.fyi
SkillsMCPPluginsSubagents

Browse by category

DevOps & CI/CD SkillsProductivity & Workflow SkillsOther SkillsProduct & Project Management SkillsDocumentation & Knowledge SkillsCode Review & Refactor SkillsBackend & APIs SkillsAgent Meta & Communication SkillsResearch SkillsSecurity SkillsUX UI & Design SkillsTesting & QA SkillsSee all →

Every Claude Code skill, MCP server, plugin and subagent in one directory. Searchable, comparable, and one command from installed. Live stats from GitHub, npm and PyPI.

We're on Product HuntYour agent's app storeCheck it out →
Agent SkillsMCP ServersPluginsSubagentsCoding Agents
CollectionsOfficial publishersGlossaryFAQBlogSearchSavedFeedback
PrivacyTermsllms.txtSitemap

made with ♥ · © 2026 aaaa.fyi

Independent project · real data from public registries

…/cloudwego/abcoder
home/mcp-servers/cloudwego/abcoder
cloudwego avatar

abcoder

bycloudwego· 1 MCP server

Stars

385

Forks

56

Category

Code Review & Refactor

View on GitHub

TL;DR

  • Universal Abstract-Syntax-Tree (UniAST), a language-independent, AI-friendly specification of code information, providing a boundless, flexible and structural coding context for both AI and humans.
  • How to install abcoder?

    cloudwego/abcoder
    $git clone https://github.com/cloudwego/abcoder

    Installs into the current project.

    ›Prefer a prompt? Paste this to your agent

    Install & use

    Install abcoder by running `git clone https://github.com/cloudwego/abcoder`, then use it for the current task and follow its documentation at https://github.com/cloudwego/abcoder.

    Files · 1

    View on GitHub
    README.md
    1# ABCoder: AI-Based Coder(AKA: A Brand-new Coder)
    2 
    3![ABCoder](images/ABCoder.png)
    4 
    5# Overview
    6ABCoder, an AI-oriented Code-processing **Framework**, is designed to enhance and extend the coding context for Large-Language-Model (LLM), finally boosting the development of AI-assisted-programming applications.
    7 
    8 
    9## Features
    10 
    11- Universal Abstract-Syntax-Tree (UniAST), a language-independent, AI-friendly specification of code information, providing a boundless, flexible and structural coding context for both AI and humans.
    12
    13- General Parser, parses arbitrary-language codes to UniAST.
    14 
    15- General Writer transforms UniAST back to code.
    16 
    17- **Code-Retrieval-Augmented-Generation (Code-RAG)**, provides a set of MCP tools to help the LLM understand code repositories precisely and locally. And it can support both in-workspace and out-of-workspace third-party libraries simultaneously -- I guess you are thinking about [DeepWiki](https://deepwiki.org) and [context7](https://github.com/upstash/context7), but ABCoder is more reliable and confidential -- no need to wait for their services to be done, and no worry about your codes will be uploaded!
    18 
    19Based on these features, developers can easily implement or enhance their AI-assisted programming applications, such as reviewing, optimizing, translating, etc.
    20 
    21 
    22## Universal Abstract-Syntax-Tree Specification
    23 
    24see [UniAST Specification](docs/uniast-zh.md)
    25 
    26 
    27# Quick Start
    28 
    29## Claude Code Integration
    30 
    31ABCoder provides deep integration with [Claude Code](https://claude.ai/code) through the AST-Driven Coding workflow, enabling hallucination-free code analysis and precise execution. Check [Claude Code Specification](docs/claude-code-spec.md) for more details.
    32 
    33### Setup
    34 
    35Use the `init-spec` command to automatically configure Claude Code integration for your project:
    36 
    37```bash
    38# Install ABCoder
    39go install github.com/cloudwego/abcoder@latest
    40 
    41# Run init-spec in your project directory (optional: specify target path)
    42cd /path/to/your/project
    43abcoder init-spec
    44```
    45 
    46The `init-spec` command will:
    471. Copy `.claude` directory to your project root
    482. Configure MCP servers in `~/.claude.json`:
    49 - `abcoder`: for code analysis using AST
    50 - `sequential-thinking`: for complex problem decomposition
    513. Replace all `{{CLAUDE_HOME_PATH}}` placeholders with actual project paths
    52 
    53### Start Coding with Claude Code
    54 
    55Once setup, you can start coding with Claude Code:
    56 
    571. Start Claude Code in your project directory
    582. Use slash common `/abcoder:schedule <problem_desc>` to address your feature/requirement/issue, and ABCoder will help you analyze the codebase and design a technical solution.
    593. Once all questions are set, use slash common `/abcoder:task <task_name>` to create a coding task(specification)
    604. Recheck the task using `/abcoder:recheck <task_name>` before real implementation
    615. Begin coding! Claude Code will process the task step by step according to the specification, leveraging the power of AST-driven analysis.
    62 
    63### AST-Driven Coding Workflow
    64 
    65[`.claude/hooks`](internal/cmd/assets/.claude/hooks) provide a 4-layer analysis chain from repository to node details:
    66 
    67```
    68list_repos → get_repo_structure → get_package_structure → get_file_structure → get_ast_node
    69 │ │ │ │ │
    70 └── repo_name └── mod/pkg list └── file list └── node list └── dependencies/references
    71```
    72 
    73### Claude Code Slash Commands
    74 
    75[`.claude/commands`](internal/cmd/assets/.claude/commands) provide three custom slash commands to streamline development:
    76 
    77| Command | Function | Description |
    78|---------|----------|-------------|
    79| [`/abcoder:schedule` <task_desc>](internal/cmd/assets/.claude/commands/abcoder/schedule.md) | Design implementation | Analyze codebase by using ABCoder, design technical solution |
    80| [`/abcoder:task <name>`](internal/cmd/assets/.claude/commands/abcoder/task.md) | Create coding task | Generate standardized CODE_TASK document |
    81|

