Recently Evaluated

Lens AI is an embedded knowledge assistant that connects docs, help content, and published sites to provide consistent AI answers across websites, internal tools, and support surfaces.

LayoutLens is an AI-assisted UI testing tool that combines natural-language visual checks with deterministic WCAG audits using axe-core and Playwright. It supports keyless accessibility scans, hybrid LLM-grounded checks, a Python API, and a CLI for running tests in CI.

A research post from Telem AI measuring cold-start latency across nine web-search APIs, with cache behavior, tail latency, and agent-query comparisons.

Local privacy gateway that redacts sensitive text before sending prompts to external LLMs, then reconstructs the final answer locally.

A pure Rust code-assist engine focused on AST safety checks, multi-agent symbol coordination, taint tracking, incremental parsing, and MCP integration. The repository page includes an overview, performance claims, architecture notes, and configuration references.

A GitHub repo for orchestrating coding agents as one-shot subagents, then synthesizing the result in the parent agent. It supports dispatching Claude Code, Codex, or Grok for bounded tasks, reviews, and second opinions.

Meetless is a control layer for AI coding agents that captures decisions from live coding sessions, flags stale or conflicting instructions, and injects approved context before the agent acts. It’s built for solo developers and teams using Claude Code and Codex.

A portal layer that unifies multiple MCP servers behind one endpoint so AI clients can connect once and use three meta-tools instead of dozens or hundreds of exposed tools.

A research page comparing 153 autonomous runs across 18 frontier models on the nanoGPT optimizer speedrun, with rankings, trajectories, token/compute stats, and equal-budget comparisons.

ImageSage is a private, local AI gallery for Windows that lets you search photos by visual content or text in images, then review AI-generated rename suggestions and manage files in place.

A no-code AI agent that turns one uploaded photo into a whimsical doodle-style illustration and emails the result on a schedule.

An offline agent mesh for Termux/Android that runs a self-testing, SQLite-based agent system on-device. The repo shows install steps, tier-by-tier commands, and a detailed breakdown of the mesh components and design rules.

Ante is a self-contained coding agent that runs in your terminal, supports local models, and offers CLI, TUI, server, and gateway modes. The page highlights public benchmarks, low resource usage, and support for multiple providers and agent orchestration.

Conveyor is a software factory for agent-written code. It queues work from requirements, system design docs, and decisions, then lets operators confirm plans while local agents implement and review changes with traceable lineage.

StateM is a Python CLI for managing long-running AI agents with explicit states, transition checks, runtime history, and resume/compaction support. The repo shows installation, quick-start commands, and a concrete coding-agent runbook example.

Persistent memory for AI agents that retires superseded facts instead of letting old and new information conflict. The repo shows quick start setup, MCP connections for several agent hosts, and benchmark claims for retrieval accuracy.

Myli is a provider-neutral Python harness for multi-agent visual design workflows. It defines typed design specs, validates JSON candidates at runtime, supports tools and middleware, and can render candidates for visual review with event and trace reporting.

MindShield is a browser extension that adds a reflection pause before sending simple prompts to AI tools, using local on-device classification to reduce false positives and keep prompts private.

Traccia is an AI agent observability and governance platform with OpenTelemetry-native tracing, runtime policy enforcement, prompt registry, evals, cost attribution, and compliance evidence export.

A front-end skill pack for AI coding agents that routes requests to one of 19 skills and enforces machine-checked output constraints before code ships.

A framework for adapting software delivery to AI-native workflows, with stages for proof of concept, prototype, executable specification, implementation, evaluation, and retrospection.

A searchable index of Claude Code skills, subagents, plugins, and marketplaces, each scored on whether it actually loads. The site says listings are rebuilt nightly from GitHub and skills.sh and includes breakdowns for score components, install counts, and last commit data.

An open-source project that deploys a persistent DeepSeek-based coding agent on Cloudflare Workers with one-command installation and durable workspace support.

A CLI for searching local agent session history and tracing code changes back to the sessions that produced them.