Menlo Research (@menloresearch) 's Twitter Profile
Menlo Research

@menloresearch

Menlo is an open R&D lab building the brain for robots.

Building AI in the open:
๐Ÿ“ Ichigo, AlphaMaze, PoseLess and more.
๐Ÿ‘‹ @jandotai

ID: 1795929339269443586

linkhttps://menlo.ai/ calendar_today29-05-2024 21:25:26

238 Tweet

1,1K Followers

324 Following

๐Ÿ‘‹ Jan (@jandotai) 's Twitter Profile Photo

Jan v0.6.0 is here: It's a whole new vibe! Jan's been redesigned to be faster, cleaner, and easier to use. It also lays the groundwork for upcoming tool use. You can now create assistants with custom instructions and settings. Update your Jan or download the latest.

Jan v0.6.0 is here: It's a whole new vibe!

Jan's been redesigned to be faster, cleaner, and easier to use. It also lays the groundwork for upcoming tool use.

You can now create assistants with custom instructions and settings.

Update your Jan or download the latest.
๐Ÿ‘‹ Jan (@jandotai) 's Twitter Profile Photo

๐Ÿ”ด Community Call: Jan's new agentic model & MCP capabilities, refreshed architecture and more. Join us for a full walkthrough and live Q&A. - Date: Tuesday, June 24 - Time: 10PM AEST / 8AM ET - RSVP here to get the event link: lu.ma/nimqd2an See you there!

๐Ÿ‘‹ Jan (@jandotai) 's Twitter Profile Photo

Jan v0.6.2 is out: Experimental MCP support is now in Jan. Try it: - Settings > Experimental Features ON - Settings > MCP Servers ON Plus, CORS fixed: Jan now connects cleanly to localhost providers (e.g. Ollama :11434, LM Studio :1234). Update your Jan or download the latest.

Lysandre (@lysandrejik) 's Twitter Profile Photo

BOOOM! transformers now has a baked-in http server w/ OpenAI spec compatible API Launch it with `transformers serve` and connect your favorite apps. Here I'm running ๐Ÿ‘‹ Jan with local transformers and hot-swappable models. There is preliminary tool call support as well!

๐Ÿ‘‹ Jan (@jandotai) 's Twitter Profile Photo

Jan v0.6.4 is live: Local models no longer get stuck on "loading." This hot-fix sorts out a settings glitch that blocked some local models in v0.6.3. Update your Jan or download the latest.

Victor M (@victormustar) 's Twitter Profile Photo

what a time to be alive: a local 4B model (Jan-nano) + Web Search tool is already amazing to get the info you need with no overhead ๐Ÿš€

what a time to be alive: a local 4B model (Jan-nano) + Web Search tool is already amazing to get the info you need with no overhead ๐Ÿš€
Menlo Research (@menloresearch) 's Twitter Profile Photo

Menlo Research is hiring, come build cool stuff with us. Some open roles: - Sr Backend Engineer (Tauri) - Sr Software Engineer - Research Engineer (PyTorch) - Lead Electromechanical Systems Engineer - Mechanical Engineer - Management Associate menlo.bamboohr.com/careers/

๐Ÿ‘‹ Jan (@jandotai) 's Twitter Profile Photo

Jan v0.6.5 is out: SmolLM3-3B now run locally Highlights ๐Ÿ’ซ - Support for Hugging Face's SmolLM3-3B - Fully responsive design across all screen sizes - New layout for Model Providers Update your Jan or download the latest.

Menlo Research (@menloresearch) 's Twitter Profile Photo

Introducing Lucy: 1.7B model that Google for you It's an agenticโ€‘search model that can even run on your phone. - Agentic search on tap - Lucy calls tools (<think></think>โ€‘aware) - Fits in your pocket - runs on CPU or mobile Under the hood: - Built on Qwen's Qwen3โ€‘1.7B

Casper Hansen (@casper_hansen_) 's Twitter Profile Photo

Recipe to post-train Qwen3 1.7B into a DeepResearch model What does it mean for something small to think deeply? Meet Lucy, a postโ€‘trained Qwen3โ€‘1.7B as a DeepResearch model based on will brown's verifiers. Primary Rule-based Rewards: - Answer correctness We check whether the

Tetraslam (@tetraslam) 's Twitter Profile Photo

this is really cool, i've been trying it out for the past couple hours and it's ridiculously agentic and intelligent for a 1.7b model congrats Menlo Research! looking forward to the paper and building stuff with it :)