mini-verl
verl for a single consumer GPU. PPO, GRPO and on-policy distillation on NVIDIA GPUs.
HYSEN LABS DIRECTORY
Language tag · curated repositories and deep analysis.
verl for a single consumer GPU. PPO, GRPO and on-policy distillation on NVIDIA GPUs.
DeepHyper: A Python Package for Massively Parallel Hyperparameter Optimization in Machine Learning
Continue-thinking middleware for Codex / OpenAI Responses-compatible APIs.
Build personal agents and enterprise AI workforces that plan, delegate, use tools, and deliver real work — without brittle workflows.
A modern, interlingual wordnet interface for Python
Gendangzou: a traceable A-share sector research skill for AI agents, connecting policy, authoritative media, market funds, companies, and ETFs, with real-time queries, research orchestration, and support for secondary application development.
Prosodic: a metrical-phonological parser, written in Python. For English and Finnish, with flexible language support.
Handwritten Text Synthesis and Recognition
Asynchronous Distributed Hyperparameter Optimization.
Turn natural language into structured data (supports Chinese, with N custom models covering different scenarios and tasks).
The Naomi Project is an open source, technology agnostic platform for developing always-on, voice-controlled applications!
Free email for AI agents. No signup, no human needed. Install → provision → send and receive. Ed25519 keypair auth.
[MobiSys 2026] A large-scale, multimodal dataset and benchmark for Human Action Recognition, Understanding and Reasoning
Run Claude Code against any AI provider. DeepSeek, Groq, Ollama, OpenRouter — your call.
Record and Replay AI Agent Trajectories.
Evidence-first infrastructure for reproducible, isolated executable evaluation and online rewards.
The spend meter, cost/margin, & budget gate for AI voice agents. Meters STT + TTS + LLM + telephony per call, out of the box (Pipecat, LiveKit — Python & TypeScript). Hard-stops the next turn before it crosses your ceiling. Local, no account, no telemetry. Built by Floe.
Local-first CLI for agent skills, browser automation, knowledge bases, external CLIs, and terminal AI chat.
Browser teleoperation data for embodied AI — elizaOS-ready episodes, trajectory_db converter, onchain provenance. The fuel station for agent robot stacks.
Open-source memory runtime for AI agents — reproducible, provenance-tagged context bundles instead of query-time retrieval. Apache-2.0, self-hosted on Postgres + pgvector, Python + TypeScript SDKs.