Ramanujan – Multi-Model Agent for Research in Computational Maths

What it does

Ramanujan is a terminal based multi model agentic workbench for research in computational mathematics. It is a free tool to help with research in maths. You can chat normally and when you want to dig deeper it structures your problem, surveys the literature, runs parallel subagents and brings back a consolidated report. Everything runs locally and every verdict is computed deterministically. Disclaimer: This project is still under active development. If you find any bugs, issues, or have suggestions, please open an issue on the GitHub Issues page . Open ramanujan with an empty config → provider picker → API key → main-model picker → computational pool (existing or new providers, multi-pick…from github.com

• 
  SciSpace Agent 2025 · ▲521

  Only AI agent automating research with 150+ academic tools

• 
  Qwen3.6-35B-A3BApr 2026 · qwen.ai · ▲124

  The open sparse MoE model for agentic coding

• 
  Zen Agents (by Zencoder)2025 · ▲287

  Build AI agents. Share org-wide. 100+ Tools&MCP

• 
  GLM-5Feb 2026 · z.ai · ▲154

  Open-weights model for long-horizon agentic engineering

• FA
  Freeact – A Lightweight Library for Code-Action Based Agents2025 · github.com · ▲122

  Hello! We just released freeact (https://github.com/gradion-ai/freeact), a lightweight agent library that empowers language models to act as autonomous agents through executable code actions. By enabling agents to express their actions directly in code rather than through constrained formats like JSON, freeact provides a flexible and powerful approach to solving complex, open-ended problems that require dynamic solution paths. * Supports dynamic installation and utilization of Python packages at runtime * Agents learn from feedback and store successful code actions as…

• 2C
  20+ Claude Code agents coordinating on real work (open source)Feb 2026 · github.com · ▲53

  Single-agent LLMs suck at long-running complex tasks. We’ve open-sourced a multi-agent orchestrator that we’ve been using to handle long-running LLM tasks. We found that single LLM agents tend to stall, loop, or generate non-compiling code, so we built a harness for agents to coordinate over shared context while work is in progress. How it works: 1. Orchestrator agent that manages task decomposition 2. Sub-agents for parallel work 3. Subscriptions to task state and progress 4. Real-time sharing of intermediate discoveries between agents We tested this on a Putnam-level math problem, but the…

• 
  I trained a 125M model to autocomplete piano on-device▲598

  I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.

  AI · 18d ago · simedw.com

• 
  Astute▲585

  Automate your B2B brand going viral, with new media creators

  AI · 19d ago · company-app.joinastute.com

• 
  Grok Bot▲547

  AI teammates that you can give real work to

  AI · 26d ago · x.ai

• 
  Needle2: 14MB agentic LLM for phones, wearables, smart home and robots▲537

  Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…

  AI · 27d ago · cactuscompute.com

• 
  Monid▲475

  One wallet, every paid tool your agent needs

  AI · 7d ago · monid.ai

• 
  Clara AI SDR▲460

  Turn website visitors into qualified pipeline

  AI · 20d ago · clarasdr.ai

• 
  Open-Source eInk Bike Computer▲408

  OpenTrailPaper is open-source bike computer firmware for the LilyGO T5S3 4.7" E-Paper PRO. It supports offline maps, GPX routes, FIT recording and Bluetooth sensors.

  Dev tools · 2d ago · opentrailpaper.com

• 
  Nex▲350

  Claude Cowork for high-volume GTM workflows

  Life & fun · 4d ago · nex.ai

• 
  Reflexio▲282

  Behavioral learning that makes AI agents better over time

  AI · 6d ago · reflexio.ai

• OD
  Omi Desktop▲272

  Ask your Mac anything you saw or heard

  Life & fun · 4d ago · api.omi.me

• 
  Running 104GB Qwen3.8-Flash-Next on 48GB Mac with at ~12 tok/s▲239

  I built slotstream, a way to run Qwen3.8-Flash-Next 4-bit on a low-memory mac starting from 16GB, a 125B parameter model that would need 100GB+ memory/RAM, thanks to expert-offloading/ssd-streaming. Easy to install/update, and mac-native using MLX and Swift. It ships with auto-mode, which makes a good tradeoff between memory usage and speed. I'll be implementing and porting the MTP module for speculative decoding next Local models really are the future of computing!

  Life & fun · 5d ago · github.com

• 
  Atlas by World Labs▲227

  Turn text, pics, video, + 3D into camera-controlled HD video

  AI · 5d ago · worldlabs.ai