Browse evidence-backed project records from the current public release. Each project page includes deployment, license, use cases, limitations, and source information.
A structured workflow framework that runs locally to orchestrate AI agent tools for the end-to-end job search process. It requires the Claude Code CLI and Anthropic Claude models to operate, utilizing a drafter-reviewer pipeline for genera…
Orca is a desktop and mobile development environment that orchestrates multiple CLI coding agents in isolated parallel git worktrees. Developers must bring their own subscriptions for underlying coding agents, and inference depends on thos…
A ruleset and review/audit commands encouraging coding agents to reuse existing solutions before adding code.
ComfyUI provides a modular node graph and backend for generative workflows across images, video, audio and 3D. Local model workflows and optional paid API nodes have different dependencies.
This project adds a coordination, memory, and security layer around existing AI coding tools. It targets developers who need to orchestrate multiple specialized agents, using a CLI and integrations with both cloud-based and local model pro…
Graphify turns a folder of code or documentation into a queryable knowledge graph using deterministic tree-sitter AST parsing across approximately 40 languages without requiring LLM calls. It generates graph files for local analysis and ex…
OpenCode provides an open source AI coding agent that ships with a full-access build agent and a read-only plan agent. It can be installed through multiple package managers or run as a beta desktop application on macOS, Windows, and Linux.
A collection of personality-driven AI agent personas specialized by discipline, accompanied by scripts for installing them into multiple agentic coding tools. It is designed for developers seeking specialized, deliverable-focused agents ra…
This project reduces LLM token consumption by compressing agent context such as tool outputs, logs, and retrieved chunks. It operates as a local-first, reversible context compression layer to lower costs while maintaining answer accuracy.
Kronos is a pre-trained foundation model specialized for financial candlestick (K-line) sequences, addressing the limitations of general-purpose time series models on high-noise market data. It provides a Python library for generating OHLC…
vLLM is a high-throughput, memory-efficient inference and serving engine for large language models. It provides an OpenAI-compatible API server and uses PagedAttention to manage attention key and value memory efficiently.
Obsidian Mind is a self-organizing Obsidian vault template that gives AI coding agent CLIs (Claude Code, Codex CLI, Gemini CLI) persistent, linked memory across sessions via git-tracked Markdown notes, hooks, commands, subagents, an MCP se…