Skillget

augmented-codebase-indexer

mcp
Guvenlik Denetimi
Uyari
Health Uyari
  • No license — Repository has no license file
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Community trust — 87 GitHub stars
Code Gecti
  • Code scan — Scanned 12 files during light audit, no dangerous patterns found
Permissions Gecti
  • Permissions — No dangerous permissions requested
Purpose
This tool provides semantic code search capabilities for your local codebase by using tree-sitter parsing and vector embeddings. It allows developers and AI agents to ask natural language questions and receive precise, line-number-specific code references.

Security Assessment
Overall Risk: Medium. The code scan found no dangerous patterns, hardcoded secrets, or suspicious permission requests. However, the tool inherently processes your local source code and requires an active network connection to function. It makes external network requests to an OpenAI-compatible API to generate vector embeddings, meaning your code snippets will be transmitted to a third-party embedding provider. Additionally, it relies on Qdrant for vector storage, which runs locally via Docker or in the cloud. It does not appear to execute arbitrary shell commands beyond standard indexing operations.

Quality Assessment
The project is in active development (last updated today) and demonstrates good community interest with 87 GitHub stars. The codebase is lightweight, with 12 files scanned during the audit. A major drawback is the complete absence of a license file, meaning the software is strictly proprietary by default. This lack of licensing creates legal ambiguity and may restrict how you can legally use, modify, or distribute the tool in commercial projects.

Verdict
Use with caution — the code itself appears safe and clean, but be aware of the external data transmission to embedding APIs and the legal restrictions imposed by the missing software license.
SUMMARY

Semantic level code search/indexer with tree-sitter parsing, Qdrant vector store, and Typer/FastAPI interfaces. Supports calling via MCP.

README.md

ACI — Augmented Codebase Indexer

Tests
Python
linux.do

Language: English | 简体中文

Ask your codebase a question. Get a precise answer — down to the line.

ACI indexes your code with embeddings and Tree-sitter AST parsing, then lets you search it with natural language. Results come back with exact file paths and line numbers, not just fuzzy matches.

$ aci search "function that validates JWT tokens"

src/auth/middleware.py:42  verify_token(token: str) -> Claims
src/auth/utils.py:118      decode_and_validate(raw: str) -> dict

Why ACI?

Most code search tools give you grep or a fuzzy filename match. ACI gives you semantic understanding:

  • You describe intent, it finds the implementation
  • Hybrid search combines embeddings with keyword/grep for precision
  • Multi-level indexing: raw chunks, function summaries, class summaries, file summaries
  • Incremental updates — only re-indexes what changed
  • Works with Python, JavaScript/TypeScript, Go, Java, C, C++

Get Started

# Install
uv sync

# Configure (add your embedding API key)
cp .env.example .env

# Index your codebase
aci index /path/to/your/project

# Search
aci search "error handling in the HTTP layer"

That's it. See Installation for full setup details.

Interfaces

Interface Command Use case
CLI aci <command> Day-to-day search and indexing
Interactive shell aci shell Iterative exploration sessions
HTTP API aci serve Integrate with other tools
MCP server aci-mcp LLM / agent integration

Documentation

MCP — Let Your LLM Search the Code

ACI ships a first-class MCP server so agents can index and search your codebase directly.

{
  "mcpServers": {
    "aci": {
      "command": "uv",
      "args": ["run", "aci-mcp"],
      "cwd": "/path/to/your/project"
    }
  }
}

For Docker-based deployment (recommended for agentic tools), see MCP Integration.

Requirements

  • Python 3.10+
  • Qdrant (auto-started locally via Docker, or point to Qdrant Cloud)
  • Any OpenAI-compatible embedding API (OpenAI, SiliconFlow, etc.)

Development governance: AGENTS.md

Yorumlar (0)

Sonuc bulunamadi