agentkb 0.1.1

A unified search and knowledge tool for AI agents and developers

AgentKB

Pre-alpha. This is under active development. APIs, CLI commands, and storage formats may change without notice and will likely break frequently. Use at your own risk.

A unified search and knowledge tool for AI agents and developers. Braids together your code, a knowledge base of markdown files, and your Claude Code chat history into one searchable system.

Your data stays local, in universal formats (source files, markdown, JSONL), on your machine. Back everything up with agentkb sync push and restore on a new machine with agentkb sync pull.

Install

pip install agentkb

Quick Start

# Index your code
agentkb code index

# Search semantically
agentkb search "database connection pooling"

# Initialize a knowledge base
agentkb kb init

# Index your Claude Code chat history
agentkb chats index

# Search across everything
agentkb search -s all "authentication flow"

Stores

AgentKB has three store types:

• Code — source files parsed with tree-sitter (Python, JS, TS, Rust, Go, Java, C, Ruby), searchable by meaning
• Knowledge Base — plain markdown files you and your agents write. Hard-won lessons, project context, accumulated knowledge.
• Chat History — Claude Code conversations exported as readable markdown, fully searchable

Search

agentkb search "retry logic with backoff"              # semantic search (default: code)
agentkb search -s kb "why did we choose JWT"            # search knowledge base
agentkb search -s chats "how did I fix the auth bug"    # search chat history
agentkb search -s all "authentication"                  # search everything
agentkb search -e "async def" "error handling"          # regex + semantic
agentkb search --include="*.py" "config parsing"        # filter by file type
agentkb search --json "query"                           # JSON output for scripts

Documentation

Full docs at isaacflath.com/plait.

How It Works

Hybrid search: ColBERT multi-vector embeddings (semantic) + SQLite FTS5 (keyword), fused with reciprocal rank fusion. Indexes are incremental — only changed files are re-encoded.