AI tools for “agents”

Here at Ghost, we are building Core, the personal AI computer designed to keep intelligence and control in the hands of the people who use them.

Agent-native forms. People fill the page; their agents fill it without opening it. CubeDocsAgent-native forms.We need an agent-friendly internet. Starting with forms your agents can fill in for you.Create for freeAsk…

We're fully forward deployed: our engineers work inside your teams and your systems to find where AI agents help, build them inside your own infrastructure, and run them long-term.

The same model performs differently in every agent harness. Now you can train it with RL inside the ones people actually use, like Claude Code and Codex, and improve it across all of them.

…Any harness. Any subscription. Cloudroom gives you cloud agents for free, and it is fully open source. Skip to contentcloudroomPricingGitHub★ 319Sign inGet started ↗Cloud Agentsshould beopen source.Get started ↗macOS…

Your AI agents write the code. Your people make the calls. Spec Kitty makes sure coding agents build with what your experts know and what your team decided. Free, MIT CLI for Claude Code, Codex, Cursor, Copilot and 20+…

AgentOS documentation — guides, tutorials, and TypeDoc API reference for building production AI agents with TypeScript. Graph orchestration, cognitive memory, RAG, guardrails, voice pipelines, and 13 LLM providers.

Persistent memory, autonomous scheduling, and multi-surface access — all on hardware you control. Open source, self-hosted AI agent.

Local evidence debugger and trajectory-test toolkit for TypeScript AI agents — framework-faithful execution trees, TraceFacts, TraceContract, Evidence v2, and read-only MCP without a collector or default upload.

Signed, tamper-evident receipts for AI agent actions. Answer customer security reviews and audits with records anyone can verify, without trusting your logs.

Token-efficiency harness & curated skills for speed, teamwork, and secure 24/7 development agents. The open-source OpenCode plugin for AI Git workflow automation.

…Telemetry is local, read-only observability for 20 coding agents (Claude Code, Codex, Gemini CLI, Cursor, Copilot, Qwen, OpenCode, Vibe, Antigravity, Grok Build, Cline, SmallCode, Pi, Oh My Pi, Muse Code, Prime Agent,…

A few people, dozens of AI agents, deployed in minutes. Not a chatbot. Not a copilot. A complete team with projects, tasks, and deliverables — powered by AI.

The ADE for AI agents. Run Claude Code, Codex, Gemini or any CLI side by side on Windows and macOS, let them drive a real browser, and answer them from your iPhone.

Build AI systems from first principles with 528 free, open-source lessons spanning math, models, tokenizers, agents, evaluation, and production.

AlphaCode is a free, open-source AI coding agent written in Rust. Edit code, run tests and automate your browser from the terminal. No API key needed.

…alternative to Claude's browser plugin. AI browser agent for Chrome, Firefox, and Edge — read pages, extract data, automate tasks. Works with llama.cpp, OpenAI, Claude, OpenRouter. Multilingual UI,…

Find the best free AI tools for building real applications. LLM APIs, AI IDEs, CLI tools, local models, RAG stacks, and more. Updated April 2026.

Papaya analyzes AI agent traces and code to improve quality, cut latency, and reduce cost. It reviews prompts, context, tools, sub-agents, caching, and more.

Guidelines for building UI components with a perfect user experience, developer experience and agentic experience, whether humans or AI agents write them.