Recently Evaluated

Open-source governance harness for AI agents with policy enforcement, human approvals, isolated execution, budgets, and signed audit evidence. It includes a CLI, REST API, web dashboard, SDKs, and adapters for common agent frameworks.

ModelPlane is an OpenAI-compatible AI gateway that routes requests across multiple model providers through one endpoint. It includes model groups, fallback and weighted routing, multiple provider support, reasoning output normalization, and usage/billing tracking.

A cross-platform CLI release for switching between isolated Claude Code accounts on Linux and macOS without re-login, with per-profile storage and Keychain-backed credentials on macOS.

RequestGuard creates CAPTCHA-gated short links that hide the destination until a visitor passes verification. It also supports expiry, passwords, and an API/SDK for generating protected links from a backend or embed flow.

An open-source project for running a small LLM and limited agent workflows on ESP32-P4 hardware, with model details, architecture notes, examples, and setup instructions.

BoundaryBench is an open-source benchmark for coding agents running under hardened sandbox policies. It compares harnesses like Claude Code, Codex, Terminus 2, and Grok on Terminal-Bench tasks and includes quickstart, policy controls, and result export tools.

Open-source skill contracts for AI agents that change response style based on the user’s state, such as overloaded, foggy, burnout, and reality-check modes. The README shows the intended behaviors, example prompts, and install instructions via Skills Store.

Lapse is a personal memory layer for AI tools, letting users speak naturally and have memories captured, tagged, and read back through MCP, a custom connector, and a REST API.

A read-only MCP server that lets AI assistants search, browse, and inspect public AI-agent listings from natural language inside clients like Claude and Cursor.

Graft builds a semantic code graph for coding agents so tools like Claude Code and Cursor can understand a repository faster with less re-exploration. It ships as a CLI with agent wiring, graph generation, and visualization, and supports local or hosted model providers.

Lucidos is a local AI OS and companion that keeps described apps running, responds to events, and works from a persistent desktop or browser-based interface. The repo shows install paths for macOS and Linux, a headless runtime, source build instructions, and a clear focus on user-owned local data.

Fast Rust MCP aggregator that exposes a small fixed tool surface for agents while semantically searching and calling tools across many downstream MCP servers. Supports SQLite-backed persistence, restart-safe embeddings, stdio and Streamable HTTP transports, plus a REST API for testing.

MCP server that lets AI agents control labgrid-managed embedded hardware labs through 47 tools, including power, console, flashing, muxing, SSH, and place management.

A Markdown-based personal finance CLI built with Claude that uses AI for receipt and expense transcription while keeping totals and settlements deterministic in code.

Vocab Top is an AI-powered vocabulary builder for language learners. The page highlights contextual translations, word forms, pronunciation support, example sentences, visual memory aids, and a personal library for tracking words.

Market-derived RL environments for training agents on quant trading and long-horizon planning under adversarial noise.

An unofficial MCP server for cosmos.so that lets AI clients search, browse, and save visual moodboards. The repo includes install steps, authentication guidance, and concrete examples for Claude Code, Claude Desktop, and Cursor.

A playable text-adventure that teaches Claude Code through real prompts, skills, and agent workflows.

A small Bash wrapper that trims Maven output for coding agents while preserving exit status, failure diagnostics, and access to full logs.

Sif 1.0 is a developer tool that uses an LLM for planning while handling code changes, validation, promotion, and recovery through deterministic execution. The repo includes install scripts, a quick demo, and detailed README guidance for trying the system locally.

Local-first coding agent workbench that runs agents in secretless microVMs, with support for multiple providers, parallel sessions, and shared repository workflows.

A macOS menu bar app that mounts Android and other MTP devices as Finder volumes. It aims to replace transfer-window tools with a real mounted drive experience.

Mint MCP is an AI developer tool for generating 3D models, worlds, materials, asset packs, and audio from coding agents like Cursor, Claude, and Codex. The page includes install steps, example prompts, and workflow guidance for building 3D apps and assets.

Hubmesh is a Python library for multi-hop GraphRAG retrieval planning on top of existing vector databases. It adds centrality-aware seed selection, budget-aware context packing, entity graph building, and an MCP server for agent/tool integrations.