Tyler

AI coding agent optimized for small LLMs. 87% benchmark with 4B-active model.

Terminal coding agent built for small local LLMs (8B-35B params). Adds context budgets, forgiving tool parsers, and patch-based edits so weaker models can do real coding work.

A declarative LLM friendly language that compiles system descriptions into complete, runnable Node.js backends.

MarrowScript compiler. Welcome to deterministic typed LLM orchestration as a compile-time concern

DSL and compiler that turns a single .marrow file describing entities, capabilities, events, and flows into a full Node.js backend with Express, Postgres, JWT, SDK, and admin UI.

Model-agnostic code memory MCP server. Budget-aware graph retrieval for AI agents. Sub-millisecond queries, token budgeting, deterministic results. Built on CodeGraphContext.

MCP server that gives AI coding assistants budget-aware code context by walking call and import graphs from an anchor symbol until a token limit is hit, backed by SQLite and tree-sitter.

OpenCode plugin that makes BoneScript the preferred way to build backends — entities, APIs, state machines, realtime channels, and workflows.

Brain-anatomical proto-AGI cognitive engine. Fork of Aditya-B-007/Shiva.

No description.

TypeScript adapter that wraps AUTOMATIC1111's Stable Diffusion Web UI HTTP API while routing prompts through LM Studio (or any OpenAI-compatible chat endpoint) for prompt enhancement.