Recently Evaluated

A Claude Code plugin that learns from user corrections and successful runs, then turns them into reusable rules and playbooks stored locally.

A GitHub repo for evaluating agentic AI pipeline systems, with guidance for defining metrics, building eval cases, running repeatable tests, and tracking regressions.

A metadata-first trust control plane for authorized security workflows, evidence retention, release trust, and business-flow proof. The repository includes role-based docs, quick-start commands, safety boundaries, and release-trust materials.

A ~1000-line C workflow runtime where an LLM can modify a DAG during execution using a restricted four-verb grammar, with every change written to an append-only audit log for replay and inspection.

Open-source agile planning and orchestration layer for AI coding agents, with bidirectional sync to Claude Code, AI-generated user stories, sprint planning, and a self-hosted CLI workflow.

An Apple Silicon–optimized inference build of Bonsai 1.7B with custom Metal kernels, benchmark results, quick-start instructions, and a bundled OpenAI-compatible server.

A hands-on workshop repository that walks developers through building a small GPT-style language model from scratch, including tokenization, transformer blocks, training, and text generation.

Apple Machine Learning Research paper proposing LaDiR, a reasoning framework that combines a VAE-based latent space with latent diffusion to improve LLM text reasoning and iterative refinement.

A self-hosted Docker Compose stack for running local AI services including Ollama, LiteLLM, Whisper, Kokoro, embeddings, and an MCP Gateway.

A self-hosted TypeScript harness for building provider-neutral LLM agent systems inside an application or platform, with typed agent and workflow runtime, tool support, state, tracing, and example workspaces.

Herd is a lightweight desktop IDE for coordinating multiple AI coding agents at once. It supports parallel tasks, real-time status monitoring, and works with tools like Claude Code and Codex on Windows, macOS, and Linux.

A local-first, file-based context and memory system for AI coding assistants. It’s designed to persist decisions, tasks, and learnings across sessions so tools can rehydrate project context instead of starting from scratch.

Patchwork is a Rust CLI for AST-native code refactoring without LLMs. It can find, replace, delete, and insert code by structure instead of regex, with support for Java, Python, JavaScript, TypeScript, and TSX.

Chrome extension that exports ChatGPT conversations to PDF, Word, Google Docs, or Notion, with partial exports, formatting controls, and local processing in the browser.

Open-source agentic mesh for governing AI agents across enterprise systems, with identity, policy enforcement, audit trails, observability, and Kubernetes-native deployment.

Open-source Rust coding agent with LLM-native code understanding, shell safety, and support for multiple LLM providers with automatic failover.

A tool that converts any URL into markdown optimized for coding agents, with browser, CLI, API, SDK, and agent integration support.

Open-source themed design systems for shadcn/ui, with 29 style variants and one-command installs through a shadcn registry.

An embeddable AI agent library written in C with tool calling, memory, sessions, voice, streaming, structured output, and support for both cloud and local models.

A public slide deck about vLLM-compile, a project focused on bringing compiler optimizations to LLM inference and speeding up torch.compile for vLLM workflows.

A research article from Applied Compute on how agentic, tool-using workloads differ from traditional LLM benchmarks, with production observations, workload profiles, and an open-source harness for replaying traces.

SPARKIT is a scientific research agent delivered through an API. It searches literature, reads PDFs, runs analyses, and returns cited Markdown reports for research workflows.

Gate is an agentic desktop OS for developers that runs AI desks locally, extracts reusable skills from completed work, and logs every action with receipts. The page shows install flow, platform limits, model requirements, sandboxing, and a clear comparison with Cursor/Aider.

Rinhelp is an AI support diagnosis tool for technical support teams. It starts from Crisp support threads, pulls evidence from GitHub and Sentry, and returns a reviewable diagnosis draft for internal use.