Menlo Research
@menloresearch
AI is the new electricity. Community: https://discord.gg/Exe46xPMbK
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/
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 @menloresearch! looking forward to the paper and building stuff with it :)
Recipe to post-train Qwen3 1.7B into a DeepResearch model What does it mean for something small to think deeply? Meet Lucy, a post‑trained Qwen3‑1.7B as a DeepResearch model based on @willccbb's verifiers. Primary Rule-based Rewards: - Answer correctness We check whether the…
Recipe to post-train Qwen3 1.7B into a DeepResearch model What does it mean for something small to think deeply? Meet Lucy, a post‑trained Qwen3‑1.7B as a DeepResearch model based on @willccbb's verifiers. Primary Rule-based Rewards: - Answer correctness We check whether the…
Introducing Lucy: 1.7B model that Google for you It's an agentic‑search model that can even run on your phone. - Agentic search on tap - Lucy calls tools (<think></think>‑aware) - Fits in your pocket - runs on CPU or mobile Under the hood: - Built on @Alibaba_Qwen's Qwen3‑1.7B…
Jan v0.6.5 is out: SmolLM3-3B now run locally Highlights 💫 - Support for @huggingface's SmolLM3-3B - Fully responsive design across all screen sizes - New layout for Model Providers Update your Jan or download the latest.
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 🚀
Jan should be wherever you are. Jan Mobile is on our roadmap.
In the future is there any chance to get it on Android?
Jan answers stuff like "What happened to Grok yesterday?" by actually checking the web.
Jan is an open source alternative to ChatGPT that runs 100% offline on your computer
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 @jandotai with local transformers and hot-swappable models. There is preliminary tool call support as well!
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.
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.
Isn't this cool? Jan-nano knows me so well, heck, it knows about me more than myself 🤣. Try Jan-beta with SequentialThinking! at @menloresearch
🔴 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!
Just saw Menlo/Jan-nano trending on the Hugging Face landing page, Amazing work, @huggingface @jandotai @menloresearch
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.