Stars
💫 Toolkit to help you get started with Spec-Driven Development
All materials needed to follow along with the Spec-Driven Development with Coding Agents course, built in partnership with JetBrains
Hindsight: Agent Memory That Learns
Run agents like Hermes, LangChain Deep Agents, and OpenClaw more securely inside NVIDIA OpenShell with managed inference
Train the smallest LM you can that fits in 16MB. Best model wins!
AI agents running research on single-GPU nanochat training automatically
Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. Includes AI agent skills.
Archived: official Ouroboros moved to https://github.com/razzant/ouroboros
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23
Just a set of claude/codex skills to be 10x Deevs' engineer
[DL4C @ ICLR 2025] A Benchmark for Automated Environment Setup
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
(ACL2025 Findings) Official code for the paper "STeCa: Step-level Trajectory Calibration for LLM Agent Learning"
First-of-its-kind AI benchmark for evaluating the protection capabilities of large language model (LLM) guard systems (guardrails and safeguards)
Readymade evaluators for agent trajectories
The local UI to run and train text and diffusion models, including Kimi K3, Gemma 4, Qwen3.6, DeepSeek-V4, FLUX and more.
Hammer: Robust Function-Calling for On-Device Language Models via Function Masking
xLAM: A Family of Large Action Models to Empower AI Agent Systems
A high-throughput and memory-efficient inference and serving engine for LLMs
SWE-bench: Can Language Models Resolve Real-world Github Issues?
🐙 OctoPack: Instruction Tuning Code Large Language Models
A framework for the evaluation of autoregressive code generation language models.
Retrieval and Retrieval-augmented LLMs
Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search
Language modeling and instruction tuning for Russian
[ACL 2023]: Training Trajectories of Language Models Across Scales https://arxiv.org/pdf/2212.09803.pdf