Eclipse Linux Alpha - Void-based with custom init
End-to-end typing across client-server beats LangChain's loose contracts.

End-to-end TypeScript typing for agents when Vercel AI SDK already handles this well.
TypeScript developers building AI applications
Vercel AI SDK · LangChain · LangGraph
Most setups I tried didn’t handle end-to-end typing well, didn’t fit cleanly into an existing app, or made it hard to reuse behavior across agents. This tries to keep things consistent across client and server, make plugins easy to share, and support stateful, resumable runs without a lot of glue code.
Website: https://better-agent.com GitHub: https://github.com/better-agent/better-agent
End-to-end typing across client-server beats LangChain's loose contracts.
The plugin-proxy split is smart: credentials live in a backend (Keychain/1Password/Vault/etc.) and a separate proxy injects auth headers over a UDS so the agent process never handles raw keys. It autosurveys plugin configs and channels to migrate plaintext secrets and even ships a Docker image and CLI for local setups — very practical for anyone already on OpenClaw, though it’s narrowly focused and adds an extra trusted component that deserves an audit.
Yet another DI library when Awilix and Inversify already exist.
Production-focused agent lib, but LangChain and CrewAI already own this space.
Type-safe SDK generation catches invalid jobs at compile time before n8n does.
Brings better-auth's plugin DX to Go without framework lock-in.