Recently Evaluated

A Python CLI and research toolkit for simulating AI training math before model training. It estimates memory, training time, token budget, config risks, benchmark speed, and reliability, with optional native Rust and C backends.

Retriever AI’s blog post explains a browser-agent architecture built around DeepSeek Flash, text-only DOM handling, and executable code as the planning layer. It includes concrete examples of the harness, the model’s role, and the cost argument behind the approach.

AirPosture is an open-source iOS app that turns AirPods sensor data into a real-time posture coach, with features like background tracking, posture streaks, activity switching, stretching prompts, and Live Activity syncing.

A Python library that transpiles stateful imperative LLM workflows into optimizable DSPy programs, with typed outputs, self-correction loops, validation reporting, and prompt tuning support.

A free AI tools directory and review site that ranks 14 tools and publishes comparison guides across writing, images, video, coding, and other workflows.

An MCP server that gives AI agents access to 8,500+ curated awesome lists and 1.3M+ resources, with hosted and local setup options plus tool docs and example queries.

A reference implementation for intent-execution separation in LLM agents. The project uses a typed intent layer (SIF) over domain vocabularies, with a deterministic execution layer and demo domains for legal and veterinary workflows.

A persistent code knowledge graph and MCP server for AI coding agents. It analyzes codebases, builds a graph of files, symbols, commits, and cross-boundary edges, and exposes MCP tools plus generated markdown artifacts for agent workflows.

Local-first desktop LLM wiki that hydrates notes, PDFs, emails, and docs into Markdown entries, then retrieves them with keyword search and link traversal instead of embeddings or a vector DB.

A Claude Code plugin that fills agent wait time with rotating dev news in the status line, with HN, GitHub Trending, per-language sources, auto-translation, and short summaries.

Open-source multi-agent protocol for AI research agents. It pairs a tool-using Scientist with a question-only advisor that can only ask questions and approve plans, and the README includes quick-start setup plus notes on reproducing results on MLE-bench/Kaggle tasks.

CLI tool for versioning, diffing, rolling back, and searching AI prompts, with Git-style workflows for prompt management.

Open-source authorization engine for AI agents that gates actions by confidence, policy, and human review, with prompt-injection detection and full audit logging.

Open-source AI agent framework and meta-harness for orchestrating Claude Code, Codex, Cursor, Pi, and custom agents with policies, sandboxing, and cross-device collaboration.

Local-first document AI that extracts structured JSON from PDFs, scans, images, text, and Markdown without sending data to a third-party API. It includes a REST API, CLI, and Web UI, and supports local execution on macOS Apple Silicon and Linux NVIDIA systems.

A visual workspace where designers, engineers, and AI agents work on the same canvas, with live code, previews, collaboration, and integrations for tools like Claude Code, Codex, Cursor, GitHub, and MCP.

Google’s announcement for a built-in computer use tool in Gemini 3.5 Flash. The page explains that developers can use it to build agents that interact across browser, mobile, and desktop environments, with safety features and access through the Gemini API and Gemini Enterprise Agent Platform.

Michii is an AI product team for online businesses that claims to plan, build, launch, market, support customers, and fix issues for founders who do not want to hire a tech team.

An open-source, self-hostable customer platform built for the agentic era, with MCP-first tooling for knowledge base, conversations, CRM, CMS, outreach, and analytics. The README shows concrete modules, data portability, and self-host setup instructions.

A dynamic MCP server that turns JSON configs into callable API tools, with lazy tool discovery, hot reload, and a hosted console/registry.

A native macOS menu-bar app that lets you mark exact pixels in a screenshot and copy an AI-ready prompt with annotated image context and marker notes.

A Rust CLI and MCP server for orchestrating multiple coding agents, fusing their answers, and resuming or routing agent sessions locally.

Giskard presents an AI red-teaming and continuous evaluation platform focused on finding hallucinations, security issues, and agent vulnerabilities. The page explains how it compares tools for agent-level testing, regression checks, and guardrail workflows.

Tecture helps coding agents write and maintain architecture docs directly in the repo, then lets teams explore them as interactive diagrams in VS Code or the browser.