Recently Evaluated

Open-source tooling for keeping coding-agent work alive across sessions and handoffs. It preserves work state, evidence, and next steps across agents like Codex, Claude, OpenCode, and Amp, with a CLI and local workspace flow.

A private, referral-based community for builders deploying agentic AI in production, with playbooks, case studies, and weekly working sessions focused on autonomous operations.

A research post from Prime Intellect comparing 153 autonomous runs across 18 frontier models on a nanoGPT optimizer speedrun. It presents the setup, harness, results, and discussion around autonomous AI research performance.

An agentic LLM-based coding tool that analyzes symbol names in source code, measures name ambiguity, and proposes clearer replacements with a human-in-the-loop review flow.

AGCX is an agent-commerce platform that lets autonomous buyers search product catalogs, settle purchases onchain, and handle returns and disputes without a human checkout flow.

A lightweight shell-based guard that blocks destructive commands before an AI coding agent can run them. It targets risky actions like git reset --hard, rm -rf, force-pushes, and destructive cloud/database commands, with local regex rules and a test script.

A native macOS Postgres GUI that can draft SQL from natural-language questions, using either a configured cloud model or Apple’s on-device Foundation Model on supported Macs.

Open-source, self-hosted monitoring for how a brand appears in AI assistant answers. It tracks mentions across models, generates prompt variations, trends visibility over time, and benchmarks competitors.

An unofficial Grafana plugin for Hermes Agent that records LLM calls and tool executions as generations and sends OTEL traces and metrics to Grafana Cloud.

Waku is a native desktop app for managing local coding agents in one timeline. It supports agents like Amp, Claude Code, Codex, Cursor, OpenCode, Grok, and Pi, keeps data on the user’s machine, and includes checkpoint-based rewind for code and conversation state.

Anthropic’s Claude Platform docs page tracking system prompt updates for Claude web and mobile apps, with dated entries across model versions and a note that the updates do not apply to the API.

Captain is an AI travel agent on Telegram that helps plan trips in plain language, compare live flight prices, organize complex itineraries, and monitor fares for better options.

Tempered is an AI-assisted Windows optimizer that explains performance issues in plain language, shows measured before-and-after results, and keeps changes revertible through an Undo Center.

A lightweight Hacker News view that filters out AI-related stories and shows a cleaner front page feed.

Molt is an open protocol for letting an AI agent make bounded purchases through disposable, single-use payment credentials. The repo includes a clear quickstart, MCP integration, a threat model, and a working test-mode demo.

A Claude Code skill for building Apple-style Liquid Glass UI, with CSS fallback, a refraction layer, and install steps for Claude Code and manual use.

A GitHub repo for SHOVE, a turn-based CLI tactics puzzle created by Claude Fable 5 and iterated through six play sessions until it was judged fun. The page includes a brief, writeup, source code, logs, and the main game script.

TypeScript SDK for AI agents and backends that connect to Squid Pay, letting agents propose payments or trades while the owner wallet remains the final signer.

ApplyWise is an AI job-hunt toolkit that generates ATS-friendly CVs and cover letters, scores applications against job descriptions, rewrites drafts to sound more natural, and offers a prompt library for job seekers.

A macOS feedback layer for coding agents that captures comments on text, screenshots, web elements, and voice, then passes them to agents through MCP with attached context.

A logical KV cache profiler and leak detector for PagedAttention engines like vLLM and SGLang, with a dashboard, live engine hook, CI checks, and Perfetto trace export.

A Windows voice-dictation app in Rust that runs locally with whisper.cpp, supports hotkey dictation, system audio capture, file transcription, and optional local LLM cleanup.

A native Emacs mode for chatting with AI agents via ACP, with prompt queueing, chat mode, image handling, and buffer navigation improvements.

A repo-improving agent harness that researches a codebase, proposes ideas, waits for human approval, and then drives execution with SHA-bound merge gating.