developer tools

Open-source benchmark that measures which developer tools LLMs recommend when asked to build real web apps. It runs fixed prompts against a panel of models, parses the tool recommendations, and publishes rankings and head-to-head comparisons.

dmx is an open-source MCP server that adds structured, gated workflows to coding agents like Cursor, Claude Code, and Copilot. It focuses on loop-based development with human approval points, validators, persistent job state, and repo-backed configuration.

Weir is a CI gate for AI agents that reads OpenTelemetry traces and fails builds when sensitive data reaches forbidden sinks. It includes a gauge for trace coverage, taint tracking, HTML reports, and rule-based scans for agent workflows.

Wolfpack is a self-hosted control room for persistent coding-agent sessions across your machines, with Tailscale-based private access and support for tools like Claude Code, Codex CLI, Gemini CLI, and shell sessions.

A hands-on lab toolkit for Docker and container security, covering CIS checks, image hardening, signing, SBOMs, admission control, runtime security, and AI context-poisoning defenses.

Codecut is a CLI for keeping coding agents on track by turning project rules into automatic checks. It flags issues like missing tests, failing test output, temporary agent comments, long code comments, and large changes that need an explanation, then explains what to fix.

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 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 self-healing knowledge layer for AI coding agents with trust-verified search results, session auto-sync, and filesystem-backed reconciliation.

A community gallery of Claude Code status lines with rendered previews and one-paste copy options, aimed at developers customizing their Claude Code workflow.

A GitHub project that adds a popup UI for surfacing and editing a coding agent’s implicit assumptions while it works. The README describes how a watcher sub-agent scans session history, generates steering controls, and updates decisions without polluting the main thread.

SightDiff is a local visual proof tool for checking what an AI coding agent changed before you commit. It captures baseline screenshots, re-renders your app after changes, and shows a before/after diff sheet with changed and unchanged surfaces flagged.

Public benchmark for comparing agent memory systems, with separate textual and coding tracks, submission flow, documentation, and API guidance.

An open-source benchmark for testing whether LLMs can follow long arithmetic derivations without using tools. It compares models on recall-proof inputs, logs digit accuracy, and reports results across multiple endpoints and model families.

GreatArrow.ai is an open beta workspace that gives Claude, ChatGPT, Cursor, Gemini, and other MCP-compatible clients shared memory plus action access across tools like Gmail, Slack, GitHub, Notion, and Jira.

Bb is an agentic IDE that can control itself, with a desktop app, CLI, web app, and HTTP API for orchestrating coding agents and running work in live threads.

Research preview for a voice-agent reasoning harness that lets a realtime assistant think between turns without adding in-band latency. The page includes benchmark results, pricing, example behavior, and a description of the architecture behind Waterr’s AI meetings.

Open-source runtime guardrails for AI agents that intercept unsafe tool calls before they execute, aiming to block prompt-injection-driven exfiltration and other policy violations.

A web tool that compares how many AI tasks different models can buy per hour of work across countries, using wage and benchmark-cost data.

A Linux-only CLI wrapper that lets users switch between isolated Claude Code accounts without re-authenticating, using separate config directories per profile.

Projektor is a self-hosted issue tracker and wiki built for AI agents as the primary client, with MCP-based agent access and Cloudflare-based deployment.

A local-first Windows tool for indexing, searching, and loading large agent skill libraries without keeping full skill bodies in context. It supports SQLite FTS5 search, multiple ranking modes, CLI use, HTTP, and MCP stdio.

Open-source runtime action grounding framework for AI agents. It verifies proposed agent actions against live systems of record before execution and can return allow, hold-for-human, or block decisions.

A VS Code extension that organizes Claude Code and Codex sessions around Git worktrees, keeping sessions, terminals, changed files, and provider tabs in one cockpit.