3.6k+ AI tools. Sorted by what actually ships.
Contextberg is a local memory app for AI coding agents. It watches your screens, agent transcripts, and browser activity in the background, then serves both short-term and long-term memory to agents like Claude Code, Cursor, and OpenClaw over the Model Context Protocol (MCP). It is privacy-first and Windows-first - your data never leaves your machine - and installs from the Microsoft Store.
Cleo is an AI product manager for founders and lean teams that lives inside Telegram, Discord, and Slack. It learns your tone, knows your team, connects your sources, and runs the recurring PM work, including standups, follow-ups, decisions, and one-page briefs covering the top bet, the customers asking, the evidence chain, and a draft spec. Every fact Cleo learns is transparent with a visible source and confidence, and it operates across five trust levels from observer to operator. Cleo is free to use in Telegram.
Hiro is your agentic security team — scan, fix, triage, and turn every fix into SOC 2 evidence. Built for the Claude Code stack, it works from first commit to audit. Hiro is the autonomous security team for fast-moving companies, built by former SRE leaders at Samsara who spent years doing this work manually. Y Combinator-backed.
Runtime is the runtime for all your team's coding agents. It provides sandboxed environments with your company's context, integrations, and guardrails, so anyone on your team — engineers, PMs, designers, marketers, ops — can spin up an environment in milliseconds, make changes with their preferred coding agent (Claude Code, Codex, Cursor, Gemini, Copilot, OpenCode), and open a PR through the same review process as anything else. Works programmatically or through Slack, Linear, Jira, Asana, Teams, and CLI. Session-level observability, configurable guardrails, and a live preview of production.
Relay captures context from your AI chats and keeps a living project brief synced across ChatGPT, Claude, Cursor, Claude Code, and 20+ tools.
Nimbus is an AI-native browser companion that navigates, fills forms, and extracts data — so you can focus on decisions that matter.
Per-project colors, icons, and names. Stop confusing 10 identical terminal windows. 14-day free trial on macOS.
HiveTerm is one terminal workspace where Claude Code, Codex, Gemini, Cline, and your dev stack run side by side. Config-driven via a hive.yml, with per-agent recap, voice input, and an integrated MCP server (Queen) that lets agents spawn sub-agents and talk to each other.
The best AI tools in your inbox. 7am. Free.
Join 2,029 builders reading daily.
Traycer brings spec-first development to AI coding workflows, helping developers plan changes clearly and execute them with confidence. It turns product intent into shared, structured specs that teams can refine together, then guides coding agents with full context and verifies every change against the plan. Features include spec-driven development, team artifacts, task orchestration, one-click hand-off to AI agents, and review changes with codebase scanning.
Bito AI Architect builds a knowledge graph from your code, commits, docs, and issues to provide full system context for autonomous development. It enables technical design, grounded code generation, and AI code reviews across coding agents and issue trackers like Cursor, Claude Code, Jira, and Slack. Trusted by enterprise teams, it reduces planning from days to hours, accelerates onboarding, and cuts PR review time by 89%.
ChatBetter is a tool that routes questions to the right LLM model for the task, grounds responses in source data, and lets agents judge and combine outputs automatically. It focuses on multi-model orchestration, quality guardrails, and trustworthy AI output. The project is now being succeeded by Unsupervised (long-running agentic data analysis) and DeepWork (automate long-running processes with Claude Code). Open source alternatives include OpenChatBetter and TokenWar.
Multiplayer connects your favorite coding agent to production to automatically fix application bugs. It runs locally, captures full-stack data including frontend screens, backend traces, logs, and request/response content, and routes issues to agents like Claude Code, Codex, or Copilot. It deduplicates issues and generates high-quality PRs, eliminating noisy PR slop.