Coderabbit
Score 77 out of 100 — Strongcoderabbit.ai
What it does: AI-first pull request reviewer with context-aware feedback, line-by-line code suggestions, and real-time chat.
The full directory
Find the right tool for the job.
Search by the work you need done, then narrow by category, pricing, platform, score, or review activity.
Category results
52 tools matched your view.
Ito — AI code review that runs your code
Score 77 out of 100 — Strongito.ai
What it does: AI-powered code review tool that builds applications on every pull request, runs impacted user flows in isolated environments, and posts video evidence and bug reports directly to the PR.
KiHub — Hardware review platform for KiCad projects
Score 76 out of 100 — Strongkihub.dev
What it does: Review KiCad project changes from pull requests, branches, tags, or commits with visual diffs, checks, design discussions, and a traceable decision.
Muse Code — Meta’s terminal agent for long-horizon coding
Score 75 out of 100 — Strongmeta.ai
What it does: Meta AI Research is a division of Meta Platforms, Inc. that develops and releases AI models and tools. Key offerings include Muse Code, a terminal agent for long-horizon coding, and Muse Spark, a multimodal intelligence model. The site provides access to research publications, AI developer tools, and the Meta Model API.
Progress AI Observability — Trace, evaluate, and improve AI agents in production
Score 75 out of 100 — Strongtelerik.com
What it does: The Progress Agent Engineering Platform captures trace-level data from AI agents and LLM applications, including prompts, responses, model calls, retrieval steps, tool use, latency, token usage, and cost signals. It enables teams to debug failures, monitor production costs, evaluate output quality, and optimize workflows across .NET, Python, and JavaScript.
AgentConnect — Tag any agent, wherever work happens.
Score 74 out of 100 — Strongagentconnect.md
What it does: AgentConnect is an open-source, self-hostable platform for managing AI agent fleets across communication channels like Slack, Telegram, Discord, and GitHub. It provides a centralized dashboard to monitor agents, sessions, daemons, and schedules, assign roles/tools/memory, and integrate with tools like Figma and Fireflies.
Keystroke — Build powerful AI agents & workflows
Score 74 out of 100 — Fairkeystroke.ai
What it does: Keystroke gives teams everything they need to build powerful agents and AI systems in a single platform.
实在agent — 自主操作软件的企业级智能办公助理。
Score 72 out of 100 — Fairai-indeed.com
What it does: 实在Agent是基于AGI大模型 (TARS) 屏幕语言理解 (ISSUT) RPA机器人流程自动化等技术融合构建的超自动化企业级智能体。以自然对话的交互方式，将口述的任务自主拆解为步骤并转化RPA执行动作，同时自动识别界面、反馈修正、记忆历史经验，直至任务完成。
TraceLLM — OpenTelemetry for production AI applications
Score 72 out of 100 — Fairtracellm.in
What it does: TraceLLM connects prompts, retrieval, tool calls, model spans, token usage, errors, and exports into one inspectable workflow for production AI applications.
Show HN: GlassBox – what the browser reveals, and how identifiable you are
Score 72 out of 100 — Faircodecanary.org
What it does: Client-side browser fingerprinting diagnostic tool that runs live measurements in the browser and displays collected signals for identifiability assessment.
Premai
Score 71 out of 100 — Fairpremai.io
What it does: Prem provides a confidential API for secure, client-encrypted LLM inference at scale, featuring zero data retention options and attestation verification.
Gauge — Agent Led Growth: Get written into every customer's codebase
Score 70 out of 100 — Fairwithgauge.com
What it does: AI visibility platform that tracks brand mentions across LLMs (ChatGPT, Gemini, Perplexity), analyzes citation gaps, and generates/publishes content to improve AI search presence. Also offers Agent Led Growth to track how coding agents select tools.
Buildship
Score 70 out of 100 — Fairbuildship.com
What it does: Visual workflow automation platform for building backend logic, APIs, and AI agent tools using natural language or low-code/no-code interfaces. Connects to hundreds of external apps, databases, and AI models.
Token Harbor — The easiest way to access frontier AI models.
Score 70 out of 100 — Fairtokenharbor.ai
What it does: Token Harbor is a unified, OpenAI-compatible API gateway providing developers and teams with access to frontier AI models through a single key, dashboard, and per-token billing system.
Agent Orchestrator — Your coding agent fleet manager
Score 69 out of 100 — Fairaoagents.dev
What it does: Open-source desktop IDE and local CLI for supervising fleets of parallel AI coding agents in isolated Git worktrees, managing branches, reviews, CI status, and merge workflows without API proxying.
Clears — Move beyond AI coding to agentic software delivery
Score 68 out of 100 — Fairclears.ai
What it does: Clears is an agentic execution platform that autonomously executes software delivery from requirements to reviewed pull requests, coordinating engineering workflows across the SDLC.
HookLens — Real-time webhook triage & AI root-cause analysis
Score 66 out of 100 — Fairusehooklens.com
What it does: HookLens intercepts failed webhooks across Stripe, PayPal, WooCommerce, Shopify, GitHub and custom APIs, diagnoses the root cause in seconds with AI, and notifies your team directly in Slack & Discord.
Treebar — Treebar gives you one view of every active worktree
Score 66 out of 100 — Fairtreebar.net
What it does: Treebar is a macOS desktop application that provides a read-only, local-first view of active Git worktrees directly from the Mac notch. It groups work by project, displays branch changes and diffs on demand, and controls folder access without modifying repositories or reading prompts.
Chert — Vapi for FaceTime: AI video agents in a few lines
Score 65 out of 100 — Fairtrychert.com
What it does: YC-backed AI company building iMessage infrastructure for reaching people at scale, enabling developers to deploy AI agents that communicate via real iMessage with quality, trust, and personalized interaction.
Origin by Cursor — The Git forge built for the age of coding agents
Score 64 out of 100 — Faircursor.com
What it does: Cursor plans, writes, and reviews code using AI agents that understand your entire codebase. Everywhere you work: Desktop, CLI, Web & Mobile.
MiniMax Design — Your own agent team for open-ended creation
Score 64 out of 100 — Fairminimax.io
What it does: A multimodal AI creative studio that turns ideas into finished images, videos, voiceovers and edits. Keep local files private and reuse workflows with Skills.
Openbase — Manage your team of AI agents by voice, from anywhere
Score 63 out of 100 — Fairopenbase.cloud
What it does: Voice-controlled IDE that allows developers to direct coding agents via spoken commands, approve sensitive actions, and review code diffs remotely from a mobile device while the agent executes locally on a Mac.
Grok 4.5 — SpaceXAI's model for coding, agentic tasks & knowledge work
Score 58 out of 100 — Below the barx.ai
What it does: Grok is an AI assistant offering chat, real-time web/X search, multi-agent reasoning, and text-to-image/video generation across web, iOS, Android, and X. It provides free and paid subscription tiers alongside a developer API for business and enterprise use.
akta.pro — Private company data and signals API for the agent economy
Score 58 out of 100 — Below the barakta.pro
What it does: Private company data and signals API providing access to 20M+ global entities, real-time news signals, and historical archives. Supports agent workflows via API, MCP, CLI, and bulk export.
AI & Agent Infrastructure
38 sitesAgent runtimes, model APIs, LLM observability, agent tooling and training data
Productivity & Utilities
44 sitesNotes, calendar, inbox, meeting capture, and desktop, file and web utilities