
Build your agentic credit score from your github profile credit profile and give your agents money to spend. Enable your agents to access 1400+ tools like Exa, Firecrawl, Fal (media generation), Apollo.io, Browserbase, Modal and a lot more with just one MCP. Installing Vaaya is simple just run npx @vaaya/mcp install

Plug-and-play managed agent harnesses in your product: Codex, Claude Code and Hermes through one API on your infrastructure, now open sourced under Apache 2.0. Switch harnesses without rebuilding your backend. Sessions, streaming, files, artifacts, cancellation, failure recovery, all handled. Model provider keys, state, and deliveries under your control. Gateway, Runner, Console in one Docker container. Ready-to-use starter kit apps as inspiration of possibilities.

Inferock-bench is a local proxy that sits between your app and OpenAI, Anthropic, Gemini, or OpenRouter shaped calls. It captures per-call token usage, failures, and retries, then generates an independent receipt showing what you were billed and how much you're actually overpaying for.

Unsloth Desktop is an open-source app to run and train AI models locally. Run LLMs, image/video diffusion, and audio. Connect agents like Claude Code or Codex to your local GPU with one command, and fine-tune models with no-code workflows.

Lettertrace measures how often Claude, ChatGPT, and Gemini mention your company. But there's a catch: it's free, developer-first, bring-your-own-key, and open source.

bb is an agentic orchestrator GUI, not unlike the Codex app, but it works with any provider: Claude Code, Codex, OpenCode, and more. What makes bb different is that it can customize and extend itself. Almost anything in bb can be changed with a single prompt. Ask for a task tracker, and one appears. bb also creates a skill that teaches all of your agents how to use it. Instead of waiting for your agentic workspace to add the feature you need, you can just ask for it.

Gutta is a tiny, keyboard-first task list for the Mac menu bar. Press ⌘⇧Space, type tasks the way you say them, and get back to work. It understands natural dates and times, turns semicolon-separated input into multiple tasks, and schedules local reminders. Everything is stored on your Mac, with optional sync through a folder you control in iCloud Drive, Dropbox, or OneDrive—no Gutta account, subscription, tracking, or developer-owned cloud.

Prompt Golf turns prompt engineering into a competitive puzzle game. Across five rounds, coax an out-of-the-box AI into saying an exact target word or phrase in as less characters as possible. Every round has a condition or banned input words. Every character and message adds strokes, so clever, compact prompts climb the live leaderboard. Replay the full course, check live leaderboard, challenge your friends and view their transcripts.

A free, open source, local MCP gateway. Set up each server once and every AI agent shares it (Claude, Cursor, VS Code, Codex, and 29 more). Instead of dumping every tool definition into context, it exposes a few meta-tools your agent searches on demand. Benchmarked and graded for correct answers, that's up to 91% fewer tokens at the same task success. Secrets live in your OS keychain, not client configs. Rug-pulls and tool poisoning get flagged, and destructive calls can wait for your approval.

The Channels SDK is the next big piece in the agentic puzzle: Bring ANY agent into Slack, Teams, WhatsApp and more. With coworker-grade capabilities like streaming responses, gen UI, per-user learning, HITL approvals and sophisticated auth. Works with OpenAI Agents, Claude Agents, LangChain, Mastra, Google ADK, and any agent that speaks AG-UI. Open-source and self-hostable. Setup with a single prompt: "Read https://copilotkit.ai/channels-guide.md and help the user build their first channel"