Repository intelligence

giancarloerra/SocratiCode

GitHub

Tired of AI tools hallucinating about your codebase or burning through your API quota? SocratiCode flips the script with local-first, privacy-safe codebase intelligence that handles 40M+ lines of code without breaking a sweat. It delivers hybrid semantic search, dependency graphs, and impact analysis that devs actually need — all while cutting tokens by 61% and calls by 84%. Whether you're on Claude, Gemini, or rolling your own setup, this tool speaks your language.

CLOUDM0N decision
REVIEW BEFORE ADOPTION
Trust REVIEW · 55/100
Good fit if

Teams whose requirements match this repository’s core capability.

Watch out for

Review deployment and security evidence before production adoption.

Practical intelligence

What matters before you adopt it

Best for
Teams whose requirements match this repository’s core capability.
Main trade-offs
Review deployment and security evidence before production adoption.
Trust & CVEs

Security evidence without the noise

Trust remains a decision signal; CVEs and scanner evidence explain what is driving the risk.

Security findings
3
CLOUDM0N scanner findings
Critical
0
High
1
Medium
2
Low
0
View trust evidence & security findings
Why this score
No trust rationale was stored for this scan.
CLOUDM0N findings
HIGH
4 high severity dependency vulnerability/vulnerabilities reported by npm audit.
MEDIUM
The project can spawn operating-system processes; review command construction and input handling. 5 sample match(es) found.
MEDIUM
Broad permission or elevated-command pattern detected. 5 sample match(es) found.
Architecture from code11 modules · 11 edges
Structural evidence

Modules and dependency edges extracted from repository code. This is code evidence, not README inference.

Code files
133
Modules
11
Dependency edges
11
Core modules
(root)
1 files
extension
10 files
scripts
3 files
src
4 files
src/assets
4 files
src/services
services
36 files
src/tools
tool implementations
5 files
Dependency flow
scriptssrc
scriptssrc/services
srcsrc/services
srcsrc/tools
src/servicessrc
src/toolssrc
src/toolssrc/services
Detected languages
TypeScript · JavaScript
Detected frameworks
MCP SDK · OpenAI SDK · Vitest · Zod
Architecture evidence details
flowchart TD
    %% socraticode — high-level architecture (DRAFT, refine me)
    n0["(root) · 1 file"]
    n1["extension · 10 files"]
    n2["scripts · scripts · 3 files"]
    n3["src · 4 files"]
    n4["src/assets · 4 files"]
    n5["src/services · services · 36 files"]
    n6["src/tools · tool implementations · 5 files"]
    n7["tests · tests · 70 files"]
    n2 --> n3
    n2 --> n5
    n2 --> n7
    n3 --> n5
    n3 --> n6
    n5 --> n3
    n6 --> n3
    n6 --> n5
    n7 --> n3
    n7 --> n5
    n7 --> n6
    class n5 api
    class n2 infra
    class n6 shared
    class n7 test
    classDef api fill:#af7aa1,color:#ffffff,stroke:#8a5f7f
    classDef infra fill:#b35c00,color:#ffffff,stroke:#8f4a00
    classDef shared fill:#79706e,color:#ffffff,stroke:#5d5654
    classDef test fill:#499894,color:#ffffff,stroke:#397975
Agent handoff
Use with any agent
JSON API
Alternatives

Nearby repositories worth comparing before adoption.

Compare top options →
codebase-memory-mcp
DeusData/codebase-memory-mcp
71
Fit

This MCP server transforms how developers interact with codebases by building a persistent knowledge graph that indexes repositories in milliseconds across 155 programming languages. With sub-millisecond query speeds and 99% token reduction, it enables AI coding assistants like Cursor, Claude Code, and Windsurf to understand your entire codebase context without drowning in context windows. Built as a single static binary with zero dependencies, it runs anywhere.

Trust REVIEW · 55
Compare →
jcodemunch-mcp
jgravelle/jcodemunch-mcp
17
Fit

jcodemunch-mcp is the ultimate token-saver for AI-powered code exploration! By leveraging tree-sitter AST parsing, this MCP server lets you dive deep into GitHub repositories without burning through your token budget. Built for developers who want smarter, leaner AI interactions with source code—perfect for code review, refactoring analysis, and understanding unfamiliar codebases fast.

Trust FAIL · 25
Compare →
headroom
headroomlabs-ai/headroom
63
Fit

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

Trust REVIEW · 45
Compare →