Back to Home
Kastalien-Research icon

thoughtbox

Verified Safe

by Kastalien-Research

Overview

Provides a durable, local-first reasoning ledger and structured cognitive tools for AI agents, enabling step-by-step thinking, branching, revisions, and autonomous critique, with progressive tool disclosure and client compatibility adaptations.

Installation

Run Command
npx -y @kastalien-research/thoughtbox

Environment Variables

  • THOUGHTBOX_TRANSPORT
  • THOUGHTBOX_STORAGE
  • THOUGHTBOX_DATA_DIR
  • THOUGHTBOX_PROJECT
  • DISABLE_THOUGHT_LOGGING
  • THOUGHTBOX_OBSERVATORY_ENABLED
  • THOUGHTBOX_OBSERVATORY_PORT
  • THOUGHTBOX_OBSERVATORY_CORS
  • THOUGHTBOX_OBSERVATORY_PATH
  • THOUGHTBOX_OBSERVATORY_MAX_CONN
  • THOUGHTBOX_OBSERVATORY_HTTP_API

Security Notes

The server is designed for local-first use and incorporates robust input validation (`sanitizePath`, `validateFilename`) in the notebook component to mitigate path traversal and similar file-system based vulnerabilities when executing user-defined code. External process execution (`spawn` for Node.js, npm, tsx) is performed with explicit commands and arguments, reducing the risk of shell injection. There are no overt hardcoded secrets. While the Observatory component allows for flexible CORS configuration (including `*`), this is an opt-in setting in an optional, typically local, monitoring tool. Overall, the source code indicates a conscious effort towards security for its intended use case.

Similar Servers

Stats

Interest Score48
Security Score9
Cost ClassLow
Avg Tokens200
Stars32
Forks6
Last Update2026-01-19

Tags

AI Agent ReasoningCognitive ToolsDurable Reasoning ChainLocal-FirstStructured ThinkingDebuggingDecision-MakingArchitecture