-
TeskaLabs
- London & Prague
- teskalabs.com
- @alesteska
- in/ateska
Highlights
- Pro
Lists (1)
Sort Name ascending (A-Z)
Starred repositories
Rust LLM inference engine for MoE models on NVIDIA unified memory (IBM AC922, DGX Spark). Runs GGUF and Hugging Face safetensors (NVFP4, FP8) as shipped, with speculative decoding, continuous batch…
AI gateway / AI control plane / AI proxy written in Go. Unified OpenAI-compatible and Anthropic-compatible API for OpenAI, Anthropic, Gemini, Groq, xAI, Ollama, vLLM and more. A LiteLLM alternative…
Re-created version of the 1993 game Warlords II. Three ports have been made: Web, C++ and Love2d.
Hindsight: Agent Memory That Learns
OpenShell is the safe, private runtime for autonomous AI agents.
Full-weight Qwen decision model with calibrated probabilities, training code, REST API, and playground.
Claude Code plugin that replaces the compaction summary with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verb…
Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per re…
Claude Code skill for managing a UniFi Dream Machine Pro via its local API
BEAR-C2 is an adversary simulation and emulation framework built around real-world TTPs inspired by Russian, Chinese, North Korean, and Iranian APT groups.
The set-and-forget LLM engine for Pascal and Volta: PXQ codec + kernels, auto-tuned per card. Ready-to-run PXQ models in MODELS.md; benchmarks vs llama.cpp in the README.
jasl / vllm
Forked from vllm-project/vllmA high-throughput and memory-efficient inference and serving engine for LLMs
Open-core SOAR platform for the autonomous SOC. Tier-1 triage agents, immutable audit, MCP portal for examiners. Built on SynapCores.
A plain-language writing skill for AI agents, with a revision view that shows what changed.
Set of EVTX samples (>270) mapped to MITRE ATT&CK tactic and techniques to measure your SIEM coverage or developed new use cases.
Accessible React loading states for generative interfaces: streamed text, inline activity, and image generation.
Agent Skills-compatible LLM wiki for Claude Code, Cursor, and Codex. Build a Karpathy-style knowledge base from raw sources, citations, and linting.
Skills for Real Engineers. Straight from my .agents directory.
A GRC Compliance tool for SaaS products to manage the entire lifecycle of security audits.
A community‑driven, SentinelOne‑assisted library of parsers, dashboards, detections & response playbooks that supercharge the Singularity Platform.
the optimized, token-efficient version of the leaked Claude Fable 5 / Mythos 5 system prompt. Re-engineered into clean Markdown for universal execution on Gemini 3.1 Pro, ChatGPT 5.6, and advanced …
A hypervisor and sandbox cloud for self-hosting AI agents and RL
OpenAI-compatible server with a live view into any HF model's residual stream. pip install brainscope