Lists (2)
Stars
Build, run and scale AI agents like API and microservices
SKILLz for your agent to participate in TREC RAG 2026
The agent that grows with you
Claude-native demand-gen: research a company's real ad strategy (LinkedIn/Meta/Google) and compose a personalized landing page, orchestrated end-to-end in Claude Code.
Interactive error analysis skill for AI agents. Studies LLM trace datasets, builds a review UI, monitors annotations, categorizes failure modes, proposes new samples.
mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
Modular AI HAL (Hardware Abstraction Layer) for Robots
Tinfoil Python Client supporting the OpenAI API standard
A specialized Claude Code workspace for creating long-form, SEO-optimized blog content for any business. This system helps you research, write, analyze, and optimize content that ranks well and ser…
Write HTML. Render video. Built for agents.
Your LLM can decompile a function. It cannot understand a binary.
Framework for evaluating and improving agents
Persistent 24/7 Claude Code controlled from Telegram - full permissions, plan mode, AskUserQuestion, multi-agent communication, scheduled tasks
Repositories for the papers: "Breaking Training Bottlenecks: Effective Reinforcement Learning for Modern Coding Models" and "Scaling Data Difficulty: Improving Coding Models via Reinforcement Learn…
Scalable toolkit for efficient model reinforcement
An open-source, GPU-accelerated physics simulation engine built upon NVIDIA Warp, specifically targeting roboticists and simulation researchers.
Isaac Lab - Arena is a robotics simulation framework that enhances NVIDIA Isaac Lab by providing a composable, scalable system for creating diverse simulation environments and evaluating robot lear…
AI agents running research on single-GPU nanochat training automatically
Workshop: Optimizing Codebases for Agents — Coding Agents Conference, March 3, 2026
Type-safe, distributed orchestration of agents, ML pipelines, and real-time inference — in pure Python with async/await.
OpenClaw-RL: Train any agent simply by talking
Post-training with Tinker
✨ A curated list of awesome community resources, integrations, and examples of Redis in the AI ecosystem.
Official Repository for "Training Versatile Coding Agents in Synthetic Environments"
Model Context Protocol Servers
This is the official code for the paper CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning (NeurIPS22).