Recently Evaluated

A routing skill that helps coding agents choose the most token-efficient tool for a task instead of reading whole files or dumping verbose output into context. It recommends tools like serena, graphify, rtk, caveman, or plain Read/Grep/Bash depending on the job.

Treenix is a typed runtime for building software shared between humans and agents. The repository describes an ECS-style tree of typed components with context-aware rendering, server actions, React views, access rules, realtime updates, and MCP tools.

Raidho is an open-source coding agent that separates planning and execution across different model providers and adds durable VSA-based memory across runs. The repo includes install steps, provider options, CLI usage, and benchmark evidence.

A sourced model and short report exploring whether Europe could train a sovereign frontier AI model using public compute it already owns, with reproducible code, datasets, and a PDF report.

Claude for Foundation Models is a Swift package that brings Claude to Apple’s Foundation Models framework on supported beta OS releases. The page includes requirements, install steps, quick-start code, model selection, authentication options, streaming, structured output, and a runnable example reference.

An independent white paper proposing a local-deployment path for frontier AI weights, with a PDF, generator script, and a detailed README outlining the argument, sections, and contribution process.

A blog post describing an evaluation harness for comparing agentic coding tools and prompts across realistic SWE tasks, with token-cost results and model-specific behavior notes.

An associative memory database that stores facts in plain language and recalls them by meaning. It ships as a Rust core with optional SQLite, encryption, and HTTP server features, plus examples and API docs.

Ponytail is a repository and plugin toolkit that pushes AI coding agents to choose the smallest useful implementation first, favoring stdlib, platform features, and one-line fixes over larger generated code. The README shows installs and usage paths for Claude Code, Codex, OpenCode, Cursor, Windsurf, Cline, Copilot, Ai

Go-native framework for building, orchestrating, and observing AI agents with native OpenTelemetry, an embedded dashboard, replay, and first-party MCP/A2A support.

A lightweight golf round tracker that runs in the browser and keeps data locally. The page shows starting and finishing rounds, logging shots, club selection, and a simple workflow for tracking holes.

An AI API gateway/proxy in Go that sits between coding clients and upstream LLM providers, with request routing, secret redaction, context handling, MCP tool integration, and transparent SSE streaming.

macOS CLI tool that load-balances Claude Code sessions across multiple subscriptions by selecting the emptiest account before launch.

A Rust-based checker that compares a changed function against its prior version on deterministically generated inputs and reports counterexamples when behavior changes. It includes a PR gate via GitHub Actions, CLI usage, signed receipts, and docs for release/signing.

Local-first observability and evaluation layer for production forecasts. Captures forecasts, validates them, computes horizon-aware metrics, and serves a read-only local UI for comparing runs.

An MCP server for SharkClean and SharkNinja robot vacuums that lets MCP clients start cleanings, target rooms, dock the robot, and check status. The repo also includes setup steps, authentication guidance, CLI commands, and notes on supported models and cloud backend behavior.

Self-hosted AI assistant that connects to many apps and services, with Tamil and Hindi UI support, mobile PWA access, and Anthropic model integration.

A native Windows terminal multiplexer built for AI coding agents, with split panes, MCP bridging, and browser automation. It targets Windows users running tools like Claude Code, Codex CLI, and Gemini CLI without WSL.

Local-first encrypted memory engine for AI agents, built in Rust with MCP support and persistent cross-session memory for Claude and other MCP clients.

A local-first Python tool that audits Git history to quantify rework in AI-generated engineering work, including PR correction rates, churn clusters, superseded work, and line survival.

A lightweight React Markdown renderer with built-in LaTeX, syntax highlighting, streaming-safe rendering, and security-focused defaults.

A service-boundary-aware coordination layer for heterogeneous LLM code agents via MCP. It combines versioned Markdown documents, pub-sub notifications, diff-aware updates, and a web dashboard for browsing, search, and AI chat.

An agent skill and Python builder that turns Markdown note folders from Obsidian or gbrain into an interactive HTML knowledge map with a force graph, growth timeline, filters, and note detail panels. The repo includes a prebuilt demo for quick inspection and supports use in Claude Code, OpenAI Codex, Cursor, and simila

A detailed walkthrough for running a local coding agent on macOS with llama.cpp, Gemma 4, MTP speculative decoding, image support, and Pi as the agent interface.