Recently Evaluated

An MCP server and API that checks documents for hidden or invisible text before an AI assistant reads them.

A reverse proxy for OpenAI-compatible agent traffic that detects runaway tool loops and enforces hourly and daily spend caps with zero payload retention.

An open public experiment that tests whether AI agents can complete everyday web errands, publishes the full transcripts, and scores 113 sites for agent-readiness.

Open-source personal agent for phone, desktop, and browser that can take actions, keep running in the background, remember user preferences, and coordinate across devices.

OpenTPU is an open-source AI accelerator project with RTL, ISA, simulator, compiler, profiler, and host software in one repo. The page shows it running real models like Qwen and LFM on a Kintex-7 PCIe card, with detailed performance results and documentation links.

OpenAI API documentation for the Decisions API, which checks conditions, selects from fixed options, and scores text or images against a rubric.

Genjutsu AI is a video-to-video tool that keeps the original subject and motion while restyling the scene, objects, or look around it. It supports motion transfer, object swaps, multiple resolutions, and one-time credit pricing.

A reputation layer for AI agents that tracks verified tasks, trust scores, and weekly leaderboards, with a CLI to register and run agents.

An agent skill that converts AI output into more readable formats such as simplified technical English, diagrams, interactive HTML, narrated explainers, and review summaries for human oversight.

Open-source repo for Muse’s “chief of staff” workflow: it coordinates specialist agents, preserves per-agent memory, and builds a private Office app for tracking projects, team, customers, reports, and notes.

A native Mac screen recorder with a built-in editor and MCP support so Claude, ChatGPT, or Cursor can help cut, zoom, add captions, and export demos locally.

Orbtile turns a Logitech MX Creative Keypad into a live status pad for AI coding agents, showing session state, approvals, and requests at a glance on macOS.

An open-source iPad app that turns handwritten notes into AI answers by detecting triple underlines or circles and responding in a handwriting style.

A reproducible GitHub research repo comparing Codex reasoning-token usage between API and ChatGPT Pro access across 960 completed responses, with code, data, and verification steps included.

A local-first todo board that connects to an AI assistant through MCP, letting the assistant read and update tasks on the same machine.

Deterministic gates for coding agents that block risky or pointless actions with code-based checks. The repo shows hook-based controls for delete protection, git safety, egress blocking, credential access, install pinning, loop detection, and idle-process handling across Claude Code, OpenAI Codex, and Antigravity.

Mac voice assistant that sits in the notch or menu bar, lets you hold a key and speak from any app, and uses your own Claude or ChatGPT plan, API key, or local model to answer and act on your Mac.

Open-source memory system for LLM characters with library, API, MCP server, and WebUI options. The repo explains how it stores and recalls character, user, episode, emotion, world, and calendar memory, and includes install and usage examples.

Self-hosted AI coding agent platform for GitLab built with LangGraph. It reviews merge requests, resolves issues or tasks, and offers a GitLab-aware chat assistant with persistent project context.

An MCP server that connects Claude Desktop, Cursor, Codex, and other MCP clients to bounty.index’s live bug bounty index, with 14 tools, 3 prompts, and a stats resource.

Headline Arena is a public forecasting platform where AI agents make daily market predictions, settle against outcomes, and appear on a public leaderboard. The page shows live and recently settled markets, methodology, onboarding, API, and pricing links, plus visible agent performance data.

Octri turns an OpenAPI spec into docs, SDKs in 10 languages, an MCP server, and monitoring tied to generated SDKs.

A Claude Code plugin that delegates bounded coding tasks to cheap DeepSeek Flash workers in disposable repo copies, then returns patches for Claude to review and apply.

A small open model trained to turn English requests into Bash commands, with published training data, GGUF weights, and benchmark results.