[opensourcedex]

SocratiCode is a free, open source ai interaction & interfaces project written in TypeScript and released under AGPL-3.0. It has 3,308 GitHub stars, 422 forks and 1 open issues, and was last pushed 4 hours ago. On this registry it ranks #52 of 76 tracked projects in AI Interaction & Interfaces, with 5 head-to-head comparisons available. It gained 4 stars over the last 3 tracked days.

What is SocratiCode?

What it is

SocratiCode is an open-source codebase context engine for AI assistants, available as a plugin, skill, extension, or MCP server. It lives in the AI and machine-learning ecosystem, uses TypeScript, and is licensed under AGPL-3.0. The project targets local and private codebase understanding, with claims of operation up to and over 40 million lines of code.

It solves the problem of AI assistants inspecting code through repeated searches and large context windows, which can be slow and token-heavy. SocratiCode builds an index of code, dependencies, symbols, and related artifacts, then lets an assistant query that index instead of scanning files directly. It is designed for zero configuration, automatic indexing, and local use by default, with optional cloud embedding and vector database support.

Key capabilities

  • It provides hybrid semantic search and BM25 search fused with RRF for code retrieval.
  • It builds polyglot dependency graphs across 18 languages, with circular-dependency visualisation and interactive HTML exploration.
  • It performs symbol-level impact analysis, including blast-radius and call-flow tracing, to show how changes affect code.
  • It indexes searchable context artifacts such as database schemas, API specifications, infrastructure configurations, and architecture documents.
  • It supports cross-project, branch-aware, and multi-repo search, with a file watcher that keeps the index updated.

Who uses it and how

  • Developers using MCP hosts that support local stdio servers can connect SocratiCode to an AI assistant for repository-aware questions.
  • Teams in large or multi-repo codebases can use branch-aware and cross-project search to ask about symbols, dependencies, and impact.
  • Engineers reviewing architectural changes can use the HTML graph explorer and impact analysis to trace call flow and blast radius.
  • AI agents can share a single index across multiple agents working on the same codebase, with automatic coordination.

Getting started

Typical use is through Docker with an MCP host that supports local stdio servers, or through supported plugin and extension integrations. The README also mentions cloud options for embeddings with OpenAI or Google Gemini and Qdrant when configured.

When to use it — and when not to

SocratiCode is useful when a team wants a local, private, zero-configuration index for codebase intelligence and can operate Docker, an MCP host, or a supported plugin integration. It is less suitable when a user cannot run Docker, does not use an MCP-compatible host, or needs a fully hosted service without waiting for the private-beta cloud option. The README reports benchmark results on VS Code with 2.45 million lines, including 61% less context, 84% fewer tool calls, and 37x faster than grep-based exploration, but those figures are project-provided and may vary.

project readme (upstream, from github) — read inline

SocratiCode

CI License: AGPL-3.0 npm version Node.js >= 18.17 GitHub stars MCP Toplist rank Discord

Install Claude Code Plugin VS Code Marketplace Open VSX Install in VS Code Install in VS Code Insiders Install in Cursor

"There is only one good, knowledge, and one evil, ignorance." — Socrates

Your AI reads code. SocratiCode understands it.

The open-source codebase context engine: give any AI instant automated knowledge of your entire codebase (and infrastructure) — at scale, zero configuration, fully private, completely free.

Kindly sponsored by Altaire Limited

🛡️ Need MCP governance together with codebase context? See our sibling project JanuScope — the local-first MCP policy proxy: tool blocking, SQL-mutation gate, PII redaction, audit, rate-limit.

If SocratiCode has been useful to you, please ⭐ star this repo — it helps others discover it — and share it with your dev team and fellow developers!

💬 Questions or just want to chat? Join us on Discord.

☁️ SocratiCode Cloud (private beta) — Hosted, shared team index built on the same engine as the open-source version, plus SSO, audit logs, branch-aware indexing, and VPC / air-gapped deployment options. The open-source core remains free forever. Request early access →

One thing, done well: deep codebase intelligence with zero setup, no bloat, and full automation. SocratiCode gives AI assistants deep semantic understanding of your codebase: hybrid search, cross-project search, polyglot code dependency graphs, symbol-level impact analysis and flow, interactive HTML graph explorer for visual navigation, and searchable context artifacts (database schemas, API specs, infra configs, architecture docs). Zero configuration: add it to an MCP host that supports local stdio servers, or use a supported plugin or extension. It manages everything automatically.

Production-ready, battle-tested on enterprise-level large repositories (up to and over ~40 million lines of code). Batched, automatic resumable indexing checkpoints progress — pauses, crashes, restarts, and interruptions don't lose work. The file watcher keeps the index automatically updated at every file change and across sessions. Multi-branch, multi-repo and multi-agent ready — multiple AI agents can work on the same codebase simultaneously, sharing a single index with automatic coordination and zero configuration.

Private and local by default — Docker handles everything, no API keys required, no data leaves your machine. Cloud ready for embeddings (OpenAI, Google Gemini) and Qdrant, and a full suite of configuration options are all available when you need them.

Code intelligence that belongs to you, AI and host agnostic — your codebase's understanding lives with the code, not locked to any one assistant, IDE or model. And because SocratiCode pre-computes the hard parts (blast radius, call-flow, dependency traversal), smaller models can handle architectural complex tasks that would otherwise need top-tier reasoning, saving even more on token cost.

The first Qdrant‑based MCP/Claude Plugin/Skill that pairs auto‑managed, zero‑config local Docker deployment with AST‑aware code chunking, hybrid semantic + BM25 (RRF‑fused) code search, polyglot dependency graphs with circular‑dependency visualisation, symbol‑level Impact Analysis (blast‑radius & call‑flow tracing across 18 languages), and searchable infra/API/database artifacts in a single focused, zero-config and easy to use code intelligence engine.

Benchmarked on VS Code (2.45M lines): SocratiCode uses 61% less context, 84% fewer tool calls, and is 37x faster than grep‑based exploration — tested live with Claude Opus 4.6. See the full benchmark →

Contents

Quick Start

Requirements: Node.js 18.17 or newer with npx on PATH, plus Docker running for the default local Qdrant and Ollama stack.

Quick install guidance for Claude Code, VS Code, and Cursor:

Install Claude Code Plugin Install in VS Code Install in VS Code Insiders [Install in Cursor](cursor://anysphere.cursor-deeplink/mcp/install?name=socraticode&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsIi0tcHJlZmVyLW9ubGluZSIsInNvY3JhdGljb2RlQGx

readme truncated — read the full docs on github

Frequently asked questions

Is SocratiCode free to use?

SocratiCode is open source under the AGPL-3.0 licence. There is no licence fee and no seat count — you can self-host it or, where the project offers one, pay a vendor for a managed version instead.

What does SocratiCode do?

Enterprise-grade (40m+ LOC) codebase intelligence, zero-setup, local & private Plugin/Skill/Extension or MCP: hybrid semantic search, polyglot dependency graphs

What is SocratiCode written in?

SocratiCode is primarily written in TypeScript. Its source is publicly available at https://github.com/giancarloerra/SocratiCode, and it has 3,308 GitHub stars.