Recently Evaluated

Deliberate is an SDK and proxy that records the alternatives an AI agent considered, what it rejected, and why, with replay, policy gates, approval workflows, and exportable decision logs.

Ouijit is an open-source task and terminal session manager for coding agents. It adds agent status, notifications, automatic worktree management, and VM sandboxing, with support shown for Claude Code, Codex, and Pi.

Self-hosted AI workspace with chat, agents, deep research, document editing, email triage, notes, calendar, and model comparison. The README includes setup instructions for Docker and native installs, plus a broad feature list and demo references.

A macOS utility that compresses screenshots locally and copies them to the clipboard for use with coding agents like Codex and Claude.

agentpack is a tool for staging reproducible AI coding environments across agent harnesses like Claude Code, Codex, Cursor, and OpenCode. It manages skills, hooks, MCPs, and other agent configuration from a single manifest without polluting the project or user config.

fuguUX is an AI-powered user testing and CX analysis tool that simulates real users on a website, surfaces UX issues, and generates reports with severity-rated findings, session records, and improvement roadmaps.

Open-source security scanner and firewall for MCP servers. It scans configs for common MCP risks, enforces runtime policies on tool calls, and produces audit logs, with CLI commands, policy examples, and a programmatic API.

A visual editor for React apps that lets you edit UI live and writes the changes back into source files. It runs locally as a proxy/overlay and supports Next.js, Vite, and Create React App.

An OWASP incubator project that protects AI agent memory from prompt injection, secret leakage, and tampering. It includes a Python library, policy-based controls, benchmarks, and integrations for agent frameworks like LangChain and AutoGen.

NodeCartel is a cloud tool for managing AI agents across multiple hosts with workspaces, task assignment, shared wiki memory, live chat, and usage/cost tracking.

SnapName is a macOS app that watches a screenshot or image folder and uses bundled local AI to suggest better filenames without uploading images.

A TypeScript zot extension that adds an /answer slash command for responding to numbered questions from the latest assistant message in an interactive panel.

Extend AI turns a spoken or rough written idea into posts that match the user’s own voice across LinkedIn, X, Instagram, and more.

Pure Effect is a small JavaScript library for building testable business logic as data-driven commands instead of relying on mocks. It includes primitives like Success, Failure, Command, Ask, Retry, and Parallel, plus helpers like effectPipe and runEffect for composing and executing flows.

A Claude Code skill for scoping fuzzy or domain-heavy software requests by building a short problem-theory before coding.

Autolang is a scripting language and compiler for AI agent code, designed to run untrusted AI-written scripts in a controlled environment with restricted access to registered functions.

crune is a static web dashboard and CLI for analyzing Claude Code session logs. It offers session playback, analytics, semantic knowledge graph generation, and reusable skill synthesis from prior sessions.

A tutorial showing how to build a release notes generator with the Cline SDK, including project structure, setup, custom tool design, and code walkthroughs.

tokentoll is a GitHub Action and CLI that scans Python and JavaScript/TypeScript code for LLM API calls, estimates spend, and blocks pull requests when cost or model-policy thresholds are exceeded.

Open-source terminal coding agent in Rust with LLM-native code understanding, shell safety, multi-provider support, and automatic failover.

A research write-up on detecting AI agents through process differences in CAPTCHA and related cognitive tasks. It outlines the CogCAPTCHA30 approach, reports human-vs-model differences, and connects the findings to Roundtable’s Proof of Human product.

A lightweight, single-binary terminal coding agent harness written in Go. It supports multiple model providers, local OpenAI-compatible models, built-in file and shell tools, extensions, session management, side chat, and swarm subagents.

Open-source C++ and CUDA LLM inference engine inspired by vLLM, with a teaching-focused course that walks through model serving, batching, KV cache, and attention kernels.

arXiv paper on a self-speculative decoding framework for speeding up reasoning LLM inference on edge hardware, with hardware co-design and reported speedups.