Recently Evaluated

A monthly briefing on agentic coding developments, covering model releases, benchmarks, tool updates, and workflows for engineers and technical leaders.

AI-powered PDF to Markdown converter focused on preserving structure like headings, tables, images, and reading order for research, docs, and knowledge workflows.

Claudinho is a community marketplace for Claude skills, letting users browse and install ready-made skills by task instead of searching manually. The page highlights thousands of skills, category browsing, and one-click installation without a terminal.

Open-source local document memory for AI tools, coding agents, and humans. It offers a local CLI, optional daemon, searchable notes, metadata, tags, links, and version history.

Clor is a tool for creating background or scheduled AI agents (“claws”) that reuse the same MCP servers, CLIs, skills, and tools as a coding agent. It includes a CLI install flow, docs, pricing, and examples for monitoring, reporting, support, and changelog workflows.

Open-source TypeScript project for building a minimal coding agent that can write and modify its own code, with setup instructions and example commands in the README.

Cast is an open-source, self-hosted harness for multi-user Claude agents. It focuses on routing, identity, and access control outside the prompt, with support for agent building, review flows, and extensions like email, calendar, web fetch, and WhatsApp.

A Python CLI that packages data science repositories and data-heavy project files into LLM-friendly prompts, with sampling for CSV, SQL, Excel, and notebooks.

Open-source interface for running coding agents from phone, desktop, web, and CLI. Supports multiple providers, runs locally on your own machine, and includes a daemon plus client apps.

NUA is a compliance-testing agent for regtech teams. It ingests rules, runs generated checks against a product, flags gaps, and produces an audit-ready coverage report that updates on every release.

A pure-Python LLM inference engine and server with CUDA/HIP/Metal code generation, OpenAI-compatible API support, built-in RAG, and multi-GPU backend support.

A blog post about verifiable RAG that benchmarks open-source NLI verifiers against Claude on RAGTruth and describes a Python library for sentence-level citation and claim verification.

PaperProfit explains an AI-assisted stock evaluation approach that combines fundamentals, technical signals, and qualitative analysis from transcripts and SEC filings into a weighted score.

OpenAI’s SDK docs for programmatically controlling local Codex agents, with coverage of setup, core concepts, tools, orchestration, evaluation, and deployment paths.

A technical guide that shows how to build a small CLI-based LLM agent for microservices using tool discovery, model calls, conversation history, and a REPL loop.

A macOS utility that keeps a MacBook awake while AI agents are running, then lets normal sleep resume when they go idle. It includes install scripts, hooks for Claude Code and Codex, and a menu bar status indicator.

A Python filter layer for LLM apps that evaluates responses against a Lean-verified Scherf logic backend and can pass, flag, correct, or block output.

A detailed tutorial that explains what agent tools are and walks through a basic set of implementation patterns for an AI agent in Python, including bash, file, search, edit, and web fetch tools.

A GitHub-hosted guidelines file for AI coding assistants used in Stanford CS336. It tells assistants how to help students with debugging, explanations, and feedback while avoiding direct solutions or code generation.

An open-source ecommerce starter that boots a Magento or Mage-OS store in GitHub Codespaces and uses Claude to make changes directly in the live dev environment.

A local Go tool that turns encrypted iOS WhatsApp backups into a searchable workspace for AI agents, with OCR, transcription, and SQLite/FTS5 indexing.

A local AI IDE plugin that cleans up messy prompts before they reach Claude, Cursor, or OpenCode. It fixes typos, dropped words, and split tokens on-device with no network or token cost.

QVAC SDK 0.12.0 adds TurboQuant, a KV-cache quantization feature for local LLM inference that claims up to 5x more context on-device with no retraining or code changes.

JetBrains introduces Mellum2, an open-source 12B model built for software engineering workflows, routing, Q&A, RAG, sub-agents, and private deployment.