Tag
Explore by tags
A 100-line LLM framework built on one graph abstraction of nodes and flows, with zero dependencies and no vendor wrappers. The tiny core composes agents, workflows, and RAG, and is small enough for a coding agent to read and extend on its own.
Full-stack AI red‑teaming platform that fingerprints AI infrastructure for known CVEs, audits MCP servers and agent skills with LLM-driven analysis, and runs cross-model jailbreak evaluations; designed for hands-on security assessment of AI deployments.
A 671B-parameter Mixture-of-Experts language model (37B activated) trained on 14.8T tokens with 128K context, FP8-first training, a Multi-Token Prediction module, and Hugging Face weights—focused on efficient MoE training and long-context use cases.
Captures, transcribes, and summarizes meetings entirely on the user's machine with real-time local transcription and speaker diarization. Privacy-first design keeps audio, transcripts, and models local; supports Ollama, Claude, Groq, OpenRouter or custom OpenAI-compatible endpoints.
Open-weight Mixture-of-Experts LLM with 671B total parameters but 37B activated per token, trained on 14.8T tokens for 2.788M H800 GPU-hours. Matches leading closed models at a fraction of typical training cost via FP8 and architectural tricks.
Simulates a trading firm using LLM agents in specialized roles — fundamentals, sentiment, news and technical analysts feed bull/bear researcher debates, then a trader and risk team decide. Works across US, global and crypto markets and 10+ LLM providers.
Lets teams build, deploy, and manage AI agents from chat, visual workflows, code, knowledge bases, tables, and more than a thousand integrations.
Runs penetration tests autonomously: a multi-agent system (researcher, developer, executor) plans attacks, writes and runs exploit code, and chains 20+ tools like nmap, metasploit and sqlmap in isolated Docker containers — for authorized testing only.
Turns camera, audio, LIDAR and web inputs into robot motion, navigation and speech by routing them through pluggable LLMs and VLMs. Hardware-agnostic Go runtime configured via JSON5, with ROS2/Zenoh middleware for real robots and simulators.
Provides end-to-end PyTorch scripts to download/prepare data, implement a transformer from scratch, train LLMs (13M→billion-scale) and generate text. Emphasizes educational clarity and single‑GPU experiments; useful for researchers or hobbyists, but large-scale training still requires substantial compute and engineering.
Wires retrievers, rerankers, and generators as standalone MCP servers orchestrated in YAML, so iterative RAG logic fits in dozens of lines instead of glue code. Adds loops, conditional branches, one-command web UIs, and shared evaluation benchmarks.
MCP-native agent framework built around the Model Context Protocol from the start, with end-to-end tested Sampling and Elicitation. Define agents and multi-step workflows in Python, run terminal-first, and swap Anthropic, Google or local models.