AI infrastructure

Sub-millisecond VM sandboxes for AI agents via copy-on-write forking

Train and run transformers directly on Apple's Neural Engine — 4.76x faster than CoreML.

A lightweight inference engine supporting speculative speculative decoding (SSD).

Training neural networks on Apple Neural Engine via reverse-engineered private APIs

Open-source AI Gateway written in Go, one API for OpenAI, Anthropic, Bedrock, Azure, and 100+ LLMs. Built-in caching, guardrails, retries, and cost optimization. Run as a proxy or embed as a library.

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 64 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

Fastest, smallest, and fully autonomous AI assistant infrastructure written in Zig

Route every request to the cheapest model that can handle it and save 70%+

LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar

OmniRoute is an AI gateway for multi-provider LLMs: an OpenAI-compatible endpoint with smart routing, load balancing, retries, and fallbacks. Add policies, rate limits, caching, and observability for reliable, cost-aware inference.

Open-source LLM router & AI cost optimizer. Routes simple prompts to cheap/local models, complex ones to premium — automatically. Drop-in OpenAI-compatible proxy for Claude Code, Codex, Cursor, OpenClaw. Saves 40-70% on AI API costs. Self-hosted, no middleman.

14-stage Fusion Pipeline for LLM token compression — reversible compression, AST-aware code analysis, intelligent content routing. Zero LLM inference cost. MIT licensed.

Krasis is a Hybrid LLM runtime which focuses on efficient running of larger models on consumer grade VRAM limited hardware

Decentralized AI inference for OpenClaw agents. Powered by Morpheus AI. Stake MOR, access Kimi K2.5 + 10 models, never run out of inference.

🛡️Decision infrastructure for AI agents. Intercept actions, enforce guard policies, require approvals, and produce audit-ready decision trails.

Track AI API quotas across Synthetic, Z.ai, Anthropic (Claude Code), Codex, GitHub Copilot & Antigravity in real time. Lightweight background daemon (<50MB RAM), SQLite storage, Material Design 3 dashboard. Zero telemetry.

Persistent memory graph for AI agents. Facts, decisions, entities, and relationships that survive across sessions, tools, and providers. MCP server — works with Claude, Cursor, ChatGPT, and any MCP client.

The agent-native LLM router for OpenClaw. 41+ models, <1ms routing, USDC payments on Base & Solana via x402.

🌟 Open Source AI Agent Security Infrastructure — intercepts and blocks dangerous agent behaviors before they happen. Just one command! Join us to build safer Human-AI Symbiosis!

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

Single-file memory layer for AI agents, sub mili-second RAG on Apple Silicon. Metal Optimized On-Device. No Server. No API. One File. Pure Swift