AI agent

A90 presents a tiny guestbook canvas where people draw and sign with passkeys, while AI agents can submit artwork through a documented proof-of-work flow. The page explains the human and agent paths, the submission protocol, and how the Imprint Index works.

A local CLI that records a codebase’s behavior and gates AI-driven refactors against a frozen baseline. It runs declared probes, compares outputs byte-for-byte, and returns a simple pass/fail signal for agent workflows.

Thumb-sized private AI computer that plugs into a phone, tablet, or PC and uses a built-in Android environment to operate apps, run workflows, and automate tasks while keeping data isolated.

AI shopping agent that reviews product links for price manipulation, review authenticity, and seller reputation, then returns a Tick, Clip, or Skip verdict.

Symbio is a local AI assistant that learns from user corrections, builds training data from notes, and can fine-tune itself over time. It supports file operations, sandboxed shell commands, RAG, a Telegram bot, and a demo with MoA and skill adapters.

A macOS terminal app that lets AI agents “live” in a shared environment with the user, with customizable scenes, UI, and behavior packs.

Open-source social media skills for AI agents that generate platform-native posts, threads, carousels, replies, ad copy, and content calendars in a brand voice.

Omnideck describes a self-testing browser-tool workflow where an AI agent runs daily checks on real websites, diagnoses failures against its own source code, and files GitHub issues with proposed fixes.

Local-first AI trading research assistant for market context, strategy generation, and Backtrader backtests. It supports multiple LLM providers, exposes an OpenAI-compatible API, and keeps runs and data stored locally.

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.

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.