Repo for vLLM Hook, an vLLM plug-in for programming internal states of models deployed on vLLM

Find, benchmark and install in CLI 200+ FREE coding LLM models across 20+ providers in real time

UAVVaste: COCO-like dataset and effective waste detection in aerial images

Mount Hugging Face Buckets and repos as local filesystems. No download, no copy, no waiting.

Detect Anything in Real Time: Real-time object detection using frontier object detection models.

Nahw is a comprehensive benchmark for evaluating Arabic grammar understanding in large language models. It includes multiple-choice grammar questions (Nahw-MCQ), annotated passages for grammatical …

The Prometheus monitoring system and time series database.

Academic Research Skills for Claude Code: research → write → review → revise → finalize

Tadabur is a large-scale, high-diversity Qur'anic speech dataset designed to advance Arabic speech research.

Self-referential self-improving agents that can optimize for any computable task

python parser for human readable dates

[Up-To-Date] Awesome Agent Memory Paper Resource

Generalist and Lightweight Model for Named Entity Recognition (Extract any entity types from texts)

Agent Skills to empower developers building AI applications with Weaviate.

Language, engine, and tooling for expressing, testing, and evaluating composable language rules on input strings.

A fast, helpful, and open-source document parser

Virtual whiteboard for sketching hand-drawn like diagrams

🦞 Just talk to your agent — it learns and EVOLVES 🧬.

"ClawTeam: Agent Swarm Intelligence" (One Command → Full Automation)

[ICLR 2024 & NeurIPS 2023 WS] An Evaluator LM that is open-source, offers reproducible evaluation, and inexpensive to use. Specifically designed for fine-grained evaluation on a customized score ru…

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Qianfan-VL: Domain-Enhanced Universal Vision-Language Models

Agent harness built with LangChain and LangGraph. Equipped with a planning tool, a filesystem backend, and the ability to spawn subagents - well-equipped to handle complex agentic tasks.

AI-powered citation search & paper review for Overleaf — Chrome extension. Think Google Scholar but inside Overleaf. Also works with OpenAI Prism.

Fully local meeting transcription with speaker diarization, AI summaries, and PDF output

OpenClaw-RL: Train any agent simply by talking

CLI for Recursive Language Models (arXiv:2512.24601)