Results for context-composer

composable context.

SmartBrain provides commit_turn and compose_context APIs for agent memory, retrieval planning, evidence fusion, and context assembly.

Gaskit provides a lightweight, extensible framework for encapsulating business logic using a consistent, composable operation pattern. It supports context propagation, exit handling, structured results, and flexible logging via configuration.

View-model base class for Rails: typed, immutable presentation objects via Literal::Data, composable traits, opt-in Rails helper mixins, fragment-cache key generation, and a background-job-friendly fake view context.

Rubagent is a lightweight Ruby framework for building modular, composable AI agents that can interact with LLMs (like OpenAI), tools, and external APIs. It provides a flexible architecture for defining agents, managing prompts, and orchestrating multi-step workflows using functional patterns. Features: - Streamed LLM responses (OpenAI, etc.) - Plug-and-play agent design - Shared context and memory flow - Support for custom tools and HTTP integrations - Built-in dry-rb and Zeitwerk compatibility

RubyPi is a minimal, composable AI agent harness for Ruby. Build production-ready LLM agents and AI agents with a unified provider interface across OpenAI, Anthropic Claude, and Google Gemini, plus first-class support for tool calling (function calling), streaming responses, automatic retries, provider fallback, context compaction, and a think-act-observe agent loop. Anti-framework design — small, idiomatic, and explicit. Ideal for building autonomous AI agents, ReAct agents, tool-using LLM agents, and chatbots in Ruby.

CommandSet is a user interface framework. Its focus is a DSL for defining commands, much like Rake or RSpec. A default readline based terminal interpreter (complete with context sensitive tab completion, and the amenities of readline: history editing, etc) is included. It could very well be adapted to interact with CGI or a GUI - both are planned. CommandSet has a lot of very nice features. First is the domain-specific language for defining commands and sets of commands. Those sets can further be neatly composed into larger interfaces, so that useful or standard commands can be resued. Optional application modes, much like Cisco's IOS, with a little bit more flexibility. Arguments have their own sub-language, that allows them to provide interface hints (like tab completion) as well as input validation. On the output side of things, CommandSet has a very flexible output capturing mechanism, which generates a tree of data as it's generated, even capturing writes to multiple places at once (even from multiple threads) and keeping everything straight. Methods that normally write to stdout are interposed and fed into the tree, so you can hack in existing scripts with minimal adjustment. The final output can be presented to the user in a number of formats, including contextual coloring and indentation, or even progress hashes. XML is also provided, although it needs some work. Templates are on the way. While you're developing your application, you might find the record and playback utilities useful. cmdset-record will start up with your defaults for your command set, and spit out an interaction script. Then you can replay the script against the live set with cmdset-playback. Great for ad hoc testing, usability surveys and general demos.

Diff and patch tables

Diff and patch tables

No description provided.