Clone git repos, index local folders and web docs into knowledge stores, then search semantically for precise library code, APIs, internals, and configs to inform AI coding agents. Suggest dependencies from package files, manage background indexing jobs, and evaluate agent performance on library queries.
npx claudepluginhub chris-xperimntl/agent-knowledgeIndex a local folder of reference material
Clone and index a library source repository
Multi-tool orchestration patterns for BK operations
Cancel a background job
Check status of background operations
Crawl web pages with natural language control and add to knowledge store
Diagnose plugin issues and get fix instructions
Evaluate agent quality across three modes — without BK, BK grep-only, and BK full
Check health of all stores (path existence, model compatibility)
Re-index a knowledge store
Library and dependency expert. ALWAYS invoke this skill when working with third-party libraries, frameworks, or dependencies — including debugging dependency errors, planning code that uses external packages, checking API signatures, or understanding library internals. Do not grep node_modules, vendor directories, or rely on training data for library questions directly — use this skill first.
Delete a knowledge store and all associated data
Optimize BK search with intent, detail level, and store filtering
Search indexed library sources
Toggle skill auto-activation on/off or configure individual skills
Install or update the agent-knowledge statusline module
Create, index, and manage BK stores
List all indexed library stores
Suggest important dependencies to add to knowledge stores
Sync stores from definitions config (bootstrap on fresh clone)
Run comprehensive plugin validation test suite
Launch the admin web UI to browse stores, search, and manage knowledge
Remove Agent Knowledge data from this project
When to use BK vs Grep/Read for current project
Document search with hybrid BM25/semantic retrieval, GraphRAG knowledge graphs, and pluggable providers for Claude Code. Index documentation and code, then search using keyword matching, semantic similarity, graph relationships, or comprehensive multi-mode fusion.
Share bugs, ideas, or general feedback.
Multi-agent knowledge hub plugin. Bundles CLI-backed ask/refresh slash commands and the agent-repo-init skill.
CodeAlive context engine for semantic code search and AI-powered codebase Q&A. Enables AI coding agents to understand entire codebases beyond just open files — search across all indexed repositories, trace cross-service dependencies, discover usage patterns, and get synthesized answers to architectural questions. Includes a lightweight code exploration subagent, authentication hooks, and multiple search modes (fast lexical, semantic, and deep cross-cutting). Works standalone or alongside the CodeAlive MCP server for direct tool access via the Model Context Protocol.
Optimized file search, semantic indexing, and persistent memory for Claude Code — with optional sync to a self-hosted web dashboard
Codebase search and context retrieval using hybrid semantic/lexical search with neural reranking
Persistent project memory for AI coding agents — semantic search, AST-aware chunking, dependency graphs, and conversation history