Developer Tools AI Tools

Local guardrails for AI coding agents that intercept destructive actions before they execute, now extended to Git hooks for commit and push enforcement.

Kimi WebBridge is a browser extension that lets AI agents click, fill forms, navigate, screenshot, and extract data in Chrome or Edge while running locally on the user’s device.

A browser-based demo where an AI agent writes x86_64 assembly and eBPF to generate Wolfram cellular automata and Mandelbrot fractals inside a real Linux VM, with framebuffer and kernel trace streams exposed live.

An open-source MCP server for controlling macOS with AI agents. It supports file navigation, app control, UI interaction, browser automation, and system operations, with setup instructions and client integrations for tools like Claude Desktop and Gemini CLI.

A VS Code AI sidebar for focused coding help, with voice input, file and selection chat, Git and debugger context, and support for OpenAI-compatible, local, and budget models.

Darc is a CLI tool for coding agents that indexes prior agent sessions for grep-like memory search and lets teams share encrypted session indexes through Git-backed branches.

A local-first shared development environment for humans and CLI coding agents, with persistent workspaces, worktree-isolated tasks, agent coordination, and built-in review and browser tools.

A native macOS Markdown viewer that renders GitHub-flavored and Obsidian-style Markdown in a lightweight app with CLI, drag-and-drop, file association, math, Mermaid diagrams, and frontmatter support.

A zero-config CLI that scans repositories for AI-slop patterns like missing .env.example files, committed secrets, large files, duplicated code, TODO drift, and missing tests, then returns a Vibe Score from 0 to 100.

Beacon is an open-source endpoint telemetry layer for local AI agents. It captures supported activity from tools like Claude Code, Codex CLI, Gemini CLI, OpenCode, Factory Droid, Claude Cowork, and Cursor, then normalizes events for local inspection or forwarding to SIEM pipelines.

Open-source AI end-to-end testing for web and mobile apps. It lets teams write tests in natural language, runs them in an agentic runtime, and stores execution memory to improve future runs.

Open-source, local-first AI web testing app that lets you write test steps in plain English and run them in a real browser on your machine.

SwarmWright is a self-hosted multi-agent AI orchestration platform for designing, running, and inspecting swarms of agents from markdown and config. The page highlights Docker-based setup, topology-enforced agent graphs, human approval steps, local storage, and detailed audit logs.

Zero is an experimental programming language for agents, with a compiler, standard library, docs, examples, and CLI commands for checking, running, building, and inspecting programs.

A Node CLI for running multiple isolated Claude Code accounts on one machine, with separate credentials, history, settings, and profile switching via a single cc command.

Hopper is an agentic development environment for mainframes and z/OS. It uses AI agents through Model Context Protocol to navigate TN3270, inspect datasets, write JCL, debug jobs, and work inside mainframe systems from a modern interface.

Local-first code intelligence for Claude Code that adds structural graph search, semantic memory, cross-project links, MCP integration, and automated hooks for coding workflows.

Tessera is a workspace for organizing AI coding sessions across projects, collections, tabs, panes, and Git worktrees. It supports Claude Code, Codex, and OpenCode, with demos for Kanban-style task flow, worktree tracking, tool logs, diffs, and cross-platform runtimes.

Open-source visual workspace for building with coding agents like Codex and Claude Code, with session management, task tracking, diffs, and custom editors.

Adola offers Rose 1, a prompt compression API that trims noisy context before LLM calls while aiming to preserve answer quality. The page shows quickstart code, benchmark claims, and use cases for agent traces, RAG retrieval, prompt gateways, and support copilots.

Hivemind is a shared brain for coding agents that captures traces, turns repeated patterns into reusable skills, and syncs them across a team. The repo shows installation commands, supported assistants, commands, and troubleshooting notes.

SLayer is an open-source semantic layer for AI agents and humans that sits between a database and downstream tools. It can auto-create data models from schema, compile natural-language-style queries into SQL, and be used through MCP, REST, CLI, or Python.

Kon is a minimal terminal coding agent with a tiny default prompt, a built-in toolset, and configurable model/provider support. The repo includes install steps, CLI usage, example commands, and configuration details.

Self-hostable MCP server that collects memories from coding agents and regenerates shared AGENTS.md-style context for the next session.