Recently Evaluated

Relaymux is a tmux-backed harness for running local coding agents, with Telegram as the remote control interface and support for iMessage/SMS in beta.

Open-source persistent memory agent for AI coding tools and assistants. It supports local and cloud setups, integrates with several agent IDEs and CLIs, and offers remember, recall, and answer primitives for long-term context.

Anthropic research report on how people use Claude Code in practice, based on a large privacy-preserving analysis of session data. It covers task types, division of labor between user and model, and how domain expertise affects outcomes.

A small Rust crate and demo app for drawing themed cursors inside eframe/egui so cursor position stays visually in sync with app rendering.

GRID is a small framework for working with coding agents in a spec-driven way. The repository explains its purpose, basic workflow, and how it can be used in CI/CD to check for spec-code-test mismatches.

AutomatiQ is a Python CLI that records a browsing session and uses vision and LLM steps to generate a standalone HTTP-based automation script.

Local-first desktop app for AI document translation and side-by-side comparison, with support for multiple engines and cloud APIs.

An open-source mixture-of-agents server that fans prompts out to multiple LLMs, judges the responses, and synthesizes a final answer. It exposes an OpenAI-compatible API and also includes an agentic coding harness plus integrations for tools like Claude Code, aider, Continue, LangChain, and Pi.

An open-source simulator that studies how GPT inference behaves under space radiation and cosmic-ray fault conditions, with CLI runs, comparisons, and self-contained HTML reports.

MakerChecker is a self-hosted governance layer for AI agents that enforces roles, approvals, and tamper-evident audit logs. The repo shows quickstart commands, a demo flow, and SDK/connectors for TypeScript, Python, and LangChain-style integrations.

Modular desktop IDE built for agentic coding, with dockable panels, an MCP sidecar, plugin support, and built-in tooling for debugging, verification, memory, and secrets handling.

A VS Code blog post explaining how GitHub Copilot’s agentic harness is being optimized to reduce token usage, latency, and cost through extended prompt caching, tool search, and WebSocket connections.

ctx is a local-first desktop workbench for coding agents, now open source under GPL-3.0. The page explains that it runs agents in a desktop environment with worktrees, transcripts, artifacts, diff review, container boundaries, and a local merge queue.

A CLI for running long-lived autonomous coding agents in isolated Docker containers, with detach/reattach, review, commit, push, and optional browser preview workflows.

Open-source, local-first desktop workbench for coding agents. It centralizes tasks, sessions, transcripts, artifacts, diffs, containers, and merge-queue state for agents like Claude Code, Codex, and Cursor.

MCP server for Unreal Editor that exposes a small MCP surface for a large set of editor automation tools. It supports blueprint editing, asset management, animation authoring, trace analysis, PIE actions, and Python execution, with setup notes for Unreal Engine 5.x and MCP-compatible clients.

GrassDx is an AI lawn diagnosis tool that analyzes lawn photos and ZIP code data to identify likely issues and return a localized treatment plan. It supports guided uploads, suggests DIY, subscription, or pro-service options, and includes lawn care tool recommendations.

A tiny GPT implementation in pure Go, trained on Jules Verne books, with runnable code and notes that explain the model’s evolution and design choices.

A zero-budget research search engine and RAG pipeline for 5,600 arXiv papers, built with free Colab processing, Qdrant free tier, and hybrid dense+sparse retrieval.

NakshGuard is a self-hosted reverse proxy for OpenAI and Anthropic chat APIs that detects and blocks runaway AI agent loops before they waste tokens or API spend. It includes per-agent session tracking, configurable thresholds, shadow mode, and hot config reload.

Offload is a developer tool that lets coding agents continue long-running tasks on another machine, with support for Claude Code and Codex. It can move the project state to a remote machine, run work on a new branch, expose remote localhost services, and send status updates while the laptop sleeps or disconnects.

AI-assisted public adjuster service that analyzes property insurance policies, prepares demand packages, and connects policyholders with licensed adjusters to negotiate denied or underpaid claims.

AI job-search assistant that tailors résumés and cover letters to a specific role, tracks applications, detects ghosting, and generates interview practice from the job description.

Wattfare is an OAuth-style way for apps to let users connect and fund their own AI usage with a monthly cap. It offers an SDK, OpenAI-compatible model access, and support for Vercel AI SDK workflows.