Lists (2)
Stars
A curated paper list on On-Policy Distillation (OPD) & On-Policy Self-Distillation (OPSD) for LLMs — student rollouts + teacher feedback, covering white-box/black-box methods, OPD-RL hybrids, agent…
Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
Official code for "Breaking the Ceiling in On-Policy Distillation via Multi-Agent Debate" (arXiv:2605.01347).
slime is an LLM post-training framework for RL Scaling.
Post-training with Tinker
Modern CUDA Learn Notes with PyTorch for Beginners, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings
AgentCgroup: Understanding and Controlling OS Resources of AI Agents
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.
SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]
The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!
A lightweight, powerful framework for multi-agent workflows
Make Any Website into CLI & Use your logged-in browser by AI agent.
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…
A research framework for studying how multi-agent LLM teams complete software tasks given different team structures and sizes.
A powerful GUI app and Toolkit for Claude Code - Create custom agents, manage interactive Claude Code sessions, run secure background agents, and more.
ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works…
AI agents running research on single-GPU nanochat training automatically
Turn GitHub Copilot into OpenAI/Anthropic API compatible server. Usable with Claude Code Or Codex Or Opencode!
Sub2API 一站式开源中转服务，让 Claude、Openai 、Gemini、Grok订阅统一接入，支持拼车共享，更高效分摊成本，原生工具无缝使用。
CRS-自建Claude Code镜像，一站式开源中转服务，让 Claude、OpenAI、Gemini、Droid 订阅统一接入，支持拼车共享，更高效分摊成本，原生工具无缝使用。
nanoRLHF: from-scratch journey into how LLMs and RLHF really work.