awesome-repositories.com
Blog
MCP
awesome-repositories.com

Discover the best open-source repositories with AI-powered search.

ExploreCurated searchesOpen-source alternativesSelf-hosted softwareBlogSitemap
ProjectMCP serverAboutHow we rankPress
LegalPrivacyTerms
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
DeusData avatar

DeusData/codebase-memory-mcp

0
View on GitHub↗
deusdata.github.io/codebase-memory-mcp↗

Codebase Memory Mcp

codebase-memory-mcp is a Model Context Protocol server that indexes source repositories into a persistent code knowledge graph, giving AI coding agents a queryable map of symbols, call paths and architecture so they read fewer files. Parsing uses bundled tree-sitter grammars covering more than 160 languages, and a built-in type layer links calls to their true definitions without a separate language server. Everything runs locally, with no cloud service or API key.

Beyond the core graph, it offers read-only Cypher-style queries that return clear errors for unsupported syntax, and semantic code search that combines bundled embeddings, full-text ranking and structural filters. It maps code changes to affected symbols and their blast radius, finds dead code, and selects which tests a change reaches, falling back to broader runs when evidence is weak. It also links services across repositories over HTTP, gRPC, GraphQL, tRPC and messaging channels, and connects Kubernetes, Terraform, Docker and similar configuration back to source.

Agent setup is automated: the tool detects supported coding clients and installs their server connections, instructions, skills, profiles and fail-open hooks that never block a tool call. A shared per-account background daemon watches files and re-indexes only what changed, while any tool can also be run as a one-shot command-line call with compact or JSON output. Teams can commit a compressed graph snapshot beside the source so teammates index only their local differences.

Additional features include architecture summaries with functional clustering, persistent architecture decision records, documentation linked to the code it mentions, index coverage reporting, and a local browser interface for exploring source, call paths and architecture maps.

Features

  • Code Knowledge Graphs - Stores source symbols, calls and relationships in a persistent graph that agents query for structure instead of rereading raw files.
  • Code Context Servers - Serves a live index of the codebase to coding agents through MCP, command-line calls and hooks so they read fewer files.
  • AI Coding Agent Platforms - Gives AI coding agents a persistent, queryable map of symbols, call paths and architecture so they read fewer files.
  • Tree-Sitter Parsers - Parses source files in more than 160 languages into syntax trees using bundled tree-sitter grammars, with no external language servers.

AI search

Explore more awesome repositories

Describe what you need in plain English — the AI ranks thousands of curated open-source projects by relevance.

Start searching with AI
48,292 stars·3,992 forks·C·MIT·1 view
  • Change Impact Analysis - Maps code changes to affected symbols and their blast radius, and selects which tests a change reaches.
  • Non-Blocking Agent Context Hooks - Offers optional agent hooks that add matching graph symbols as context and never block a tool call, even on failure.
  • Hybrid Semantic Search Tools - Combines bundled semantic embeddings with full-text ranking and structural filters so meaning-based code search runs fully on the local machine.
  • Graph Database Queries - Runs read-only Cypher-style graph queries with filtering, aggregation and variable-length paths, returning clear errors for unsupported syntax.
  • Git-Backed Snapshot Sharing - Exports a compressed graph snapshot beside the source so teammates import a shared baseline and index only their local differences.
  • Cypher Engines - Runs a read-only openCypher-style engine with filters, aggregation and variable-length paths, rejecting writes and unsupported syntax with clear errors.
  • Code Search - Finds symbols and code with structural filters, keyword ranking and embedding-based queries, returning ranked results with surrounding context.
  • Semantic Code Search Engines - Runs meaning-based and structural code search locally using bundled embeddings and full-text ranking, with no cloud service or API key.
  • Model Context Protocol Servers - Detects supported coding clients and installs server connections, instructions, skills, profiles and fail-open hooks automatically.
  • Shared Code Index Daemons - Runs one per-account background daemon shared by all connected agents, owning file watchers and indexing jobs and re-indexing only changed files.
  • Cross-Repository Indexes - Matches HTTP routes, gRPC, GraphQL and publish-subscribe channels to their callers and joins multiple indexed repositories into one cross-repository view.
  • Local Code Indexers - Runs a local background indexer that builds a persistent, searchable graph of code structure, with all analysis on the local machine.
  • Source Code Call Path Tracing - Follows callers, callees, data flow and cross-service paths through the graph to show how a symbol is reached and what it depends on.
  • Multi-Language Code Parsers - Parses source code across more than 160 languages into structural symbols and syntax trees, with no external language servers needed.
  • Infrastructure-to-Code Mapping - Connects Kubernetes, Helm, Terraform, Docker, Compose and CI configuration to source code so a service can be traced to the program its container runs.
  • Service Boundary Detection - Matches HTTP routes to call sites and detects gRPC, GraphQL, tRPC and publish-subscribe channels to connect services into one cross-service graph.
  • Codebase Architecture Visualizers - Produces a compact architecture overview of languages, packages, routes, hotspots and cycles, grouping code into functional modules via community detection.
  • Cross-Repository Service Linking - Connect multiple indexed repositories and trace service relationships over HTTP, gRPC, GraphQL, tRPC, and asynchronous patterns, optionally adding relationships observed in runtime traces.
  • Call-to-Definition Binding - Provides a built-in type layer covering imports, generics and inheritance that links each call to its true definition without a language server.
  • Cross-Repository Dependency Mapping - Links services across repositories over HTTP, gRPC, GraphQL, tRPC and messaging channels, tracing how they communicate and affect each other.
  • Change-Based Test Selection - Selects affected tests by combining static reachability, changed tests and per-test coverage, falling back to a full run when evidence is doubtful.
  • Context Delivery & Compaction - Code intelligence MCP server full-indexing repositories into a knowledge graph.
  • Agent Context and Memory - High-performance codebase intelligence engine and MCP server.

