Help us improve
Share bugs, ideas, or general feedback.
From agent-brain
Searches documents, codebases, and knowledge bases using BM25 keyword, semantic vector, hybrid, graph, and multi retrieval modes for dependencies, relationships, and references.
npx claudepluginhub spillwavesolutions/agent-brain --plugin agent-brainHow this skill is triggered — by the user, by Claude, or both
Slash command
/agent-brain:using-agent-brainThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Expert-level skill for Agent Brain document search with five modes: BM25 (keyword), Vector (semantic), Hybrid (fusion), Graph (knowledge graph), and Multi (comprehensive fusion).
references/api_reference.mdreferences/bm25-search-guide.mdreferences/graph-search-guide.mdreferences/hybrid-search-guide.mdreferences/installation-guide.mdreferences/integration-guide.mdreferences/interactive-setup.mdreferences/provider-configuration.mdreferences/server-discovery.mdreferences/troubleshooting-guide.mdreferences/vector-search-guide.mdreferences/version-management.mdscripts/query_domain.pyInstalls and configures Agent Brain RAG document search system with Ollama or OpenAI/Anthropic providers. Covers pip installs, env vars, project init, server management, and troubleshooting.
Searches, greps, fetches artifacts, and traces call graphs across codebases indexed in CodeAlive. Use for semantic code search, string/regex grep, artifact retrieval, and relationship analysis.
Detects oversized codebases or docs via thresholds like >50 MD files or >200 sources, suggesting qmd for local BM25+vector+LLM semantic search to extend AI context.
Share bugs, ideas, or general feedback.
Expert-level skill for Agent Brain document search with five modes: BM25 (keyword), Vector (semantic), Hybrid (fusion), Graph (knowledge graph), and Multi (comprehensive fusion).
| Mode | Speed | Best For | Example Query |
|---|---|---|---|
bm25 | Fast (10-50ms) | Technical terms, function names, error codes | "AuthenticationError" |
vector | Slower (800-1500ms) | Concepts, explanations, natural language | "how authentication works" |
hybrid | Slower (1000-1800ms) | Comprehensive results combining both | "OAuth implementation guide" |
graph | Medium (500-1200ms) | Relationships, dependencies, call chains | "what calls AuthService" |
multi | Slowest (1500-2500ms) | Most comprehensive with entity context | "complete auth flow with dependencies" |
| Parameter | Default | Description |
|---|---|---|
--mode | hybrid | Search mode: bm25, vector, hybrid, graph, multi |
--threshold | 0.3 | Minimum similarity (0.0-1.0) |
--top-k | 5 | Number of results |
--alpha | 0.5 | Hybrid balance (0=BM25, 1=Vector) |
Searching for exact technical terms:
agent-brain query "recursiveCharacterTextSplitter" --mode bm25
agent-brain query "ValueError: invalid token" --mode bm25
agent-brain query "def process_payment" --mode bm25
Counter-example - Wrong mode choice:
# BM25 is wrong for conceptual queries
agent-brain query "how does error handling work" --mode bm25 # Wrong
agent-brain query "how does error handling work" --mode vector # Correct
Searching for concepts or natural language:
agent-brain query "best practices for error handling" --mode vector
agent-brain query "how to implement caching" --mode vector
Counter-example - Wrong mode choice:
# Vector is wrong for exact function names
agent-brain query "getUserById" --mode vector # Wrong - may miss exact match
agent-brain query "getUserById" --mode bm25 # Correct - finds exact match
Need comprehensive results (default mode):
agent-brain query "OAuth implementation" --mode hybrid --alpha 0.6
agent-brain query "database connection pooling" --mode hybrid
Alpha tuning:
--alpha 0.3 - More keyword weight (technical docs)--alpha 0.7 - More semantic weight (conceptual docs)Exploring relationships and dependencies:
agent-brain query "what functions call process_payment" --mode graph
agent-brain query "classes that inherit from BaseService" --mode graph --traversal-depth 3
agent-brain query "modules that import authentication" --mode graph
Prerequisite: Requires ENABLE_GRAPH_INDEX=true during server startup.
Need the most comprehensive results:
agent-brain query "complete payment flow implementation" --mode multi --include-relationships
GraphRAG enables relationship-aware retrieval by building a knowledge graph from indexed documents.
export ENABLE_GRAPH_INDEX=true
agent-brain start
| Query Pattern | Example |
|---|---|
| Function callers | "what calls process_payment" |
| Class inheritance | "classes extending BaseController" |
| Import dependencies | "modules importing auth" |
| Data flow | "where does user_id come from" |
See Graph Search Guide for detailed usage.
