Choose theme
AI Resources
CodeGraphContext
CodeGraphContext builds a searchable map of how files, functions, classes, imports, and calls connect across a repository.
Developers can query that map from the command line, connect it to compatible AI assistants through MCP, use it over HTTP, or inspect it in a browser. The index can stay with one project, combine several repositories, and use embedded or remote graph storage. Use this as a first read, not a recommendation. Open the original project before trusting details like terms, limits, privacy, cost, setup, or safety.
What it is
A persistent map of a codebase
CodeGraphContext parses files and records functions, classes, imports, calls, inheritance, and other structural relationships in a graph that can be queried after the initial index is built.
Why it stands out
One graph, several ways to use it
The same repository map can support direct CLI analysis, MCP requests from compatible AI tools, HTTP queries, and a browser-based graph visualizer instead of being tied to one coding assistant.
Availability
Packaged tool with public docs and source
The official materials include Python installation paths, embedded and remote database options, setup and troubleshooting guides, tests, release history, portable graph bundles, and an MIT-licensed repository.
Why it matters
What makes it useful
Large repositories are hard to understand through file search alone. CodeGraphContext gives developers and coding agents a reusable map of calls, imports, inheritance, and other relationships, so they can trace how a change may move through the codebase before editing it.
What to know
Where it fits
It fits technically oriented workflows that need more than a one-off code search: repository onboarding, call-chain tracing, dependency review, multi-repository analysis, or a shared context layer for MCP-connected coding tools.
Notable points
What stands out
The project supports embedded storage for local use and remote graph databases for larger or shared setups. Its documentation also describes global, per-repository, and named contexts, plus exported graph bundles that can be moved without rebuilding the original index.
Before using
What to review
Which context mode should hold the index. A global or named context can combine several repositories, while per-repository mode keeps each graph separate.
Which files and folders should be excluded through .cgcignore before indexing a private, generated, or unusually large codebase.
Where graph data, configuration, logs, and database credentials are stored, especially when using a remote FalkorDB or Neo4j backend instead of an embedded database.
Whether the selected Python version and database driver have a ready installation path on the intended operating system. The troubleshooting guide notes extra build requirements for some KuzuDB installations and platform limits for FalkorDB Lite.
Treat relationship and call-graph results as code-analysis output to verify against the repository, especially for dynamic language behavior or before making a consequential change.
The project’s security policy warns that exported graphs may contain string literals and variable values from indexed code, and recommends reviewing .cgc bundles before sharing them.
Reader fit
Who may find it relevant
Developers who want a persistent repository graph for call paths, dependencies, class relationships, and architecture questions.
Builders connecting local code intelligence to an MCP-compatible coding assistant without committing to one assistant interface.
Teams comparing embedded local graphs with remote or multi-repository graph backends.
Less relevant for readers who want a no-setup hosted coding assistant or only occasional search across a small project.
Editorial note
Why LifeHubber lists it
When another developer or a CI job needs the same repository structure, CodeGraphContext can hand over a pre-parsed .cgc graph for the receiving environment to load, avoiding a fresh parse of the original code. For a repository bundle you intend to share, the project’s security policy recommends enabling REDACT_SECRETS=true before indexing and inspecting the exported .cgc file, because graphs may contain string literals and variable values. Confirm that your chosen version supports the setting and inspect the exported contents before sharing them; enabling an option does not prove that the bundle is free of secrets.
Source links
Source materials
Reader note
Before relying on this entry
LifeHubber lists entries to help readers inspect AI projects, not to endorse them or prove they are safe, suitable, accurate, maintained, or right for a specific use. We do not verify every entry in depth. Before relying on anything listed, review the original materials, terms, privacy practices, limits, and risks that matter for your situation.
What to explore next
Choose the kind of repository map you need.
The useful choice is how you want to build and explore repository context: through a flexible graph engine, a local SQLite-backed agent index, or a guided visual workspace.
More in AI Agents
Keep browsing this category
Explore more AI agent projects.
Paperclip
paperclipai/paperclip
A self-hosted server and dashboard for coordinating agent teams through companies, goals, roles, issues, heartbeats, budgets, approvals, and persistent activity records.
Universal Modder
rehan-remade/universal-modder
Agent skills and a Python CLI for PC game modding, with engine research, generated assets, in-game checks, and shared field notes. Setup and compatibility depend on the game and workflow; fal generation requires a separate API key.
Onyx
onyx-dot-app/onyx
A self-hostable AI workspace for connected knowledge, search, agents, and actions, with Lite and Standard deployment modes, multiple model providers, granular sharing, and active v4 admin tooling.
For project maintainers
Listed here? You can use the badge.
If you maintain a project with a current LifeHubber listing, you may add the optional “Listed on LifeHubber AI Resources” badge to its README, docs, or website. No introduction or permission request is needed.
