Agent Integration: Use the MCP server to connect AI assistants with your codebase
  • Real-time Monitoring: Stream progress and results in real-time using SSE

Technology Stack

  • TypeScript: Built with TypeScript for type safety and modern language features
  • Deno Runtime: Fast, secure, and modern JavaScript/TypeScript runtime
  • OpenAI Agents API: Powers the reasoning and planning capabilities
  • E2B Code Interpreter SDK: Provides secure code execution in a sandboxed environment
  • Vector Database: Stores and indexes code changes for similarity search
  • Git Integration: Works with your existing Git repositories
  • MCP Server: Implements the Model Context Protocol for AI agent integration
  • Server-Sent Events: Provides real-time streaming updates for long-running operations

Installation

NPM Installation (Recommended)

bash
# Install globally
npm install -g @agentics.org/sparc2

# Or install locally in your project
npm install --save-dev @agentics.org/sparc2

Manual Installation

bash
# Clone the repository
git clone https://github.com/agentics-org/sparc2.git
cd sparc2

# Install dependencies
deno cache --reload src/cli/cli.ts

SPARC2 CLI

A comprehensive command-line interface for the SPARC2 project that integrates the E2B code interpreter and agent framework implementations.

Installation

If you installed via npm:

bash
# The CLI is available as the 'sparc2' command
sparc2 --help

# You can also use the 'sparc' command for direct execution
sparc --help

If you cloned the repository:

bash
# Create an alias for easier use
alias sparc2="deno run --allow-read --allow-write --allow-env --allow-net --allow-run /path/to/sparc2/src/cli/cli.ts"

# Or use the provided script
./sparc --help

Available Commands

SPARC2 CLI provides the following commands:

  • analyze: Analyze code files for issues and improvements
  • modify: Apply suggested modifications to code files
  • execute: Execute code in a sandbox
  • search: Search for similar code changes
  • checkpoint: Create a git checkpoint
  • rollback: Rollback to a previous checkpoint
  • config: Manage configuration
  • api: Start a Model Context Protocol (MCP) HTTP API server
  • mcp: Start a Model Context Protocol (MCP) server using stdio transport

Configuration

SPARC2 uses TOML configuration files:

  • config/sparc2-config.toml: General configuration
  • config/agent-config.toml: Agent-specific configuration

You can also set the configuration path using the environment variable:

bash
export SPARC2_CONFIG_PATH=/path/to/your/config.toml

Environment Variables

Create a .env file in your project root (you can copy from .env.example) or set these environment variables:

# Required
- `OPENAI_API_KEY`: Your OpenAI API key
- `E2B_API_KEY`: Your E2B API key

# Optional
- `OPENROUTER_API_KEY`: Your OpenRouter API key (optional)
- `SPARC2_CONFIG_PATH`: Custom path to your config file
- `NPM_TOKEN`: Your NPM token (only needed when publishing to npm)
- `MCP_SECRET_KEY`: Secret key for MCP server authentication

MCP Server

SPARC2 includes a Model Context Protocol (MCP) server that allows AI agents to interact with your codebase. The MCP server provides a standardized interface for tools and resources discovery, enabling seamless integration with AI assistants.

MCP Server Options

SPARC2 provides two different ways to use the Model Context Protocol (MCP):

1. HTTP API Server

The api command starts an HTTP server that implements the MCP protocol over HTTP:

bash
# Using the sparc command
./sparc api --port 3001

# Or with npm installation
sparc2 api --port 3001

Options:

  • --port, -p: Port to run the API server on (default: 3001)
  • --model: Model to use for the agent
  • --mode: Execution mode (automatic, semi, manual, custom, interactive)
  • --diff-mode: Diff mode (file, function)
  • --processing: Processing mode (sequential, parallel, concurrent, swarm)
  • --config, -c: Path to the agent configuration file

This is useful for integrations that communicate with SPARC2 over HTTP.

2. MCP Stdio Server

The mcp command starts a server that implements the MCP protocol over standard input/output (stdio):

bash
# Using the sparc command
./sparc mcp

# Or with npm installation
sparc2 mcp

Options:

  • --model: Model to use for the agent
  • --mode: Execution mode (automatic, semi, manual, custom, interactive)
  • --diff-mode: Diff mode (file, function)
  • --processing: Processing mode (sequential, parallel, concurrent, swarm)
  • --config, -c: Path to the agent configuration file

This is useful for integrations with tools like VS Code extensions that communicate with SPARC2 over stdio.

MCP Settings for VS Code Extensions

To use SPARC2 with VS Code extensions that support the Model Context Protocol (MCP), you'll need to configure the extension's settings. Here's an example configuration for the Claude extension:

…

The MCP server wrapper automatically detects the Deno executable in various common installation locations, making it portable across different systems.

MCP Endpoints

The MCP server exposes the following endpoints:

  • GET /discover: Returns a list of available tools and resources
  • GET /capabilities: Alias for /discover, returns the same information
  • GET /list_tools: Legacy endpoint that returns only the tools list
  • POST /analyze_code: Analyzes code files for issues and improvements
  • POST /modify_code: Applies suggested modifications to code files
  • POST /execute_code: Executes code in a secure sandbox
  • POST /search_code: Searches for similar code changes
  • POST /create_checkpoint: Creates a git checkpoint
  • POST /rollback: Rolls back to a previous checkpoint
  • POST /config: Manages configuration settings

MCP Tools

The SPARC2 MCP server provides the following tools:

1. analyze_code

Analyzes

Issues· 11 开放

查看全部 Issues在 GitHub 打开

暂无开放 Issues,或尚未同步最近议题。

> 标签

TypeScript

暂无评论,来聊聊你的看法吧

> 工具信息

发布日期2026年8月1日
最后更新2026年9月18日
分类编程语言
定价开源

> 相关工具

T
TypeScript
JavaScript 的超集,为前端与全栈提供静态类型
P
Python
通用编程语言,广泛用于 Web、数据与 AI
G
Go
Google 推出的简洁高效系统语言