The CAST ecosystem
CAST is a core multi-agent framework plus a set of composable, Homebrew-installable tools — a dashboard, a memory layer, a desktop app, and more. Every component reads and writes the same local cast.db, so you can install the full framework or just the pieces you need.
CAST Core
v9.5.3The complete multi-agent framework
View details →Claude Code Dashboard
v2.5.0React observability UI — sessions, agent analytics, hook health, memory browser, SQLite explorer.
View details →Cast Desktop
v1.2.12Tauri 2 native app — embedded PTY terminal, command palette, and dashboard views.
View details →CAST Memory
v0.4.1Persistent agent memory for Claude Code — FTS5 full-text search, weighted relevance, temporal validity, Ollama embeddings, and weekly consolidation over cast.db.
View details →Claude's Journal
v0.3.1Three-hook journaling for Claude Code (Stop/SessionStart/UserPromptSubmit) — maintains Claude's perspective and working memory across sessions as Obsidian-compatible markdown.
View details →CAST Time
v0.1.2Gives Claude Code a clock — injects local time, timezone, and a semantic time-of-day bucket at every SessionStart.
View details →CAST Doctor
v0.1.3Standalone read-only health check for any Claude Code install — validates hooks, MCP config, agent frontmatter, cast.db core schema, and stale memories without the full CAST framework.
View details →CAST Ledger
v0.1.0Signed, hash-chained, tamper-evident session receipts for Claude Code — SHA-256-stamped audit receipts from cast.db with --verify, plus an optional provenance hash-chain across sessions.
View details →CAST MCP
v0.1.0Read-only MCP server over the Claude Code execution record (cast.db) — dispatch decisions, incidents, cost, sessions, and full-text search as 5 MCP tools + 5 resources.
View details →CAST Predict
v0.1.0Telemetry-driven dispatch prediction for Claude Code — reads cast.db to predict a task's likely cost, suggest agents, and surface related past incidents before you run it.
View details →