Lance Martin

auto-evaluator. Evaluation tool for LLM QA chains

lex-gpt. Jupyter Notebook

llmstxt_architect. Python

generative_agents. Generative Agents: Interactive Simulacra of Human Behavior

besties-gpt. Jupyter Notebook

doc-gpt. Python

karpathy-gpt. Jupyter Notebook

vibe-code-benchmark. Python

paper-distiller. Python

govt-copilot. Jupyter Notebook

doc-gpt-chatbot. Python

langgraph-rules.

open_deep_research_training. Training setup for Langchain's Open Deep Research

rlancemartin.github.io. HTML

deepagents. Python

claude-prompt-lab. Jupyter Notebook

langchain. ⚡ Building applications with LLMs through composability ⚡

llama-recipes. Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.

gpt4-pdf-chatbot-langchain. GPT4 & LangChain Chatbot for large PDF docs

rag-agent-langgraph. Testing for LangGraph Cloud

anthropic-cookbook. A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.

ferris-gpt. Jupyter Notebook

ART. Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more!

Auto-GPT. An experimental open-source attempt to make GPT-4 fully autonomous.

OpenDevin. 🐚 OpenDevin: Code Less, Make More