Popular repositories Loading

1. bitnet-mlx-engine bitnet-mlx-engine Public

   BitNet 1-bit LLM inference on Apple Silicon: 89 tok/s with custom Metal kernel. Includes CoreML/ANE benchmarks and speculative decoding.

   Python 1

2. ccrun-benchmark ccrun-benchmark Public

   Does the language your container runtime is written in affect workload performance? We built the same runtime in Python, Go, Rust, and C, then ran 540+ benchmarks to find out.

   Python 1

3. gemma4-eval-kit gemma4-eval-kit Public

   🧪 70-test, 6-model AI benchmark: Gemma 4 vs Gemini Pro vs Flash vs Qwen. 420 verified runs across 13 categories. All prompts, rubrics, runner code & raw results included. Code executed, constraints…

   Python

4. tapish-ciro tapish-ciro Public

   Tapish — Agentic Crisis Intelligence & Response Orchestrator for Lahore. 6 Gemini-powered ADK agents, 20 function tools, real-time crisis coordination. Built with Google Antigravity for AI Seekho H…

   Python

5. muhafiz-sre-final muhafiz-sre-final Public

   MuhafizSRE: Operator-Governed AI Incident Command Room — 5-agent SRE council with HMAC approval contracts, hash-chained audit ledger, and sandbox execution. Kaggle AI Agents Capstone, Track 2.

   Python

6. concordia-dao-council concordia-dao-council Public

   Concordia DAO Council — policy-governed Casper DAO execution proof

   Python