codebase-context and codebase-mcp

These are competitors—both provide local-first codebase indexing and semantic search to augment LLMs with project context, but through different integration protocols (PatrickSys uses a custom agent interface while danyQe implements the MCP standard).

codebase-context
55
Established
codebase-mcp
37
Emerging
Maintenance 13/25
Adoption 7/25
Maturity 18/25
Community 17/25
Maintenance 6/25
Adoption 7/25
Maturity 9/25
Community 15/25
Stars: 33
Forks: 8
Downloads: —
Commits (30d): 0
Language: TypeScript
License: MIT
Stars: 37
Forks: 7
Downloads: —
Commits (30d): 0
Language: Python
License: Apache-2.0
No risk flags
No Package No Dependents

About codebase-context

PatrickSys/codebase-context

Local-first Second brain for AI agents working on your codebase - detects your team coding conventions and patterns, brings in persistent memory, code-generation checks, and hybrid search with evidence scoring. Exposed through CLI and MCP server.

Combines semantic and syntactic search with git history analysis to surface coding patterns alongside results, enabling agents to detect adoption trends and identify "golden files" as architectural exemplars. Automatically extracts team decisions from conventional commits and surfaces them with confidence-decay scoring across sessions, preventing regressions on deliberate architectural choices. Supports stdio transport for single-client integrations (Claude Desktop, VS Code Copilot) and HTTP mode for multi-client setups, with built-in routing for monorepo workflows.

About codebase-mcp

danyQe/codebase-mcp

Open-source AI development assistant via Model Context Protocol (MCP). Turn Claude or any LLM into your personal coding assistant. Privacy-first with local semantic search, AI-assisted editing, persistent memory, and quality-checked code generation. Built for Python & React. Free alternative to paid AI coding tools.

Based on the README, here's a technical summary that goes beyond the GitHub description: Implements a FastAPI backend server that exposes 13+ MCP tools via stdio transport, with a local FAISS vector index for sub-second semantic code search and persistent memory storage via SQLite. Leverages Google's free Gemini API exclusively for AI-assisted code edits while keeping all other operations local—semantic search, memory recall, and file writing happen entirely on-device.

Related comparisons

codebase-context and code-assistant

Scores updated daily from GitHub, PyPI, and npm data. How scores work