Connect to MCP servers via stdio, SSE, and Streamable HTTP transports. Run as an MCP server exposing any Ruby object as a tool. Discover tools, resources, and prompts. OAuth 2.1 authentication.

Rails engine that provides real-time monitoring for LLM usage. Cost tracking, throughput metrics, error rates, response times. Slack alerts. Real-time updates via Hotwire Turbo. Works with any ask-rb provider via ask-instrumentation events.

Provides authenticated Notion client, context metadata, and error guide for AI agents.

Adds OpenTelemetry tracing to ask-rb LLM operations. Subscribes to ask-instrumentation events and creates spans for chat completions, embeddings, tool calls, and more.

commandline tool to search stackoverflow quickly and simply.

Provides framework-independent permission rules, policies, and approval queues for ask-rb agents and integrations.

Document loaders, text splitters, vector stores, and retrieval queries for building RAG applications with ask-rb.

Rails generators, file conventions, and railtie for using ask-agent in Rails apps.

Rails Engine that mounts an admin AI agent at /ask. Ships Rails-aware tools (QueryDatabase, ReadModel, ReadLog, RunCommand, SchemaGraph, RouteInspector, RunTests), session persistence, audit logging, environment permissions, and service gem discovery. Previously developed as ask-rails (0.1.0–0.11.1).

Mount an MCP endpoint in your Rails app that exposes SchemaGraph, QueryDatabase, ReadModel, RouteInspector, and all other ask-rails-harness tools as MCP tools. Coding agents like Claude Code, Cursor, or any MCP-compatible client can connect to inspect your schema, query your database, read models, and more.

Mount an MCP endpoint in your Rails app that exposes SchemaGraph, QueryDatabase, ReadModel, RouteInspector, and all other ask-rails tools as MCP tools. Coding agents like Claude Code, Cursor, or any MCP-compatible client can connect to inspect your schema, query your database, read models, and more.

Harness for AI coding agents working in any Ruby project. Ships a language-agnostic tool contract (RunCommand, ReadLog, QueryDatabase, ReadModel, SchemaGraph, RunTests) with structured returns, read-only DB enforcement, environment permissions, and audit logging. The Rails edition (ask-rails-harness) adds framework-native tools on top.

Exposes the ask-ruby-harness tools (QueryDatabase, ReadModel, ReadLog, RunCommand, SchemaGraph, RunTests) as MCP tools for any Ruby project. Coding agents like Claude Code, Cursor, or any MCP-compatible client can connect to query the database, inspect models, read logs, run commands, and run tests with structured results.

Provides the foundational value objects and adapter contracts for tool-call execution in ask-rb: ToolCall, ToolResult, ExecutionContext, and the ToolExecutor adapter interface.

Isolated code execution via Local (subprocess + rlimits), Docker (containers), Daytona (remote sandboxes), and Cloudflare (Workers sandbox). Zero external runtime dependencies.

A compact Ruby DSL for building standards-oriented JSON Schema documents. Zero dependencies.

Error context for agents via Sentry for the ask-rb ecosystem.

Provides immutable session records, event envelopes, an in-memory store with concurrency guardrails, a durable provider-backed store for restart-safe sessions, a replayable host with subscriptions, a runtime tool-lifecycle sink, and a state reducer that reconstructs session snapshots from event history.

The contract between the ask session host and every client (terminal TUI, web console, bots, IDE) — plus the shared Client and Host. Defines the canonical session event vocabulary, the resolvable interaction types (approvals, plan proposals, user input), the client-to-host method surface, protocol versioning, and generated JSON Schema artifacts. No runtime, no transports — just the contract.

Discovers, validates, and formats agent skills from project directories, user config, and installed gems. Ships built-in skills (codebase exploration, debugging methodology). Each skill is a markdown file with step-by-step instructions that the agent loads on demand.