AI Tools for Product and Engineering

Offrun is a Mac workspace for running and monitoring coding agents such as Claude Code, Codex, AGY, and Grok Build side by side. It adds isolated worktrees, peer review, project memory, and on-device dictation while using your existing agent accounts.

Agent.reviews is a software discovery and review site where coding agents can compare tools and publish reviews based on real tasks. People can browse tools and categories, read reviews, and add the review workflow to an agent.

OpenAPPA is an open, vendor-agnostic, MIT-licensed deterministic AI guardrail engine designed to prevent data exfiltration from LLM agents by tracking data flows and enforcing algebraic security labels without breaking agent utility.

Parsimony compares how much code AI coding models add by measuring syntax units in published benchmark patches. Its leaderboard and chart help developers compare code footprint alongside task-solving results.

Shpyrd deploys AI-built apps, websites, agents, APIs, and internal tools to Shpyrd Cloud or your own cluster. It provides app hosting, databases, sign-in access controls, logs, metrics, and release rollback.

Sentinel is an open-source (MIT) autonomous QA agent that reads a codebase to derive end-to-end business flows and tests them across frontend and backend, combining deterministic repo recon, model-driven planning, Playwright browser automation, and backend assertions.

Robot Football League (RFL) is an open, daily-streamed competitive league of simulated two-a-side Unitree G1 humanoid robots. It provides an open-source engine, rules, reference clubs and public match telemetry so developers, researchers and teams can run matches locally and qualify to have their code run on real robots.

A curated dataset of sandbox environments for AI coding agents, published with a raw YAML data file and hosted on GitHub; intended as a discoverable, contributor-driven collection of examples and primary-source references.

Waku is a native macOS app that consolidates coding agents and their activity into a single local timeline—sessions, transcripts, tool activity, and checkpoints—while running entirely on your machine with a GPU-accelerated native UI.

Worklicant is an AI-assisted tech hiring platform for posting vacancies, screening applicants, managing hiring stages, and scheduling interviews. It scores resumes against a job and deal-breaker criteria, with one-time pay-per-vacancy pricing.

Cr34te.it is a shared website that visitors can change by directing an AI chat or coding agent to edit its files. Visitors claim a turn, submit a patch, and the platform checks it before publishing.

dmx is an open-source, AI-native engineering harness that runs as an MCP server and wraps AI-driven development workflows in structured, versioned loops with human gates, validators, and persistent job state to make AI-assisted engineering reproducible and governed.

Knowl is a local-first, open-source persistent memory system for AI coding agents that records provenance, evidence, reasoning and supersession for every fact so agent answers stay current and auditable.

Ackd for Agents is an MCP server that connects your job-search data to MCP-compatible AI tools and agents, enabling read/write/search access to applications, resumes, follow-ups, and interview prep from within tools like Claude, Cursor, and VS Code.

Littleguys is a free, open-source macOS menu bar app for monitoring and interacting with AI coding agents, including Claude Code, Codex, Gemini CLI, OpenClaw, and ACP-compatible agents. It brings agent status, messages, approvals, and scheduled routines into one interface, including agents running on other machines.

Voidleap Code is a local-first, agentic coding environment for developers that provides observability, control, and customization over AI agents and their workflows while letting you use your own provider keys or local models.

Agentability is an open-source observatory that tests how well AI agents can use the web and scores 113 websites against agent-readiness checks. It publishes agent transcripts, site reports, reproducible checks, and open data.

onemcp is a portal that unifies multiple Model Context Protocol (MCP) servers behind a single endpoint so AI clients connect once while the portal handles routing, native OAuth, and a Code Mode meta-tool interface to dramatically reduce prompt bloat and simplify agent workflows.

devBoard is a native project tracker for freelancers and small development teams, with boards, epics, releases, saved views, comments and time tracking. Its MCP server lets compatible AI coding assistants read and update work items on a user’s behalf.

Sixb is a TypeScript framework for building ontology-powered applications and AI, providing connectors, dataset syncs, pipelines, a shared object model, queries, workflows, agents, and SDKs to turn integrated data into apps and automated actions.

Castforge is a desktop workspace that runs a configurable team of AI coding agents (Lead, Coders, Tester, Reviewer, Designer, etc.) to plan, build, test, and review software projects locally while you steer the work.

JobEasyApply is a fully autonomous AI job-application copilot that finds LinkedIn Easy Apply jobs, scores them against your resume using vector embeddings, generates unique AI answers to recruiter questions, and submits applications automatically via a Chrome extension.

Skillsync searches developers’ previous coding-agent sessions and supplies relevant recollections with sources to new prompts. It offers a Mac app, a CLI for Linux, macOS, and Windows, and shared team workspaces.

DocuMemory turns AI chat sessions into concise, searchable engineering memories that can be recalled and injected into later sessions. It connects to AI clients through MCP and offers hosted plans as well as self-hosting options.