    Preview

    cloudwego/abcodercloudwego/abcoder

    # ABCoder: AI-Based Coder(AKA: A Brand-new Coder)

    ![ABCoder](images/ABCoder.png)

    # Overview

    ABCoder, an AI-oriented Code-processing **Framework**, is designed to enhance and extend the coding context for Large-Language-Model (LLM), finally boosting the

    Repocloudwego/abcoder
    TypeMCP Servers
    CategoryCode Review & Refactor
    UpdatedJun 2026
    LicenseApache-2.0
    First seenJul 27, 2026

    Tags

    MCPai-agentai-coding

    Related

    6 picks
    Type
    1. tirth8205 avatarcode-review-graphLocal-first knowledge graph for token-efficient code review through MCP and CLIMCP ServersJul 2026377k27k
    2. repowise-dev avatarrepowiseCodebase intelligence for AI coding agents — graph, git history, docs, decisions, code health.MCP ServersJul 202622k4.3k
    3. aashari avatarmcp-server-atlassian-bitbucketNode.js/TypeScript MCP server for Atlassian Bitbucket. Enables AI systems (LLMs) to interact with workspaces, repositories, and pull requests via tools (list, get, comment, search). Connects AI directly to version control workflows through the standard MCP interface.MCP ServersMar 202612k159
    4. jamubc avatargemini-mcp-toolMCP server for Gemini CLI integrationMCP ServersJul 202611k2.3k
    5. giancarloerra avatarsocraticodeEnterprise-grade (40m+ LOC) codebase intelligence, zero-setup, local & private Plugin/Skill/Extension or MCP: hybrid semantic search, polyglot dependency graphs, symbol-level impact analysis & call-flow, interactive HTML viewer, cross-project & branch-aware search, DB/API/infra…MCP ServersJul 20269.7k3.2k
    6. chayan-1906 avatargithub-mcpProduction-ready Model Context Protocol server providing Claude with complete GitHub integration - comprehensive tools for repository management, branch operations, file handling, issue tracking, and collaboration features with OAuth 2.0 authentication and MongoDB persistence.MCP ServersJun 20267.5k5