Skip to content
repository radar
Agents & Orchestration

📈DeepScaler

ACTIVE BREAKOUT

rllm-org/rllm · homepage ↗

Democratizing Reinforcement Learning for LLMs

⭐ Popular: 6k stars, gaining about 18 a week

View on GitHub ↗

repo profile

vintage 2025 1 year old
language Python
license Apache-2.0

momentum

total stars 6k
stars added last week +18
commits / week 1 cooling · -71% vs prior mo
issues closed 88% ~2mo to close, median
contributors 90 (+4 in 18d)
release cadence quarterly
last activity today

durability

backing foundation-backed academic (UC Berkeley Agentica)
openness permissive
bus factor 2 concentrated
top-author share 31% 6 mo

bus factor = how many people it takes to cover more than half the commits (6 months). 1 is a solo project; higher means the work is spread across a team. top-author share is the single busiest author's slice of those commits.

since we covered it

monthly average + 236/mo (+16%/mo) · + 4k total since PR#2

why it's a big deal

  • Provides an open framework for training language agents with reinforcement learning, so researchers can move the same agent code from evaluation into training without rewriting it.
  • Ships 60+ integrated benchmarks across math, coding, QA, search, vision-language, and agentic tasks, giving teams a common baseline to test agents against.
  • Lets the same setup drive real CLI harnesses like Claude Code, Codex, and opencode, so work is not locked to a single agent framework.

under the hood

  • Written mostly in Python (72 percent of the codebase) with Jupyter Notebooks (26 percent), following a pipeline of run agent, collect traces, compute rewards, update model.
  • Splits into a Workflow Engine for parallel rollouts, a Model Gateway that captures token IDs and logprobs, a transform pipeline for trajectory grouping, and a pluggable training backend.
  • Supports GRPO, REINFORCE, RLOO, SFT, and on-policy distillation, with training backends (verl, tinker, fireworks) and sandboxes (Docker, Daytona, Modal, local) switchable by flag.

Radar summary, generated from the project's public sources

star history

PR#2 · 2k6k now Jan 2025Aug 2026
  1. PR#2 2k 2025-02-19
  2. now 6k + 4k since first covered

curve is sampled from GitHub's star history, plus our own daily readings since we covered it; the dashed stretch is before we first covered it, the solid line since. figures at coverage are the numbers we printed then (approx.), current count is live.

understory

Quietly building: more output than attention, for now.

+14 understory score output 61 · clout 47
Aug 2025 Jul 2026
  • output, commits & releases
  • clout, star velocity

output = commits & releases; clout = star velocity, both 0 to 100 monthly indices; the gap where output runs above clout is the understory. The understory →

covered in

  • PR#2 2025-02-19 below the radar

    Democratizing Reinforcement Learning for LLMs

similar projects

compare these →
  • ☁️ skypilot

    1.8× the stars

    The AI Compute Platform for frontier teams. SkyPilot turns fragmented AI compute into one AI supercomputer, so frontier AI teams build custom intelligence faster.

    10k ACTIVE
  • 📖 ai-agent-book

    6.6× the stars

    AI Agent PDF

    38k ACTIVE
  • 🦌 DeerFlow

    14× the stars

    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 tasks that could take minutes to hours.

    80k ACTIVE

comments

Sign in with GitHub to add your blip on DeepScaler.

loading comments…