Top Picks

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.

Contextify stores Claude Code and Codex sessions in a private, searchable timeline, with cross-device sync and self-hosted options. It targets AI coding workflows and adds real-time session tracking, full-text search, and local Apple Intelligence summaries on supported macOS versions.

Brick is an AI model routing gateway that sends each query to the most suitable LLM based on capability and complexity. The repository includes quickstart steps, Claude Code integration, an OpenAI-compatible endpoint, and a short explanation of when to use it.

An MCP server that lets two Claude agents connect through a short-lived, end-to-end-encrypted tunnel so they can collaborate directly without a human copy-pasting between chats.

An open NDJSON specification for AI crawler ingestion and site content graphs, with examples and reference files in the repository.

An interactive CTF-style challenge where users try to break or exfiltrate data from sandboxed AI agents running in Declaw’s isolated runtime.

Loma is a self-hosted AI agents platform for teams, with a Slack interface, web dashboard, scheduled flows, webhooks, and a shared skill library. It supports open models via OpenCode and can pool existing Claude subscriptions.

Open-source tooling that generates private, point-in-time infrastructure snapshots from cloud and on-prem systems into vendor-neutral OSIRIS JSON for audits, diagrams, diffs, CMDB/IPAM/DCIM workflows, and controlled AI/MCP context.

Open-source research skill that helps Claude, Codex, and OpenClaw run a more disciplined AI research workflow, from hypothesis and literature review through baselines, leakage checks, analysis, and paper writing.

Local-first AI Chief of Staff for engineering leaders. Myna runs inside Claude Code, connects to email, Slack, and calendar through MCP, and keeps a local markdown knowledge base of projects, people, meetings, decisions, and action items.

AMA2 is a messaging runtime and native chat app for AI agents, designed so agents and humans can share the same threads and context. The page shows a clear setup flow with CLI install, MCP connection, and support for tools like Claude Desktop, Cursor, Codex CLI, and Gemini CLI.

Local-first web console for creating, configuring, monitoring, and operating Dockerized Hermes AI agents across one or more trusted machines. The repo includes setup steps, runtime requirements, screenshots, and a detailed feature list covering agent management, provider defaults, credentials, chat, VNC, terminals, bac

INFINI is an open-source portable agent loop spec and reference implementation for defining workflows in a Loopfile and running them across engines. The repo includes a CLI, mock-mode execution, trace comparison, audit checks, and a prototype UI.

A long-form technical article on building ship-ready AI agents in Rails with the Anthropic Ruby SDK, covering tool design, agent loops, MCP servers, human approval, testing, and cost control.

Standalone Playwright CLI for AI agent browser automation. It provides a real Chromium browser with structured commands, persistent sessions, token-optimized screenshots, and an eval escape hatch for custom interactions.

A macOS menu bar app that keeps a Mac awake only while AI coding agents are actively working, with hook integrations for multiple agents and support for clamshell sleep control.

Open-source authorization engine for AI agents that gates actions by confidence, policy, and human review, with prompt-injection detection and full audit logging.

A dynamic MCP server that turns JSON configs into callable API tools, with lazy tool discovery, hot reload, and a hosted console/registry.

A Rust CLI and MCP server for orchestrating multiple coding agents, fusing their answers, and resuming or routing agent sessions locally.

An open-source, self-hosted AI DevOps pipeline that ingests GitHub webhooks, generates code patches with an LLM, runs them in network-isolated Docker sandboxes, and posts validated fixes back as PR comments.

Local-first record, inspect, and replay tool for debugging AI agents. Orchid captures LLM calls and tool traffic through a proxy, exposes traces in a web UI and MCP tools, and supports offline replay for deterministic testing.

A local-first MCP server and companion CLI/TUI for giving AI agents a user-owned self model and scoped memory. It stores facets and audit events locally, supports approval-gated writes, and includes export/import for portability.

Caplets is a developer tool that wraps MCP servers into smaller capability-based surfaces for coding agents. The site explains the workflow, setup, example capabilities like OSV, GitHub, and Sourcegraph, and includes benchmark results plus docs links.

A framework-free Unix-style AI agent stack built from small shell commands. It uses bash, curl, and jq to run a REPL-like agent loop with append-only JSONL history, tool dispatch, and piping-friendly components.