lucidrains / metacontrollerLinks
Implementation of the MetaController proposed in "Emergent temporal abstractions in autoregressive models enable hierarchical reinforcement learning"
☆87Updated this week
Alternatives and similar repositories for metacontroller
Users that are interested in metacontroller are comparing it to the libraries listed below
Sorting:
- A multi-agent LLM system for detecting and resolving cognitive dissonance.☆272Updated 3 months ago
- The code repository of the paper: Competition and Attraction Improve Model Fusion☆168Updated 5 months ago
- Code for Bolmo: Byteifying the Next Generation of Language Models☆115Updated last month
- Official Project Page for Deep Delta Learning (https://huggingface.co/papers/2601.00417)☆320Updated this week
- Digital Red Queen: Adversarial Program Evolution in Core War with LLMs☆158Updated 2 weeks ago
- ☆137Updated 8 months ago
- Data recipes and robust infrastructure for training AI agents☆84Updated this week
- The State Of The Art, intelligence☆157Updated 5 months ago
- ☆159Updated last month
- Claude Code and Large-Context Reasoning (O'Reilly Live Learning)☆193Updated last week
- Marketplace ML experiment - training without backprop☆27Updated 4 months ago
- Scaling Coding-Agent RL to 32x H100s. **Achieving 160% improvement** on Stanford's TerminalBench☆91Updated 2 months ago
- Living memory for AI☆335Updated 3 weeks ago
- AI Agent that researches the lives of historical figures and extracts events into structured JSON timelines using LangGraph multi-agent o…☆225Updated 3 months ago
- ☆126Updated 4 months ago
- Deep research agents using MiniMax M2.1 interleaved thinking☆194Updated last month
- [ICLR'26] The official code implementation for "Cache-to-Cache: Direct Semantic Communication Between Large Language Models"☆324Updated this week
- ~950 line, minimal, extensible LLM inference engine built from scratch.☆396Updated 3 weeks ago
- The theory of mind module for the SWE agent☆68Updated 2 weeks ago
- ☆303Updated 5 months ago
- Super basic implementation (gist-like) of RLMs with REPL environments.☆574Updated 3 weeks ago
- FormulaOne: A dataset of algorithmic problems based on MSO formulas.☆23Updated 5 months ago
- ☆266Updated last week
- CLI agent to explore file system, powered by Gemini 3 Flash☆123Updated 2 weeks ago
- An OpenSource Deep Research library with reasoning☆170Updated last month
- ☆107Updated 2 months ago
- Anemoi: A Semi-Centralized Multi-agent Systems Based on Agent-to-Agent Communication MCP server from Coral Protocol☆373Updated 5 months ago
- DSPy module for OpenAI Codex SDK - signature-driven agentic workflows☆151Updated last month
- Agent0 Series: Self-Evolving Agents from Zero Data☆1,006Updated last month
- Building blocks for agents in C++☆134Updated last week