awlevin/typesafe-computer-use
Computer use for about $0.0002 a step: OCR the screen, classify the next action with TypeSafe, click. macOS.
Language:Python
Total stars: 665
#python
#aiagents, #automation, #computeruse, #macos, #ocr, #typesafe
Computer use for about $0.0002 a step: OCR the screen, classify the next action with TypeSafe, click. macOS.
Language:Python
Total stars: 665
#python
#aiagents, #automation, #computeruse, #macos, #ocr, #typesafe
mizorewww/laya-mlx
Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.
Language:Python
Total stars: 2574
#python
#applesilicon, #decisionmodel, #inference, #laya, #localai, #machinelearning, #mlx, #modernbert, #systemone, #typeddecisions
Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.
Language:Python
Total stars: 2574
#python
#applesilicon, #decisionmodel, #inference, #laya, #localai, #machinelearning, #mlx, #modernbert, #systemone, #typeddecisions
Claude-Reverser/IDA-instances-MCP
Custom build of ida-pro-mcp - stability-hardened MCP server for hosting headless IDA Pro instances
Language:Python
Total stars: 456
#python
Custom build of ida-pro-mcp - stability-hardened MCP server for hosting headless IDA Pro instances
Language:Python
Total stars: 456
#python
jaredpalmer/kev
tiny Jev-like family of decision models built on top of Qwen3.5 you can train and run on your own
Language:Python
Total stars: 2315
#python
#decisionmodel, #jev, #qwen3
tiny Jev-like family of decision models built on top of Qwen3.5 you can train and run on your own
Language:Python
Total stars: 2315
#python
#decisionmodel, #jev, #qwen3
TheoLeeCJ/SemIf
Semantic ifs from open models, on a 3090 at home. Independent; not affiliated with Jev or TypeSafe.
Language:Python
Total stars: 3170
#python
Semantic ifs from open models, on a 3090 at home. Independent; not affiliated with Jev or TypeSafe.
Language:Python
Total stars: 3170
#python
bespokelabsai/nimble
Local typed decisions, contrastive data curation, and model evaluation.
Language:Python
Total stars: 1475
#python
Local typed decisions, contrastive data curation, and model evaluation.
Language:Python
Total stars: 1475
#python
whitecircle/halo
Halo is an open-source framework built by White Circle for training large language and multimodal models
Language:Python
Total stars: 409
#python
#agent, #asyncrl, #distributedtraining, #finetuning, #grpo, #largelanguagemodels, #llm, #lora, #modelparallelism, #moe, #multimodal, #peft, #posttraining, #pytorch, #qlora, #quantization, #reinforcementlearning, #rlhf, #transformers, #vllm
Halo is an open-source framework built by White Circle for training large language and multimodal models
Language:Python
Total stars: 409
#python
#agent, #asyncrl, #distributedtraining, #finetuning, #grpo, #largelanguagemodels, #llm, #lora, #modelparallelism, #moe, #multimodal, #peft, #posttraining, #pytorch, #qlora, #quantization, #reinforcementlearning, #rlhf, #transformers, #vllm
xiao18825501901-rgb/coursemate-ai
CourseMate AI — RAG course assistant and study agent
Language:Python
Total stars: 466
#python
CourseMate AI — RAG course assistant and study agent
Language:Python
Total stars: 466
#python
yibie/awesome-jev
A curated list of public projects, integrations, and discussions built on Jev — TypeSafe AI's System One model for typed decisions.
Language:Python
Total stars: 1136
#python
#awesome, #awesomelist, #jev, #llm
A curated list of public projects, integrations, and discussions built on Jev — TypeSafe AI's System One model for typed decisions.
Language:Python
Total stars: 1136
#python
#awesome, #awesomelist, #jev, #llm
mizorewww/laya-coreml
Local Laya typed decisions on Apple Core ML and Neural Engine. Validated ports, ~5 ms short decisions on M3 Max, reproducible speed and energy benchmarks.
Language:Python
Total stars: 1143
#python
#appleneuralengine, #applesilicon, #coreml, #decisionmodel, #laya, #localai, #modernbert, #ondeviceai, #typeddecisions
Local Laya typed decisions on Apple Core ML and Neural Engine. Validated ports, ~5 ms short decisions on M3 Max, reproducible speed and energy benchmarks.
Language:Python
Total stars: 1143
#python
#appleneuralengine, #applesilicon, #coreml, #decisionmodel, #laya, #localai, #modernbert, #ondeviceai, #typeddecisions