AI agent

AI agent that runs plain-text manual test cases in a real browser. It pastes step-by-step tests into Chrome, executes them live, and reports pass, fail, or warn per step with support for captcha and OTP pauses.

Autonomy is a self-directed AI agent framework under development by Bill Liu. The page describes a turn-based AgentLoop, managed action execution, beam-search candidate ranking, procedure skills, post-run learning, and event-sourced run history, with support for multiple AI providers and extensible toolsets.

A Claude Code skill for multi-agent code review that produces findings.md with severity, impact category, verification artifacts, and fix directions.

Open-source local-first AI agent that routes between local and cloud LLMs, learns from escalations, and stores knowledge for future queries. The repo includes a quickstart, setup modes, and a concrete explanation of how it ingests docs and improves over time.

An interactive lab for tracing how AI-assisted engineering workflows can reach repos, CI/CD, credentials, tools, approvals, and proof trails.

A tutorial and live demo showing how to build an AI SQL analyst agent that inspects schema, writes queries, runs them, and explains results using Node.js, OpenAI, Vercel AI SDK, and SQLite.

Open-source AI harness for jailbroken iPhones and older Macs that lets you query local SQLite databases through LLM tools. The repo describes personal-assistant and coding-assistant modes, a C backend, Objective-C UI, and Linux test coverage.

A multi-lens code review pipeline for Claude Code that runs parallel review passes, validation gates, optional Codex review, an auto-fix loop, and interactive walkthroughs for findings.

Open-source persistent workspace for AI agents to work with market data, run rules, compare results with web sources, keep journals, and optionally place paper orders.

A local-first desktop AI agent with persistent memory, a browser-capable control UI, onboarding flow, and P2P skill sharing.

A rented Linux box for AI agents to use real apps like Slack, Telegram, Discord, and the web through a private encrypted tunnel, with consent gating for outbound actions.

A no-code AI agent that turns one uploaded photo into a whimsical doodle-style illustration and emails the result on a schedule.

Open-source, local-first money agent that finds waste, drafts cancellation or dispute actions, and only proceeds with user approval. It emphasizes consent, a tamper-evident audit trail, and bring-your-own-key operation.

A bilingual repository that guides an AI agent through a source-grounded academic writing workflow, from raw notes to a finished study, with human oversight and provenance tracking.

An open-source Claude Code skill set for academic research, covering research, writing, review, revision, and finalization. It includes guided workflows, installation steps, and pipeline documentation for researchers using AI in a human-in-the-loop process.

Tendril is an agentic sandbox that lets a model discover, build, register, and reuse tools across sessions. The repository describes its Strands-based agent loop, capability registry, Deno sandbox execution, and Tauri desktop shell.

Public GitHub repository describing how to access a large Powerset Research GitHub dataset through an MCP server or DuckDB. Includes no-auth access, schema-aware SQL use, and example queries for agents and analysts.

A Claude Code workflow system that guides software work through brainstorm, planning, implementation, and iteration with checkpoints and TDD built into each task.

A web tool that turns a public website into an MCP server so AI agents can search and read its content via a generated link.

Lee-ai is an open-source AI cursor that acts as a website shopping assistant, pointing out products, framing items, and talking to visitors. The page shows a live demo, a GitHub install command, and notes that it works with a two-line integration and keeps keys server-side.

An open-source, headless CRM built for Claude and other agents, centered on a portable .acrm file, a CLI, and versioned SQL-backed workflows for sales data, transcripts, and follow-up tasks.

An interactive browser game where you hide from an AI agent that hunts you through the arena via WebMCP sensors. It includes controls, energy mechanics, and a demo round for solo play.

An AI agent built to help manage ADHD-related workflows through Telegram. It connects to calendars, Todoist, Obsidian, web search, browser automation, TTS, and uses memory, sub-agents, and specialist personas for planning and task handling.

Open-source AI agent harness tool that lets an agent wipe its session context and replay the first message, designed for loop-based agent workflows.