search
Benchmark
Trends
- 1Self-play RL bot defeats strong human at StarCraft Brood War●Starcraft Brood War self-play RL bot beats strong human [video]
A reinforcement learning bot trained through self-play has beaten a strong human player at StarCraft: Brood War, one of the most mechanically demanding competitive strategy games. The result is drawing attention among AI researchers and gamers, as Brood War's complexity and action-per-minute requirements have long made it a tougher benchmark than more modern strategy titles.
Repos
- vectorize-io/hindsight Hindsight: Agent Memory That Learns
- JoasASantos/Offensive-Security-AI-Models Uncensored AI models or those fine-tuned for cybersecurity tasks.
- deepopen-com/deepopen 非自回归System 1决策引擎，专为结构化类型决策场景设计 DeepOpen Multilingual, non-autoregressive System 1 decision engine.
- google-research/rrsi
- jaredpalmer/kev Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own
- Contrastive-LM/CLM
- ethanplusai/astra-flash-orchestrator Astra plans and reviews; DeepSeek Flash builds. A native Codex workflow with phased tasks, verification, safe installati
- bespokelabsai/nimble Local typed decisions, contrastive data curation, and model evaluation.
- TianyuCodings/NanoJev A nano replica of Jev: parallel decisions, dynamic candidates, and an end-to-end training pipeline.
- mizorewww/laya-mlx Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or c
- heyjunpenn/awesome-jev A verified, community-maintained catalog of 944 open-source projects built with Jev.
- General-Instinct/InstinctFlash High-Performance Serving Runtime for Robotics Models
- Rizzo-AI-Academy/rizzo-flow The open, local take on Jev: typed decisions from an LLM, without generating a single token
- Mapika/decider A family of System One-style models fine-tuned from Qwen3.5, designed for one-pass typed decisions with calibrated proba
- awlevin/typesafe-computer-use Computer use for about $0.0002 a step: OCR the screen, classify the next action with TypeSafe, click. macOS.
- mizorewww/laya-coreml Local Laya typed decisions on Apple Core ML and Neural Engine. Validated ports, ~5 ms short decisions on M3 Max, reprodu
- nestrilabs/virtio-nvgpu [Experimental] A virtio device for near-native NVIDIA GPU access in KVM virtual machines.
- IterateAI/lifeboat-releases Lifeboat — downloads for macOS, Windows and Linux, plus Docker and Kubernetes install instructions. Run language models
- rudratoshs/buried-injections 🛡️ Regex catches 0%, Meta's Prompt Guard 2 catches 1% of 629 realistic AgentDojo injection attacks when they'r
- kvmem/kvmem-llama.cpp