agentic-rl-lab
Reproducing and studying RL algorithms for LLM agents, including GRPO, GSPO, DAPO, OPD, Search-R1, ReTool, ALFWorld and beyond.
HYSEN LABS DIRECTORY
Language tag · curated repositories and deep analysis.
Reproducing and studying RL algorithms for LLM agents, including GRPO, GSPO, DAPO, OPD, Search-R1, ReTool, ALFWorld and beyond.
Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, and carries an auditable receipt. Local-first, works through proxy, MCP, SDK, or agent wrapper.
Various Algorithms for Short Text Mining
Open-source batch OCR workbench, a free local alternative to ABBYY FineReader. Powered by Ollama, GLM-OCR and PP-DocLayoutV3, about 0.5s per page on an RTX 4090. Three-panel editor, layout-aware, batch PDF/image processing, with Markdown/Word export.
Making ANY Software Skill-Native -- Auto-generate production-ready AI Agent Skills for Claude Code, OpenClaw, Codex, and more.
Train a tiny Transformer from scratch on your iMessage history, entirely on your Mac.
Official implementation of PhiZero: A World Model Built Around Physical Language. Code and checkpoints coming soon.
An autonomous AI scientist: a multi-agent loop over literature, experiments, self-critique and write-up, with deterministic guards against reward-hacking and hallucination.
Living project docs for coding agents: keep guides, progress logs, change maps, and handoff context updated as your repo evolves.
OpenML AutoML Benchmarking Framework
ClearML - Auto-Magical CI/CD to streamline your AI workload. Experiment Management, Data Management, Pipeline, Orchestration, Scheduling & Serving in one MLOps/LLMOps solution
A RAG project built with LangChain, FastAPI and React. The main branch is a knowledge-graph-based knowledge management platform; the base-rag branch is a ready-to-use basic RAG project for learning.
BandoriPet is an open-source Live2D and PySide6 desktop pet project supporting 50+ BanG Dream! characters and 300+ outfits, turning your desktop into a CiRCLE rehearsal room.
Official Python SDK for Deepgram.
Automated SRC vulnerability-hunting system combining FOFA asset mapping with multiple LLM workers for autonomous discovery, review and intelligence accumulation. Powered by StanleyNull.
Q-Align-style framework with lightweight LMMs, including 0.8B, 4B, and 9B checkpoints, dataset builders, caching, scoring, and CLI workflows.
Provider-neutral control plane for durable-state agent swarms: subprocess workers, leases, artifacts, memory, and deterministic stitching.
Aser is a lightweight, self-assembling AI Agent frame.
cntext is a Python library for social science text analysis, offering word frequency, sentiment, word embeddings, and semantic projection to measure constructs like attitudes and psychological states from Chinese text.
MinusPod is a self-hosted server that removes ads before you ever hit play