PyTorch-native post-training at scale

AgentENV (AENV) is a distributed platform for running agent environments at scale.

[MLsys2026]: RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.

[AAAI26]: DS SERVE: The Largest Open Vector Store over Pretain Data; A Framework for Efficient and Scalable Neural Retrieval

Optimized Agentic and LLM Bulk Processing Over Your Data

slime is an LLM post-training framework for RL Scaling.

[ICLR 2026] The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution

Talk to one agent. Ship with a crew.

😼 优雅地使用基于 clash/mihomo 的代理环境

SearXNG is a free internet metasearch engine which aggregates results from various search services and databases. Users are neither tracked nor profiled.

Building and Scaling RL environments in the age of LLMs

Scaling the Horizon, Not the Parameters

Instant, Concurrent, Secure & Lightweight Sandbox for AI Agents.

A benchmark for general-purpose terminal-use agents.

Scalable RL for Any Agent and Sandbox.

Low-level unprivileged sandboxing tool used by Flatpak and similar projects

to support rl training with any search harness

Qwen3-8B trained with pure RL, reaching 36+ BrowseComp Plus token-F1 in 250 steps.

Evals Harness for $OneMillion-Bench

Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…

SearchAgent-Zero: A Scalable Multi-Turn Search Agent RL Framework

🥑 ArangoDB is a native multi-model database with flexible data models for documents, graphs, and key-values. Build high performance applications using a convenient SQL-like query language or JavaSc…

A distributed, fast open-source graph database featuring horizontal scalability and high availability

Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.

Xetrieval: Mechanistically Explaining Dense Retrieval