Recently Evaluated

Rowboat is an open-source desktop AI coworker that keeps long-term memory in a local Markdown knowledge graph and includes built-in surfaces like email, browser, notes, meeting transcription, and code mode.

A Noma Security research post detailing a prompt-injection flaw in GitHub Agentic Workflows, with attack flow, proof-of-concept evidence, and security recommendations.

A Pi extension that uses AI to generate and keep codebase documentation current, with commands for initial docs, incremental updates, and chat-based questions.

Local-first Python SDK for AI agents that compresses web pages before LLM use, flattens Shadow DOM, builds action maps, and extracts structured data from tables, forms, and lists.

A Claude Code skill that delegates coding, review, analysis, and research tasks to Google Antigravity CLI sub-agents so Claude can keep working while background jobs run.

A visual benchmark that asks AI coding agents to generate a single-file Three.js animation of a banana plant’s full life cycle, then compares the live results side by side.

A data-driven page that tracks well-known AI agent repositories with no recent public commit signal, comparing star counts with liveness to surface projects that have gone quiet.

Machine-facing documentation for agentic DNS skills from DomainHelp, covering IP lookup, resolver detection, homoglyph checks, SPF flattening, and domain permutation tools, with entry points and API references.

A local web UI for turning Claude Code and Codex agent logs into a live, readable chat feed with parent-child session trees, deep links, and real-time updates.

Bloomiro is an SEO and AI search visibility platform for SaaS teams. It tracks rankings, AI mentions and citations, competitor visibility, and turns search gaps into prioritized tasks. The site also highlights MCP support and connectors for tools like Cursor, Claude Code, VS Code, and Codex.

An in-depth Medium post from IronBee about how a verification loop affects AI coding agents, using Web-Bench and comparing DeepSeek with Claude Opus on a real web app task.

Shellular is a mobile remote-development app for running AI coding agents like Claude Code, Codex, Cursor, and OpenCode from a phone. It provides access to a real terminal, files, Git, ports, localhost apps, and browser DevTools on the host machine, with end-to-end encrypted relay access and app downloads for iOS and A

Anthropic research article on Claude interpretability, presenting evidence for a J-space and a global-workspace-like mechanism in language models.

Local CLI for analyzing when a coding agent starts degrading as session context fills, using transcript data already stored on disk.

Kiwi is a secure agentic control plane for running autonomous developer loops in the cloud while keeping secrets on the local machine. The repo describes a reverse-tunnel flow, credential caching, pause/resume behavior, Docker sandboxing, and a dashboard for monitoring tasks.

Adkumo is an AI marketing agent that turns a one-line brief or URL into on-brand ad creatives, with support for brand rules, multi-format exports, and publishing to ad platforms like Meta and LinkedIn.

A curated GitHub resource list for production AI agent infrastructure, covering runtimes, sandboxes, tool protocols, security, observability, and evaluation.

An open-source enforcement layer for AI coding agents that adds frozen specs, tamper-detected tests, independent verification, and hard-blocking gates so unverified work cannot pass.

Terminai is a transparent terminal wrapper that adds an AI overlay for Codex, Claude Code, and custom CLI agents. It gives agents live terminal context plus approval-gated shell suggestions while preserving the normal terminal workflow.

Browser-local tool for removing supported visible Gemini watermarks from single images or batches, with before/after review and ZIP export.

A Claude Code plugin and MCP server that keeps a persistent, read-only memory of a repo so agents can ask broad codebase questions without re-reading files every session.

Self-hosted AI security testing platform for authorized pentesting and bug bounty workflows, with a local web UI, live agent telemetry, verified findings, and branded PDF reports.

Heckle is a QA copilot for agentic app development. It lets you describe a bug in plain language while you use the app, then packages browser context like DOM, console, network, and path details for a coding agent to fix.

OpenAI-compatible LLM API with a flat $6/month plan, unlimited tokens, and no prompt storage. It’s aimed at developers running coding agents, automation, and other high-volume workflows.