Saved you the search.

YOUR AGENT.
A FEW EXTRAS.

The five projects from the Reel, all in one place.
Find what you need. Head straight to the source.

Meet the tools ↓

Model routing

FreeLLMAPI

Connect free-tier model providers through one OpenAI-compatible API. It routes requests between the providers you configure and switches when one hits a limit.

Useful for trying different models without wiring up every provider separately.

Bring your own provider keys. Free-tier quotas still apply; the project is intended for personal experimentation.

Open GitHub : FreeLLMAPI

tashfeenahmed/freellmapi

Security testing

Strix

AI agents investigate your application for security vulnerabilities, validate findings and provide remediation guidance. It can work with code, web apps and APIs.

Useful for checking your own app before shipping a change.

Local runs require Docker and an LLM provider key. Model usage may cost money.

Open GitHub : Strix

usestrix/strix

Session memory

Claude Mem

Captures observations from your agent’s work, summarizes them and brings relevant context into later sessions. Project history becomes something the agent can search.

Useful when you keep explaining the same decisions in a new chat.

Memory processing depends on your chosen provider or plan. See the README for local and hosted options.

Open GitHub : Claude Mem

thedotmack/claude-mem

Web research

Agent Reach

Gives command-line agents tools to read and search sources such as websites, YouTube, GitHub and social platforms. Access is configured per platform.

Useful for bringing articles, video transcripts and discussions into your workflow.

Some sources need a signed-in browser, cookies or additional setup. Availability varies by platform.

Open GitHub : Agent Reach

Panniantong/Agent-Reach

Project setup

Claude Code Setup

An official Anthropic plugin that reads your codebase and recommends relevant hooks, skills, MCP servers, subagents and slash commands.

Useful when you’re unsure which automations your project actually needs.

Its recommendation skill is read-only: it suggests a setup without changing your files.

Open GitHub : Claude Code Setup

anthropics/claude-plugins-official