activeloopai avatar

Hivemind Graph

A persistent AST-derived graph of your repo that answers "what calls this?" and "where is X defined?" without grepping or building anything. It lives as synthetic files under a Deeplake mount and rebuilds automatically on session boundaries. Start with query/ for search plus one-hop expansion, use impact/ to see the blast radius of a change, or path/ to trace dependencies across files. Covers TypeScript, JavaScript, and Python with resolved cross-file calls for named imports. The graph shows structure and location, not source, so you still need to Read the actual files to answer. Instance methods and dynamic calls aren't tracked, so zero incoming edges doesn't prove dead code. It can lag uncommitted edits, but for navigating unfamiliar codebases or scoping refactors it beats sequential file reading.

GitHub stars
1.1K
last updated
Jun 11, 2026

Install

$ npx -y skills add activeloopai/hivemind --skill hivemind-graph --agent claude-code

Installs into .claude/skills of the current project.

Files

Hivemind Code Graph

A deterministic, AST-derived map of the current repository — every function, class, method, interface, type, enum, const, and module, plus the edges between them (calls, imports, extends, implements, method_of). It is queried as synthesized files under the Deeplake mount; there are no real files on disk and no network call in the read path.

The graph builds and refreshes automatically (on Stop / SessionEnd, gated by a rate limit + git diff). You never run a build command — just read it.

Use it as a fast INDEX to locate the few files/symbols that matter, then open them with Read to answer. It is not a substitute for the source.

When to use this skill

Activate when the user asks a structural / relational question about the code:

  • "What calls pushSnapshot?" / "Who uses this function?"
  • "What does deeplake-pull.ts import?" / "What depends on X?"
  • "Where is GraphSnapshot defined?" / "Find the function that handles Y."
  • "What are the main subsystems / the architecture here?"
  • "If I change this signature, what's affected?" → use impact/<symbol> (transitive blast radius)

When NOT to use this skill

Sponsors

Details

Repository
github.com/activeloopai/hivemind
Categories
DevOps & CI/CD, Code Review & Quality
License
Apache-2.0
First seen
Jun 11, 2026

More from activeloopai/hivemind

All 4
1agentworkforce avatarfrontend-designagentworkforce/relayCreate distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applicat0skills.sh installs
2aj-geddes avatarAnomaly Detectionaj-geddes/useful-ai-promptsIdentify unusual patterns, outliers, and anomalies in data using statistical methods, isolation forests, and autoencoders for fraud detection and quality monito0skills.sh installs
3aj-geddes avatarClassification Modelingaj-geddes/useful-ai-promptsBuild binary and multiclass classification models using logistic regression, decision trees, and ensemble methods for categorical prediction and classification0skills.sh installs
4aj-geddes avatarNatural Language Processingaj-geddes/useful-ai-promptsBuild NLP applications using transformers library, BERT, GPT, text classification, named entity recognition, and sentiment analysis0skills.sh installs
5aj-geddes avatarRecommendation Engineaj-geddes/useful-ai-promptsBuild recommendation systems using collaborative filtering, content-based filtering, matrix factorization, and neural network approaches0skills.sh installs
6aj-geddes avatarRecommendation Systemaj-geddes/useful-ai-promptsBuild collaborative and content-based recommendation engines for product recommendations, personalization, and improving user engagement0skills.sh installs