A large language model (LLM) is a type of machine learning model designed for understanding, generating, and interacting with human language. These models are trained on extensive datasets containing text from books, articles, websites, and other sources to learn patterns, context, and semantics in language. LLMs are widely used in applications like chatbots, code generation, translation, summarization, and more. They are often built using transformer architectures and are central to the field of generative AI.
🤘 TT-NN operator library, and TT-Metalium low level kernel programming model.
Spine — governed, provenance-grounded autonomous software delivery (installs as agent-orchestrator).
AI agent template: pick a pattern, edit the prompt, ship. Free unit tests, real evals, built-in cost guardrails.
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
Self-hosted control plane for fleets of small, context-optimized agents: graphs, workspaces, channels, triggers, MCP.
Paper-first Solana memecoin trading bot for pump.fun: rug screening, graduation plays, an AI persona desk scored on every call, trained models and a research lab that tests every idea on recorded data, an edge check that says real or luck, and a live trading-room dashboard. Plus a DexScreener momentum bot via Jupiter.
📚 A zero-dependency, git-backed micro-lesson library for AI Agents to asynchronously share and search verified debugging experience. | https://misakanet.org
海外テックニュースを自動収集し、AIで翻訳・要約・投資文脈を分析するリサーチダッシュボード
The backend agents build with - Multimodal database, orchestration, and serving in one file
Production-oriented LangGraph multi-agent customer service reference implementation with hybrid RAG, durable Celery execution, HITL approval governance, and reproducible evaluation.
The agent that grows with you
Your work, already underway. A personal AI assistant for your job: mail, chats and tickets become tasks, the agents you already use (Claude Code, Codex, Gemini) do the work, and nothing goes out until you approve. Open source, runs on your machine.
A cognition kernel that wraps a frozen LLM in a persistent identity + trust + governance loop — testing whether capability comes from structure, not weights. Research-stage; honest about what's real vs mocked.
A Claude Code workflow harness for solo founders and small teams — keeps your coding agent on the rails with plan-gated changes, cross-session memory, per-step proof, and seatbelt hooks
An assistant built to be trusted by proof, not by sounding right: a small language model trained from random weights on one machine, running with nothing behind it, whose programs carry specifications checked by seven provers (Dafny, Verus, SPARK, Frama-C, Lean 4, Rocq, F*), each also refuting a sabotaged twin. It learns only from what was proved.
A scientific-method runtime for AI agents: hypotheses, experiments, evidence, provenance, reproducibility, and auditable conclusions.
Generate complete, coordinated AI agent teams for any project from a single description file.