A curated list of autonomous improvement loops, research agents, and autoresearch-style systems inspired by Karpathy's autoresearch.
Repository Index
76,356 visible repositories in the index
49–72 of 111 · Most stars
Structured deep research skill for Claude Code/Open Code/Codex with human-in-the-loop control
- claude-code
- claude-code-skills
- deep-research-agent
- llm-agent
verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"
- llm-agents
- llm-training
- reinforcement-learning
- large-language-models
AssetOpsBench - Industry 4.0: A unified benchmark and framework for building, orchestrating, and evaluating domain-specific AI agents for Industry 4.0 asset operations and maintenance, with 460+ scenarios, 5 specialist agents (IoT, FMSR, TSFM, Work Order,...), and multi-agent orchestration blueprints (MetaAgent, AgentHive) over MCP.
- llm-agents
- model-context-protocol
- time-series-forecasting
- condition-based-maintenance
A curated, battle-tested AI-coding toolkit: Claude Code plugins, subagent orchestration, quality gates, and ready-to-copy prompts, extracted from real production use.
A repo lists papers related to LLM based agent
- agents
- large-language-models
- llm-agent
- paper-list
No-code multi-agent framework to build LLM Agents, workflows and applications with your data
- ai
- generative-ai
- llm-chain
- llm-framework
Nix packages for AI coding agents and development tools. Automatically updated daily.
Python trading framework with AI agents that actually place the trade. Backtest, paper and live trade on 12 brokers: stocks, options, futures, forex, crypto and prediction markets.
One-stop shop for building AI-powered products and businesses with Stripe.
- llm
- llm-agents
- python
- typescript
[EMNLP2026] "VideoAgent: All-in-One Agentic Framework for Video Understanding and Editing, and Remaking"
- agents
- llm-agents
- video-editing
- video-understanding
An index of the LangChain + LangGraph ecosystem: concepts, projects, tools, templates, and guides for LLM & multi-agent apps.
[ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling
- function-calling
- llm
- llm-agent
- llm-agents
A curated collection of AI agent research papers released in 2026, covering agent engineering, memory, evaluation, workflows, and autonomous systems.
Awesome List for Agentic RL
- agent
- agentic-ai
- agentic-coding
- agentic-workflow
Ship your code, on autopilot. An open source agent that lives on your machines 24/7 and keeps your apps running. 🦀
- agent
- devops
- devtool
- generative-ai
A股 AI 投研
Open source previs software in the browser: block a scene, pose characters, author camera moves and cuts, then take the same shots to an AI video model.
The open-source cybersecurity harness. Includes a web interface for code analysis, pentesting, vulnerability research, reverse engineering, verification, and fixing + CLI and MCP for agents.
- llm-agents
- security-research
- security-tools
- application-security
An auto-evolution framework that optimizes anything — your 7×24 team of algorithm engineers.
- evolutionary-algorithms
- rsi-ai
- self-improvement
- llm-agent
TranslatedEvoOntology: A Self-Evolving Ontology Layer for Data Agents ⚙️ The EvoOntology plugin builds and evolves an ontology layer for Claude Code/Codex
RSI-Anything: Unlocking Recursive Self-Improvement with World Models
- jepa
- llm-agents
- recursive-self-improvement
- world-models
When Claude Code hits its usage limit, Codex picks the task up from the same memory. Sno Station puts Codex, Claude Code, Cursor, Hermes Agent and OpenClaw on one squad: they hand work to each other and review each other's code. Open source, runs on your computer.
The foundation layer for agentic intelligence.