Recently Evaluated

Open Science is an open-source AI workbench for scientists. It combines literature, code, figures, reports, and review into a local-first desktop workflow with model choice, reproducible artifacts, and scientific agent skills.

Excalibur is an open-source AI coding agent for product engineers. It runs from the terminal, supports multiple model providers, and covers the full workflow from discovery and planning through implementation, verification, review, and shipping.

Local-first browser tool for reviewing rendered markdown like a Google Doc, with AI agents (Claude or Codex) turning comments into inline answers or real git diffs.

peek-cli lets coding agents capture screenshots of open browser tabs through a browser extension and WebSocket daemon. The repo shows CLI usage, installation steps, supported integrations, and a safety explanation.

A playful benchmark dashboard that ranks LLMs based on one person's 10-question scoring process.

A read-only Claude Code skill that runs OpenAI Codex CLI as a second-model reviewer on diffs, with scoped review modes for branches, commits, and uncommitted changes.

WakaWiki is a Rust CLI that generates and keeps agent-facing documentation up to date for a codebase. It supports multiple model providers, a zero-LLM scan mode, incremental updates, and AGENTS.md integration, with CI-friendly GitHub Actions usage documented in the README.

A free open-source Mac app that lets non-coders enable and manage Claude Cowork skills and personas through a switchboard-style UI.

A closed-loop controller for LLM training that adapts batch size, learning rate, checkpointing, and pruning to reduce OOM crashes on limited VRAM hardware.

Pulse is an AI incident response tool that watches systems, diagnoses PagerDuty incidents with Claude, and posts suggested fixes to Slack for one-click resolve or escalation.

A native C++/SDL3 desktop IDE built to be driven by LLM agents, with editor, git, merge, terminal, search, and full DAP debugging workflows.

AI-powered code review tool that analyzes git diffs and produces structured review reports, with support for GitHub Action workflows and multiple model providers.

A small Nix-based wrapper that adds an exponential timeout around agentic AI tools and resets the limit each day, with a reminder message before the tool runs.

Open-source telephony infrastructure for AI agents. AgentLine provides a REST API and MCP server for making and receiving phone calls, handling SMS, and storing transcripts, with Docker-based local setup and a hosted option.

A minimalist CLI LLM chatbot written in Python. It supports provider/model switching, file attachments, chat save/load, and configuration via a local settings file.

A free public API for LLM pricing, specs, benchmarks, and cost calculations across 1,000+ models. It offers no-auth endpoints, CORS support, an OpenAPI spec, and a LiteLLM-compatible cost map that refreshes daily.

A self-hosted email client on Cloudflare Workers with an AI agent for reading inboxes, searching conversations, and drafting replies. The project includes deployment and setup instructions, feature details, and a clear Cloudflare-based architecture.

An OpenAI-compatible API proxy for using DeepSeek models with standard OpenAI SDKs, billed pay-as-you-go and accessible without phone verification.

An AI skill that plans and optimizes vehicle delivery routes from natural language using Routing24’s WebMCP tools. It supports multi-stop route planning, shareable outputs, and installation for compatible agents like Claude or Cowork.

A catalog of design patterns for building agentic systems that verify outputs with evidence instead of relying on self-review. The page explains two main failure modes and presents structured patterns for context, verification, and orchestration.

A research prototype for a BitTorrent-style mesh where coding agents share idle capacity, delegate tasks, and settle credits across peers.

GetSuperpower is a CLI and workflow bundle for coding agents that packages multi-step agent workflows into one installable skill tree.

SigMap is a deterministic grounding layer for AI code work. It generates a signature-and-evidence map, helps pick relevant files, validates coverage, and judges whether an AI answer is grounded in the repo.

OpenScience is an open-source AI workbench for scientific research. It can read papers, plan hypotheses, write and run code, manage experiments, query scientific databases, and present results in a browser-based workspace.