-
CHD Data s.r.o.
- Prague
-
03:45
(UTC -12:00) - www.chleba.org
- in/lukas-franek-82120423
Stars
🛡️ BLA (bla-agents / Blind LLM Agents) — Open-source Blue Defense MCP server & CLI protecting JS/TS, Electron ASAR, WASM, Python, Native Binaries, SQLite, GGUF/Safetensors & Android DEX against AI …
Agentic game development taken to the next level: plan, build and test across major engines with any coding agent🤖
Izometrická pixel-art mapa českého města z otevřených dat (ČÚZK, OpenStreetMap)
One backbone, many specialists. CMF is a self-describing, memory-mappable single-file format and a dependency-free runtime for quantized LLMs — zero-copy execution on CPU or GPU (Vulkan · Metal · D…
SpecPilot: Autonomous Algorithm Discovery and Systems Optimization for Speculative Decoding
Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent…
Code for Latent Sparse Attention: Towards Subquadratic Ultra-Long Context Attention
DeepInfer: High-performance, large-scale inference framework for DeepSeek models
Draw on top of code in your terminal to explain, debug and teach.
A world built upon something that should have stayed dead.
DeepSeek-V4.1-Flash on 4× NVIDIA CMP 170HX with vLLM: up to 297 tok/s for one user, up to 868 tok/s at eight, 262K context, one-command container install
The cross-harness, self-improving memory layer for AI agents. Join our community: https://discord.com/invite/zdNChS2fBu
Deterministic guardrails that don't break agents
Reverse engineer anything with agents, from app behavior down to native binaries.
Contrastive Language Models (CLMs) are a new class of System One model trained with a contrastive learning objective that connects states and actions.
GLM-5.3-Flash on 4× NVIDIA CMP 170HX with vLLM: up to 482.6 tok/s single-user, up to 943.7 tok/s at 8 users, 262K context, TP4 or PP4, one-command container install
An all-in-one, 100% local AI video, image, and music studio. Director mode plans full music videos and short films from a single prompt. Built on the WanGP pipeline. Install via Pinokio.
vLLM patches + root-cause forensics: Qwen3.8-Flash-Next with PP3, MTP, and prefix caching (fixes the vllm#54173-family state corruption)
PEASS - Privilege Escalation Awesome Scripts SUITE (with colors)
MeshAgent used along with MeshCentral to remotely manage computers. Many variations of the background management agent are included as binaries in the MeshCentral project.
Terminal protein structure viewer — interactive 3D visualization of PDB/mmCIF structures with cartoon ribbons, braille rendering, and Sixel/Kitty graphics
Qwen3.8-Flash-Next 176B on 2x CMP 170HX (128GB VRAM): PLE n-gram table via NVMe mmap, PP=2, 1M-token context, MTP spec-decode — vLLM patch set + launcher + benchmarks
Vulkan compute tool for testing video memory stability
High performance coding agent harness written in Rust, built for heavy multi-agent dev workflows
A spy satellite simulator in your browser, except the data is real. Live open source spatial intelligence on a photorealistic 3D globe.
DeepSeek-V4-Flash-0731 on 4x CMP 170HX (sm_80): 98 tok/s decode, ~5300 tok/s prefill. DSpark speculative decoding under pipeline parallelism, which vLLM does not support upstream.
Comp AI CRM is an open source, CRM designed for AI agents. Agentic-first CRM.