Top Picks

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.

A Claude Code plugin that lets you stash ideas during a session with /stash commands, then pop them back later without losing context.

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.

Open-source CLI and agent infrastructure for handling paid API requests. It detects 402 payment challenges, signs stablecoin payments with a local wallet, supports MCP, and includes a payment debugger plus catalog tooling.

Amnitex is a local, lossless memory layer for MCP-capable AI coding assistants. It installs as a CLI, exposes tools like search, recall, remember, and list keys, and is designed to work across clients such as Claude Desktop, Cursor, Cline, Continue, and Zed.

Fabrica is a Rust-based terminal coding agent with a full TUI, multi-provider model support, and built-in file and shell tools for autonomous coding tasks. It also supports ACP server mode for programmatic control by compatible clients.

A public leaderboard that ranks GitHub, GitLab, and Bitbucket repos by how friendly they are to AI coding agents such as Claude Code, Cursor, Devin, Codex, Gemini, Aider, and OpenHands.

A macOS companion overlay for Claude Code that shows an animated pet/sprite based on Claude Code activity. It includes a CLI, hook integration, a daemon, and a web-based atlas validator/renderer for Codex-pet-compatible pets.

GrimmBot is an open-source autonomous AI agent that runs in a sandboxed Docker container, with persistent memory, task scheduling, browser control, and the ability to create custom tools over time.

Open-source agile planning and orchestration layer for AI coding agents, with bidirectional sync to Claude Code, AI-generated user stories, sprint planning, and a self-hosted CLI workflow.

SPARKIT is a scientific research agent delivered through an API. It searches literature, reads PDFs, runs analyses, and returns cited Markdown reports for research workflows.

pi-hosts is a tool for the Pi coding agent that adds named SSH targets, cached host facts, guarded remote command execution, and JSONL audit logs for server work.

An open protocol for giving AI agents structured, real-time perception from external sensors and data sources. The repo includes architecture notes, quick-start install flows, and a sensor catalog concept.