AI infrastructure
DeepSeek 4 Flash local inference engine for Metal
将运行在本地的 OpenCode 转换为 OpenAI 兼容 API ，以在任何 OpenAI 客户端中使用免费模型。
The ultimate collection of APIs for building autonomous AI agents — 2,036 production-ready APIs across Agents, AI Models, and MCP Servers. Stop wasting weeks building infrastructure. Plug these in and ship your agent today.
Garry's Opinionated OpenClaw/Hermes Agent Brain
TriAttention — Efficient long reasoning with trigonometric KV cache compression. Enables OpenClaw local deployment on memory-constrained GPUs.
Lucebox optimization hub: hand-tuned LLM inference, built for specific consumer hardware.
The open-source memory operating system for AI agents. Persistent memory, semantic search, loop detection, agent messaging, crash recovery, and real-time observability.
AI API identity gateway — reverse proxy that normalizes device fingerprints and telemetry for privacy-preserving API proxying
Awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration.
TurboQuant: Near-optimal KV cache quantization for LLM inference (3-bit keys, 2-bit values) with Triton kernels + vLLM integration
Zig INferenCe Engine — Local LLM inference on AMD GPUs and Apple Silicon
The open-source AI platform for enterprises that can't send data to the cloud. OpenAI-compatible API, full management dashboard, zero data egress.
Curated list of the best truly open-source AI projects, models, tools, and infrastructure.
OpsKat — Infrastructure Ops, Reimagined with AI
⚡ Native MLX Swift LLM inference server for Apple Silicon. OpenAI-compatible API, SSD streaming for 100B+ MoE models, TurboQuant KV cache compression, MACOS + iOS iPhone app.
Self-hosted AI Agent Memory + Code Intelligence Platform — one MCP endpoint for persistent memory, AST-aware code search, shared knowledge, and quality enforcement across all your AI coding agents.
Privacy-first LLM proxy and AI gateway — load balancing, multi-provider routing, API key management, usage tracking, rate limiting. Self-hosted. Zero knowledge of your prompts.
CORAL is a robust, lightweight infrastructure for multi-agent autonomous self-evolution, built for autoresearch.