# Index only Python files
agent-brain index ./src --include-type python
# Index Python and documentation
agent-brain index ./project --include-type python,docs
# Index all code files
agent-brain index ./repo --include-type code
# Force full re-index (bypass incremental)
agent-brain index ./docs --force
Use agent-brain types list to see all 14 available presets.
agent-brain folders list # List indexed folders with chunk counts
agent-brain folders add ./docs # Add folder (triggers indexing)
agent-brain folders add ./src --include-type python # Add with preset filter
agent-brain folders remove ./old-docs --yes # Remove folder and evict chunks
Re-indexing a folder automatically detects changes:
--force to bypass manifest and fully re-indexEnrich chunk metadata during indexing with custom Python scripts or static JSON metadata.
# Inject via Python script
agent-brain inject ./docs --script enrich.py
# Inject via static JSON metadata
agent-brain inject ./src --folder-metadata project-meta.json
# Validate script before indexing
agent-brain inject ./docs --script enrich.py --dry-run
Scripts export a process_chunk(chunk: dict) -> dict function:
def process_chunk(chunk: dict) -> dict:
chunk["project"] = "my-project"
chunk["team"] = "backend"
return chunk
docs/INJECTOR_PROTOCOL.md for the full specificationIndexing runs asynchronously via a job queue. Monitor and manage jobs:
agent-brain jobs # List all jobs
agent-brain jobs --watch # Live polling every 3s
agent-brain jobs <job_id> # Job details + eviction summary
agent-brain jobs <job_id> --cancel # Cancel a job
When re-indexing, job details show what changed:
Eviction Summary:
Files added: 3
Files changed: 2
Files deleted: 1
Files unchanged: 42
Chunks evicted: 15
Chunks created: 25
This confirms incremental indexing is working efficiently.
agent-brain init # Initialize project (first time)
agent-brain start # Start server
agent-brain index ./docs # Index documents
agent-brain query "search" # Search
agent-brain stop # Stop when done
Progress Checklist:
/agent-brain:agent-brain-init succeeded/agent-brain:agent-brain-status shows healthy| Command | Description |
|---|---|
/agent-brain:agent-brain-init | Initialize project config |
/agent-brain:agent-brain-start | Start with auto-port |
/agent-brain:agent-brain-status | Show port, mode, document count |
/agent-brain:agent-brain-list | List all running instances |
/agent-brain:agent-brain-stop | Graceful shutdown |
Before querying, verify setup:
agent-brain status
Expected:
Counter-example - Querying without validation:
# Wrong - querying without checking status
agent-brain query "search term" # May fail if server not running
# Correct - validate first
agent-brain status && agent-brain query "search term"
See Server Discovery Guide for multi-instance details.
The embedding cache automatically stores computed embeddings to avoid redundant API calls during reindexing. No setup is required — the cache is active by default.
agent-brain cache status
A healthy cache shows:
# Clear with confirmation prompt
agent-brain cache clear
# Clear without prompt (use in scripts)
agent-brain cache clear --yes
No configuration is required. Embeddings are cached on first compute and reused on subsequent reindexes of unchanged content (identified by SHA-256 hash). The cache complements the ManifestTracker — files that haven't changed on disk won't need to recompute embeddings.
See the API Reference for GET /index/cache and DELETE /index/cache
endpoint details, including response schemas.
This skill focuses on searching and querying. Do NOT use for:
configuring-agent-brain skillconfiguring-agent-brain skillconfiguring-agent-brain skillconfiguring-agent-brain skillScope boundary: This skill assumes Agent Brain is already installed, configured, and the server is running with indexed documents.
runtime.json rather than assuming port 8000agent-brain stop when done--include-type python,docs instead of manual glob patterns--force for efficient updates--dry-run injector scripts before full indexingagent-brain jobs --watch for long-running index jobs| Guide | Description |
|---|---|
| BM25 Search | Keyword matching for technical queries |
| Vector Search | Semantic similarity for concepts |
| Hybrid Search | Combined keyword and semantic search |
| Graph Search | Knowledge graph and relationship queries |
| Server Discovery | Auto-discovery, multi-agent sharing |
| Provider Configuration | Environment variables and API keys |
| Integration Guide | Scripts, Python API, CI/CD patterns |
| API Reference | REST endpoint documentation |
| Troubleshooting | Common issues and solutions |