    • Star history

    Star history chart for deusdata/codebase-memory-mcpStar history chart for deusdata/codebase-memory-mcp

    How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.

    Frequently asked questions

    What does deusdata/codebase-memory-mcp do?

    codebase-memory-mcp is a Model Context Protocol server that indexes source repositories into a persistent code knowledge graph, giving AI coding agents a queryable map of symbols, call paths and architecture so they read fewer files. Parsing uses bundled tree-sitter grammars covering more than 160 languages, and a built-in type layer links calls to their true definitions without a separate language server. Everything runs locally, with no cloud service or API key.

    What are the main features of deusdata/codebase-memory-mcp?

    The main features of deusdata/codebase-memory-mcp are: Code Knowledge Graphs, Code Context Servers, AI Coding Agent Platforms, Tree-Sitter Parsers, Change Impact Analysis, Non-Blocking Agent Context Hooks, Hybrid Semantic Search Tools, Graph Database Queries.

    Which projects share features with deusdata/codebase-memory-mcp?

    Projects with overlapping indexed features include: cocoindex-io/cocoindex-code — Cocoindex is a command-line code search engine and indexing tool that combines abstract syntax tree pattern matching… cocoindex-io/cocoindex — Cocoindex is an incremental data processing engine that builds and maintains live indexes for AI agents, with a core… colbymchenry/codegraph — Codegraph is a local codebase indexer and static analysis graph database that serves as a context provider for AI… potpie-ai/potpie — Potpie is an LLM codebase analysis platform and multi-agent orchestration framework designed to act as an AI software… chopratejas/headroom — Headroom is an AI gateway proxy and token optimizer designed to reduce the cost and latency of large language model… etsy/hound — Hound is a self-hosted source code search engine designed to index multiple repositories for high-performance regular…

    Projects sharing features with Codebase Memory Mcp

    These projects share indexed features with Codebase Memory Mcp. Shared tags can include platform or build tooling; verify the primary use case before treating a result as a replacement.
    • cocoindex-io/cocoindex-codecocoindex-io avatar

      cocoindex-io/cocoindex-code

      1,962View on GitHub↗

      Cocoindex is a command-line code search engine and indexing tool that combines abstract syntax tree pattern matching and semantic vector embeddings for precise code discovery. It functions locally and integrates with AI coding assistants to automatically retrieve necessary codebase context through standardized communication protocols and persistent background daemon services. The platform employs an asymmetric embedding architecture that generates vector representations using separate parameters for document indexing and search queries. It supports incremental index maintenance by tracking fi

      Pythonagentsastcocoindex
      View on GitHub↗1,962
    • cocoindex-io/cocoindexcocoindex-io avatar

      cocoindex-io/cocoindex

      11,832View on GitHub↗

      Cocoindex is an incremental data processing engine that builds and maintains live indexes for AI agents, with a core focus on codebase indexing and knowledge graph extraction. The engine uses a function-graph execution model where user-defined Python functions are composed into a directed acyclic graph, and it processes data incrementally so only changed source records or code paths are re-computed, avoiding full recomputation at any scale. It supports automatic schema inference from transformation pipeline type annotations and provides full data lineage tracing, tagging every output record wi

      Rustagentic-data-frameworkaiai-agents
      View on GitHub↗11,832
    • colbymchenry/codegraphcolbymchenry avatar

      colbymchenry/codegraph

      77,006View on GitHub↗

      Codegraph is a local codebase indexer and static analysis graph database that serves as a context provider for AI agents. It parses multiple programming languages into a searchable knowledge graph of symbols and dependencies, exposing these relationships to AI tools through the Model Context Protocol. The project distinguishes itself by aggregating relevant code snippets and symbol flows to reduce token usage for large language models. It automates the configuration of server settings and steering instructions across various AI agent platforms and command line editors to enable automatic code

      TypeScript
      View on GitHub↗77,006
    • potpie-ai/potpiepotpie-ai avatar

      potpie-ai/potpie

      5,161View on GitHub↗

      Potpie is an LLM codebase analysis platform and multi-agent orchestration framework designed to act as an AI software engineer. It parses repositories into a structured code knowledge graph, enabling AI agents to perform multi-hop reasoning, dependency tracing, and grounded technical analysis across large codebases. The system distinguishes itself through a spec-driven development framework where agents generate detailed technical specifications and architecture plans before implementing multi-file code changes. It utilizes a durable execution engine to coordinate specialized AI personas for

      Pythonagentsai-agentsai-agents-framework
      View on GitHub↗5,161
    Compare all 30 related projects→