Recently Evaluated

A GitHub repository for an agentic operating system with active pull requests around workflows, model cataloging, evals, Slack, heartbeat handling, and usage caching.

Shopify documentation for browser-based AI agents to read, update, and complete checkout flows in the buyer’s browser using WebMCP.

Read-only Postgres MCP server that adds schema context files for more accurate agent answers and supports agents writing back table notes.

An iPhone app for controlling coding agents like Claude Code and Codex from your phone, with push prompts, live terminal access, and quick approve/deny actions.

Self-hosted approval gateway for AI agent tool calls. It checks actions against rules, pauses risky ones for human approval, and keeps a tamper-evident audit trail. The repo shows setup, live demo flow, and integrations with Claude Code and MCP apps.

A working example of an AI helpdesk agent built on the Phaze Enterprise API and Phaze MCP. It watches Slack requests, connects to Windows machines, and can hand off to a human when needed.

A local-first macOS desktop app for tracking manga and book libraries and turning chapters into narrated recap videos using local vision models, TTS, and swappable video backends.

Jylus is an API for turning changing records, logs, telemetry, and JSON into compact, source-backed evidence packs for AI systems. The page includes a free trial, API examples, sample response structure, and published benchmark results.

Linux command runner that kills every process started by a command and verifies cleanup before returning. Built for AI coding agents and CI jobs, with enforced cgroup mode, fallback process scanning, time and resource limits, and JSON run records.

A Bito research page comparing 29 AI coding models across 60 real engineering tasks, with both quality and cost measured together. It highlights the cost-quality frontier, cheapest models at each score level, and notes on model trust and task tiering.

A macOS Electron app that lets you talk to Claude, Codex, and Grok side by side, with voice-driven control and a lightweight local setup.

Research code for improving agent harnesses through regularized recursive self-improvement, with evaluation, selection, pruning, and domain-specific adapters.

A GitHub repository for a 7-node ESP32-S3 cluster that runs a small LLM using 1.58-bit BitNet-style quantization over an SPI daisy-chain.

A browser-based lab for running, comparing, and benchmarking small language models on-device with WebGPU.

RTSP stream simulator for developers and AI teams to test computer vision, video analytics, and VMS integrations using MP4 files instead of physical cameras.

A native Mac app that lets you type @@ in any editable field to talk to your AI agent, with screen, clipboard, and Finder context. It also includes TabTab autocomplete, clipboard history, screenshots, and screen recording.

Open-source structured memory for AI agents. Ingot stores tool results and documents in SQL-friendly form, with optional embeddings, MCP access, and a local quick start for running the stack.

A Julia-based projectional editor for structured data with multiple editable views and an AI assistant that edits the same underlying data.

Cloudflare’s agentic CLI for working with the full Cloudflare API, with programmatic TypeScript configuration and an accompanying open-source SDK generator called Forge.

A native macOS app that visualizes Claude Code runs as a city of robot-staffed offices, mapping projects, teams, and CLI events into an interactive workspace.

AI-native application protection platform with autonomous LLM pentesting, proof-of-concept exploit findings, and a full API-driven workflow for scans, reporting, and remediation.

A local sandbox for running LLM-generated code from Python or Node with no cloud, no daemon, and strong isolation controls.

Omnesis is a private, local knowledge layer that indexes a person’s digital life so AI agents and users can search email, messages, notes, calendar, files, health data, and more. The page shows a real product with setup flow, source integrations, privacy controls, and multi-surface access through CLI, web, iOS, and And

Open-source staff scheduling platform with a native MCP server so AI agents can search candidates, create assignments, manage shifts, and handle staffing requests.