Recently Evaluated

OpenEdit is an open-source, agent-driven video editing pipeline that lets coding agents add subtitles, cut, reframe, and generate motion graphics without a GUI or timeline.

Open-source runtime guardrails for AI agents that intercept unsafe tool calls before they execute, aiming to block prompt-injection-driven exfiltration and other policy violations.

Bourdon is a recognition-first memory runtime for AI agents, built to share memory across tools like Claude Code, Codex, Cursor, and others. The site shows install commands, product positioning, pricing, and several live field tests.

TokenMaxxer is a CLI-based AI usage tracker for developers that reads token counts from tools like Claude Code, Codex, Cursor, and others, then shows spend, model usage, and a public leaderboard. It emphasizes local-only reads and opt-in sharing.

AI forecasting platform with a public track record, API/docs, and integrations for Claude Desktop and Claude Code. The page highlights benchmark results, live market usage, and example forecast types for probability, numeric, date, categorical, and decision questions.

Open-source team skills for bringing shared coding standards, directives, and evals into agentic coding workflows like Claude Code and Codex.

Armature is analytics and evals for MCP-based agent sessions. It captures how users interact with products through Claude, ChatGPT, Claude Code and other clients, then groups sessions into use cases, flags issues, replays traces, and turns real workflows into evals.

Browser-only local AI app for running compatible Hugging Face ONNX community models with WebGPU. The page shows a model library, local text generation, and an inference console in the browser.

An AI-made book of thirteen machine-themed fables, written, illustrated, and typeset in one day, with a full read-online presentation and PDF download.

Privacy-first AI meeting notes and writing assistant for macOS, with on-device transcription, smart minutes, action items, and AI writing tools. The repo also shows an opt-in plain Markdown storage mode and full source for the app.

A blog post about Idle Frontier, a clicker game about building a frontier language model in 1,000 days, and the author’s experience making it with Claude, Godot, and Aseprite.

A small Rust-based LLM proxy for forwarding chat, messages, and responses requests to providers with gateway-key handling and optional protocol translation between Anthropic and OpenAI styles.

An autonomous audit-fix-verify loop for Claude Code that runs iterative code improvements with verification gates and a public journal of runs.

A 1.26B academic tutor model from Zyora Labs, built from scratch and tuned for concept-first explanations in English, Tamil, and Hindi.

Self-hosted email MCP server for AI agents that connects to IMAP/SMTP inboxes and exposes tools for reading, organizing, composing, deleting, drafting, scheduling, and searching mail.

A research article describing an empirical runtime-monitoring approach for multi-turn LLM agents, backed by 3,175 runs across four benchmarks. It also points to an open-source implementation, state-harness, with Rust/Python support, LangGraph and CrewAI adapters, CLI tooling, and OpenTelemetry export.

Kota is a macOS app for bringing AI agent CLIs into one place, presented as “a home for your agents and projects.” The page shows a download for Apple Silicon, GitHub access, docs, and feature sections around working with CLI-based agents.

A free checker that measures whether ChatGPT, Gemini, Claude, and Perplexity recommend your brand, with prompt-level gaps, cited sources, and competitor comparisons.

Kuvu AI is an all-in-one creative studio for generating images, videos, and related media with multiple AI models. The page highlights text-to-image, text-to-video, image-to-video, prompt enhancement, batch generation, and a pricing model aimed at creators and teams.

Shots is a Codex plugin and MCP tool for generating App Store screenshots, app icons, and listing copy from a codebase. It researches competitors, reads app context, and lets teams revise and localize screenshots inside a coding agent or Studio.

Authoryze is an MCP-native payment layer for AI agents that issues single-use virtual cards for approved purchases and adds spending limits, merchant rules, approvals, and audit trails.

A lightweight CLI for running multiple local MLX models on Apple silicon. It serves OpenAI-compatible endpoints, supports both text-only and multimodal models, and can browse/download from Hugging Face.

Bifrost is a high-performance AI gateway that provides a single OpenAI-compatible API across 23+ model providers, with automatic failover, load balancing, semantic caching, and enterprise deployment features.

Rust building blocks for frontier OpenAI agents, with a CLI, SDK, and examples for agent sessions, event streaming, and voice-driven workflows.