Choose theme
AI Resources
CodeGraph
CodeGraph is a local codebase knowledge graph for coding agents.
The repository presents CodeGraph as a local, auto-updating code intelligence layer for coding agents, with a Rust parsing engine, MCP tools, symbol relationships, call graphs, framework-aware routes, and a SQLite-backed index. 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
Local semantic code context
CodeGraph builds a local index of a repository so coding agents can ask for code structure, related symbols, callers, callees, and impact information instead of repeatedly scanning files from scratch.
Why it stands out
Agent-oriented repository understanding
The installer can connect CodeGraph to several coding agents, while each project keeps its own local graph and updates it as files change.
Availability
Standalone and npm setup paths
The public materials include standalone installers that do not require Node.js, an npm option, agent wiring, documentation, tests, language notes, and benchmark methodology.
Why it matters
What makes it useful
Coding agents need repository context before they can make useful changes. CodeGraph gives them a local map of symbols, call paths, routes, and likely impact, then keeps that map in step with file changes.
What to know
Where it fits
Use the graph alongside a coding agent when a change crosses several files or an HTTP route depends on middleware and handlers. Text search still finds words; the graph is for following relationships between those pieces.
Notable points
What stands out
The current project uses a native Rust parsing engine, supports more than 20 languages, auto-syncs file changes, and publishes benchmark details. Its own measurements also warn that dense graph results can leave more context in a long-running chat even when total processing falls.
Before using
What to review
How the installer changes agent configuration files, how to reverse those changes, and which project folders will receive a local index.
The benchmark methodology and project-reported savings before applying the cost, token, time, or tool-call numbers to a different repository.
The extra context that graph results may leave in a long session, especially when the available context window is small.
Which languages, frameworks, routes, and code-search patterns match the repositories the reader actually works with.
Usage telemetry and cached update checks are separate outgoing connections documented by the project. A local repository index does not mean every part of the tool stays offline.
The v1.6.2 release asks users to re-index projects because many fixes are written during indexing. Upgrading the tool alone does not establish that an existing stored graph contains those corrections.
Reader fit
Who may find it relevant
Readers using coding agents such as Claude Code, Codex, Cursor, OpenCode, or Hermes Agent.
Builders who want local codebase context, call graphs, impact analysis, or route-aware repository maps for agent work.
Less relevant for readers looking mainly for a general chatbot, hosted coding assistant, or non-code RAG system.
Editorial note
Why LifeHubber lists it
For a series of changes to one repository, CodeGraph's graph responses can flag files awaiting index updates, so the agent can return to the changed source while keeping the graph available for the surrounding code structure. To decline usage reporting, the project documents codegraph telemetry off. Update checks are a separate choice: CODEGRAPH_NO_UPDATE_CHECK=1 disables those requests, while DO_NOT_TRACK=1 covers both. These settings belong to CodeGraph; they do not change the coding agent’s model provider or its data handling.
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
Compare how coding agents map a repository.
CodeGraph uses a local database and MCP tools. These alternatives show a file-based graph and another persistent code-map approach.
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.
MiroFish
666ghj/MiroFish
A document-based multi-agent simulation project that builds personas, runs simulated social activity, and produces reports and agent conversations. Its application requires a model API and Zep Cloud; generated scenarios do not establish real-world outcomes.
Magpie
yetone/magpie
A local model gateway and configuration app for supported coding agents, with provider choices, routing groups, saved profiles, and usage views. It changes agent settings and can discover existing subscription sign-ins. Requests go to the chosen provider, and released builds send a daily user-count event unless disabled.
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.
